A hybrid air quality early-warning framework: An hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms
Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hy...
Gespeichert in:
| Veröffentlicht in: | The Science of the total environment Jg. 709; S. 135934 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Netherlands
Elsevier B.V
20.03.2020
|
| Schlagworte: | |
| ISSN: | 0048-9697, 1879-1026, 1879-1026 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM2.5; Particulate Matter 10, PM10 and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM2.5, PM10, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash–Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM2.5,ELM values ranged from 0.65–0.82 vs. 0.59–0.77 for ICEEMDAN-M5 tree, 0.59–0.74 for ICEEMDAN-MLR, 0.28–0.54 for OS-ELM, 0.27–0.54 for M5 tree and 0.25–0.53 for the MLR model. For remaining air quality variables (i.e., PM10 & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7–1.03 μg/m3(MAE), 1.01–1.47 μg/m3(RMSE) for PM2.5 whereas for PM10, these metrics registered a value of 1.29–3.84 μg/m3(MAE), 3.01–7.04 μg/m3(RMSE) and for Visibility, they were 0.01–3.72 μg/m3 (MAE (Mm−1)), 0.04–5.98 μg/m3 (RMSE (Mm−1)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation.
[Display omitted]
•An artificial intelligence predictive framework devised for air quality prediction.•Efficient forecasting of air quality with 5 modelling approaches was recorded.•OS-ELM coupled with ICEEMDAN outperformed the other models.•AI models show potential in health informatics and Australia's environment sector.•AI models can empower public health risk mitigation to a create liveable society. |
|---|---|
| AbstractList | Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM₂.₅; Particulate Matter 10, PM₁₀ and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM₂.₅, PM₁₀, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash–Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM₂.₅,ELM values ranged from 0.65–0.82 vs. 0.59–0.77 for ICEEMDAN-M5 tree, 0.59–0.74 for ICEEMDAN-MLR, 0.28–0.54 for OS-ELM, 0.27–0.54 for M5 tree and 0.25–0.53 for the MLR model. For remaining air quality variables (i.e., PM₁₀ & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7–1.03 μg/m³(MAE), 1.01–1.47 μg/m³(RMSE) for PM₂.₅ whereas for PM₁₀, these metrics registered a value of 1.29–3.84 μg/m³(MAE), 3.01–7.04 μg/m³(RMSE) and for Visibility, they were 0.01–3.72 μg/m³ (MAE (Mm⁻¹)), 0.04–5.98 μg/m³ (RMSE (Mm⁻¹)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation. Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM2.5; Particulate Matter 10, PM10 and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM2.5, PM10, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash-Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM2.5,ELM values ranged from 0.65-0.82 vs. 0.59-0.77 for ICEEMDAN-M5 tree, 0.59-0.74 for ICEEMDAN-MLR, 0.28-0.54 for OS-ELM, 0.27-0.54 for M5 tree and 0.25-0.53 for the MLR model. For remaining air quality variables (i.e., PM10 & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7-1.03 μg/m3(MAE), 1.01-1.47 μg/m3(RMSE) for PM2.5 whereas for PM10, these metrics registered a value of 1.29-3.84 μg/m3(MAE), 3.01-7.04 μg/m3(RMSE) and for Visibility, they were 0.01-3.72 μg/m3 (MAE (Mm-1)), 0.04-5.98 μg/m3 (RMSE (Mm-1)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation.Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM2.5; Particulate Matter 10, PM10 and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM2.5, PM10, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash-Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM2.5,ELM values ranged from 0.65-0.82 vs. 0.59-0.77 for ICEEMDAN-M5 tree, 0.59-0.74 for ICEEMDAN-MLR, 0.28-0.54 for OS-ELM, 0.27-0.54 for M5 tree and 0.25-0.53 for the MLR model. For remaining air quality variables (i.e., PM10 & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7-1.03 μg/m3(MAE), 1.01-1.47 μg/m3(RMSE) for PM2.5 whereas for PM10, these metrics registered a value of 1.29-3.84 μg/m3(MAE), 3.01-7.04 μg/m3(RMSE) and for Visibility, they were 0.01-3.72 μg/m3 (MAE (Mm-1)), 0.04-5.98 μg/m3 (RMSE (Mm-1)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation. Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM2.5; Particulate Matter 10, PM10 and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM2.5, PM10, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash–Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM2.5,ELM values ranged from 0.65–0.82 vs. 0.59–0.77 for ICEEMDAN-M5 tree, 0.59–0.74 for ICEEMDAN-MLR, 0.28–0.54 for OS-ELM, 0.27–0.54 for M5 tree and 0.25–0.53 for the MLR model. For remaining air quality variables (i.e., PM10 & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7–1.03 μg/m3(MAE), 1.01–1.47 μg/m3(RMSE) for PM2.5 whereas for PM10, these metrics registered a value of 1.29–3.84 μg/m3(MAE), 3.01–7.04 μg/m3(RMSE) and for Visibility, they were 0.01–3.72 μg/m3 (MAE (Mm−1)), 0.04–5.98 μg/m3 (RMSE (Mm−1)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation. [Display omitted] •An artificial intelligence predictive framework devised for air quality prediction.•Efficient forecasting of air quality with 5 modelling approaches was recorded.•OS-ELM coupled with ICEEMDAN outperformed the other models.•AI models show potential in health informatics and Australia's environment sector.•AI models can empower public health risk mitigation to a create liveable society. Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM ; Particulate Matter 10, PM and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM , PM , and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (E ) and Nash-Sutcliffe coefficients (E ) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM E values ranged from 0.65-0.82 vs. 0.59-0.77 for ICEEMDAN-M5 tree, 0.59-0.74 for ICEEMDAN-MLR, 0.28-0.54 for OS-ELM, 0.27-0.54 for M5 tree and 0.25-0.53 for the MLR model. For remaining air quality variables (i.e., PM & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7-1.03 μg/m (MAE), 1.01-1.47 μg/m (RMSE) for PM whereas for PM , these metrics registered a value of 1.29-3.84 μg/m (MAE), 3.01-7.04 μg/m (RMSE) and for Visibility, they were 0.01-3.72 μg/m (MAE (Mm )), 0.04-5.98 μg/m (RMSE (Mm )). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation. |
| ArticleNumber | 135934 |
| Author | Deo, Ravinesh C. Parisi, Alfio V. Sharma, Ekta Prasad, Ramendra |
| Author_xml | – sequence: 1 givenname: Ekta surname: Sharma fullname: Sharma, Ekta email: ekta.sharma@usq.edu.au organization: Advanced Data Analytics: Environmental Modelling and Simulation Group, School of Sciences, University of Southern Queensland, Springfield, QLD 4300, Australia – sequence: 2 givenname: Ravinesh C. orcidid: 0000-0002-2290-6749 surname: Deo fullname: Deo, Ravinesh C. email: ravinesh.deo@usq.edu.au organization: Advanced Data Analytics: Environmental Modelling and Simulation Group, School of Sciences, University of Southern Queensland, Springfield, QLD 4300, Australia – sequence: 3 givenname: Ramendra surname: Prasad fullname: Prasad, Ramendra organization: Department of Science, School of Science and Technology, The University of Fiji, Fiji – sequence: 4 givenname: Alfio V. surname: Parisi fullname: Parisi, Alfio V. email: alfio.parisi@usq.edu.au organization: Advanced Data Analytics: Environmental Modelling and Simulation Group, School of Sciences, University of Southern Queensland, Springfield, QLD 4300, Australia |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31869708$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkctu1DAUhi1URKeFVwAv2WSwY8dxkFiMKm5SJTawjhznpOPBl6ntdJgX4jlxNEMXbKg3luzv_6Vzvit04YMHhN5QsqaEine7ddImhwz-YV0T2q0pazrGn6EVlW1XUVKLC7QihMuqE117ia5S2pFyWklfoEtGZXklcoV-b_D2OEQzYmUivp-VNfmIQUV7rA4qeuPv8BSVg0OIP9_jjcfbMJdPPIUIWqW8AC6MYPHB5C0O3hoPOMH9DD4bZTH8yhEcYAvnOqf0tjAJKz9icHsTjS7cUoJH0MHtQzLZBI-VvQuxtLr0Ej2flE3w6nxfox-fPn6_-VLdfvv89WZzW2lOeK5a0GMD7TBIPgzNJLSAWitoNKsV12V6wYSkQvKW03aQepoaQdgwkEbRmk3ArtHbU-8-hjJByr0zSYO1ykOYU18zKVvJRc2fgDLCWEtFU9DXZ3QeHIz9Phqn4rH_q6EA7QnQMaQUYXpEKOkX4f2ufxTeL8L7k_CS_PBPsmBq2V6Oytgn5DenPJStPhiICwdew2iK39yPwfy34w9lttGV |
| CitedBy_id | crossref_primary_10_1007_s11063_023_11332_y crossref_primary_10_3390_rs14030805 crossref_primary_10_1016_j_engappai_2022_105352 crossref_primary_10_1007_s00477_022_02231_0 crossref_primary_10_1016_j_envpol_2021_116429 crossref_primary_10_1007_s11356_021_17442_1 crossref_primary_10_1155_2022_7632841 crossref_primary_10_1016_j_envint_2025_109389 crossref_primary_10_1007_s00477_024_02693_4 crossref_primary_10_2478_amns_2023_2_00477 crossref_primary_10_1371_journal_pone_0284811 crossref_primary_10_1002_for_3218 crossref_primary_10_3390_atmos12010064 crossref_primary_10_1016_j_apr_2020_06_028 crossref_primary_10_1016_j_jclepro_2022_133383 crossref_primary_10_1155_2020_9427102 crossref_primary_10_1007_s11356_022_22601_z crossref_primary_10_1016_j_knosys_2021_107379 crossref_primary_10_1088_1755_1315_616_1_012002 crossref_primary_10_3390_systems12020039 crossref_primary_10_1016_j_jclepro_2020_122824 crossref_primary_10_1016_j_apr_2024_102273 crossref_primary_10_1016_j_jag_2025_104368 crossref_primary_10_1016_j_scitotenv_2023_161744 crossref_primary_10_1016_j_uclim_2024_101985 crossref_primary_10_1016_j_jastp_2025_106461 crossref_primary_10_1007_s11869_020_00817_7 crossref_primary_10_1088_1742_6596_2136_1_012063 crossref_primary_10_3390_su14095394 crossref_primary_10_3390_app112412014 crossref_primary_10_1109_ACCESS_2021_3076345 crossref_primary_10_1016_j_jclepro_2020_121027 crossref_primary_10_1016_j_oceaneng_2022_112258 crossref_primary_10_1016_j_scitotenv_2021_149654 crossref_primary_10_1016_j_knosys_2021_107789 crossref_primary_10_1109_ACCESS_2020_3039002 crossref_primary_10_1016_j_asoc_2020_106957 crossref_primary_10_1016_j_compbiomed_2022_105529 crossref_primary_10_1155_2022_3973665 crossref_primary_10_1016_j_atmosenv_2025_121079 crossref_primary_10_1016_j_apr_2023_101752 crossref_primary_10_1016_j_jclepro_2021_129500 crossref_primary_10_1007_s11600_021_00678_3 crossref_primary_10_1016_j_apr_2022_101426 crossref_primary_10_1016_j_psep_2022_05_055 crossref_primary_10_1016_j_apr_2021_101144 crossref_primary_10_1016_j_jclepro_2022_130414 crossref_primary_10_3389_fenvs_2021_747101 crossref_primary_10_1016_j_chemosphere_2022_136252 crossref_primary_10_1007_s12517_022_09578_2 crossref_primary_10_1016_j_compbiomed_2025_110566 crossref_primary_10_3390_en15010147 crossref_primary_10_1007_s00477_021_01969_3 crossref_primary_10_3390_rs14051136 crossref_primary_10_1016_j_jhydrol_2021_126350 crossref_primary_10_3390_environments11060107 crossref_primary_10_1016_j_jclepro_2020_124469 crossref_primary_10_1111_exsy_13449 crossref_primary_10_1109_ACCESS_2024_3401091 crossref_primary_10_3390_cli11090188 crossref_primary_10_1016_j_measurement_2023_112954 crossref_primary_10_1155_2022_1206405 crossref_primary_10_1007_s12161_021_02048_7 crossref_primary_10_1007_s11869_022_01261_5 crossref_primary_10_1016_j_jclepro_2020_124023 crossref_primary_10_1016_j_uclim_2025_102359 crossref_primary_10_3390_atmos13091456 crossref_primary_10_1007_s10462_023_10424_4 crossref_primary_10_1109_ACCESS_2022_3210974 crossref_primary_10_3390_s24051532 crossref_primary_10_1016_j_apr_2021_101153 crossref_primary_10_1016_j_atmosenv_2022_119111 crossref_primary_10_1016_j_scitotenv_2023_167234 crossref_primary_10_1016_j_energy_2022_125609 crossref_primary_10_1016_j_apenergy_2023_121607 |
| Cites_doi | 10.13031/2013.29502 10.1029/2003WR002355 10.1109/TNN.2006.880583 10.1016/j.chemolab.2014.02.007 10.1016/j.atmosenv.2008.09.067 10.1097/01.ede.0000112210.68754.fa 10.1016/j.enconman.2014.12.015 10.1007/s11269-014-0638-7 10.1080/10473289.2003.10466276 10.1016/j.healthplace.2009.10.007 10.2166/wst.2013.222 10.1002/joc.2419 10.1093/aje/kwg096 10.1080/02626669909492273 10.1061/(ASCE)1084-0699(2003)8:6(319) 10.1029/1998WR900018 10.1016/j.enconman.2014.12.050 10.1007/s11269-013-0440-y 10.1016/0957-1272(92)90041-P 10.1016/j.bspc.2014.06.009 10.1016/j.geoderma.2018.05.035 10.1371/journal.pone.0201011 10.1016/j.envsoft.2006.06.008 10.1016/0022-1694(70)90255-6 10.1016/j.neucom.2011.12.064 10.1289/ehp.1001991 10.1016/j.neucom.2009.02.013 10.1016/j.matcom.2008.01.028 10.1289/ehp.1002203 10.1097/01.ede.0000101023.41844.ac 10.1002/tqem.21464 10.1289/ehp.1103898 10.1016/j.atmosenv.2016.01.034 10.1007/s10661-016-5094-9 10.1016/j.measurement.2016.06.042 10.1016/j.atmosres.2015.03.018 10.5194/gmd-7-1247-2014 10.1007/s11869-017-0477-9 10.1007/s00484-006-0054-7 10.1080/02723646.1981.10642213 10.1016/j.atmosres.2013.11.002 10.3390/e19070380 10.1016/j.envint.2014.10.005 10.1016/j.atmosres.2018.07.005 10.1016/j.atmosenv.2014.11.050 10.1016/j.atmosenv.2006.04.052 10.1016/j.apenergy.2019.113541 10.1016/j.simpat.2007.09.005 10.1016/1352-2310(94)00278-S 10.1016/j.biosystemseng.2009.12.011 10.1109/TSTE.2014.2365580 10.1016/S1352-2310(99)00091-6 10.1029/2002JD002914 10.1016/j.atmosenv.2005.11.076 10.1016/j.atmosenv.2004.02.026 10.1007/s11783-014-0634-4 10.1016/j.rser.2019.01.014 10.1001/jama.295.10.1127 10.1016/j.scitotenv.2018.01.195 10.5694/j.1326-5377.2002.tb04982.x 10.1016/j.engappai.2004.02.002 10.1080/10473289.1997.10463923 10.1098/rspa.1998.0193 10.1016/j.neucom.2004.04.016 10.3390/en12122407 10.1016/j.envsoft.2005.12.002 10.1136/oem.2004.014282 10.1142/S1793536909000047 10.1142/S1793536912500252 10.1080/10473289.2001.10464254 10.1016/j.atmosenv.2014.11.049 10.1016/j.neunet.2010.09.008 10.1016/j.envres.2017.07.044 10.1016/S1672-6529(11)60020-6 10.1007/s00477-016-1265-z 10.1016/S1352-2310(98)00352-5 10.5094/APR.2013.049 10.1073/pnas.1102467108 10.1007/s004840050108 10.1080/01431160701241738 10.1175/1520-0477(1982)063<1309:SCOTEO>2.0.CO;2 10.1161/CIR.0b013e3181dbece1 10.1097/00001648-199903000-00006 10.1007/s11269-016-1288-8 10.1097/EDE.0b013e3181c15d5a 10.1016/j.atmosenv.2019.01.027 10.1142/S1793536910000422 10.1061/(ASCE)0887-3801(1994)8:2(201) 10.2166/hydro.2013.134 10.1016/j.apenergy.2016.01.130 10.1016/j.apenergy.2018.02.140 10.5194/acp-12-1-2012 10.5194/adgeo-5-89-2005 10.1016/1352-2310(96)00085-4 10.5194/hess-8-940-2004 10.1155/2016/8301962 10.1016/j.scitotenv.2010.12.040 10.1016/j.envres.2015.09.007 10.1080/10962247.2014.934484 10.1016/j.knosys.2018.10.036 10.1007/s00376-012-1259-9 10.1016/j.scitotenv.2014.07.051 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. Copyright © 2019 Elsevier B.V. All rights reserved. |
| Copyright_xml | – notice: 2019 Elsevier B.V. – notice: Copyright © 2019 Elsevier B.V. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 7S9 L.6 |
| DOI | 10.1016/j.scitotenv.2019.135934 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Public Health Biology Environmental Sciences |
| EISSN | 1879-1026 |
| ExternalDocumentID | 31869708 10_1016_j_scitotenv_2019_135934 S0048969719359297 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5VS 7-5 71M 8P~ 9JM AABNK AACTN AAEDT AAEDW AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO ABFNM ABFYP ABJNI ABLST ABMAC ACDAQ ACGFS ACRLP ADBBV ADEZE AEBSH AEIPS AEKER AENEX AFTJW AFXIZ AGUBO AGYEJ AHEUO AHHHB AIEXJ AIKHN AITUG AKIFW AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AXJTR BKOJK BLECG BLXMC BNPGV CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W K-O KCYFY KOM LY9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SCU SDF SDG SDP SES SPCBC SSH SSJ SSZ T5K ~02 ~G- ~KM 53G 9DU AAQXK AAYJJ AAYWO AAYXX ABEFU ABWVN ABXDB ACLOT ACRPL ACVFH ADCNI ADMUD ADNMO ADXHL AEGFY AEUPX AFJKZ AFPUW AGHFR AGQPQ AIGII AIIUN AKBMS AKYEP APXCP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB G-2 HMC HVGLF HZ~ R2- SEN SEW WUQ XPP ZXP ZY4 ~HD AFKWA AJOXV AMFUW NPM 7X8 7S9 L.6 |
| ID | FETCH-LOGICAL-c404t-7ecd5e7bb84bb5f6c6e2cae5c32a4c007636816847417b8cff5603bb05a123fe3 |
| ISICitedReferencesCount | 72 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000512281700035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0048-9697 1879-1026 |
| IngestDate | Thu Oct 02 19:24:19 EDT 2025 Sun Sep 28 09:11:39 EDT 2025 Wed Feb 19 02:31:25 EST 2025 Sat Nov 29 07:25:17 EST 2025 Tue Nov 18 22:02:17 EST 2025 Sun Apr 06 06:53:47 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | r2 VIS D FDMS μg/m3 ELM Qld ENS NEPH NEPM SD D-TEOM WI MLR CHAG PM2.5 CEEMDAN EEMD BMA ICEEMDAN EMD WHO DERM PM2.5, iFOR AI OS-ELM TEOM RMSE Real-time air quality forecasts ppm BAM AQ MAE μm PACF r PM2.5, iOBS OEH IMFs NSW PM10 Particulate matter (PM2.5, PM10) Visibility DoE Artificial intelligence Particulate matter (PM(2.5), PM) |
| Language | English |
| License | Copyright © 2019 Elsevier B.V. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c404t-7ecd5e7bb84bb5f6c6e2cae5c32a4c007636816847417b8cff5603bb05a123fe3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-2290-6749 |
| PMID | 31869708 |
| PQID | 2330337165 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2388784624 proquest_miscellaneous_2330337165 pubmed_primary_31869708 crossref_primary_10_1016_j_scitotenv_2019_135934 crossref_citationtrail_10_1016_j_scitotenv_2019_135934 elsevier_sciencedirect_doi_10_1016_j_scitotenv_2019_135934 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-03-20 |
| PublicationDateYYYYMMDD | 2020-03-20 |
| PublicationDate_xml | – month: 03 year: 2020 text: 2020-03-20 day: 20 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | The Science of the total environment |
| PublicationTitleAlternate | Sci Total Environ |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Mohammadi, Shamshirband, Anisi, Alam, Petković (bb0425) 2015; 91 OEH N (bb0465) 2019 Ghimire, Deo, Raj, Mi (bb0215) 2019; 253 Karunanithi, Grenney, Whitley, Bovee (bb0315) 1994; 8 Witten, Frank, Hall (bb0605) 2011 Foresee, Hagan (bb0200) 1997; 3 Glinianaia, Rankin, Bell, Pless-Mulloli, Howel (bb0230) 2004; 15 Deo, Tiwari, Adamowski, Quilty (bb0160) 2016; 31 Wang, Xu, Chau, Chen (bb0580) 2013; 15 Hess, Cope, Lee, Manins, Mills, Puri (bb0260) 2000; 13 Ren, Suganthan, Srikanth (bb0510) 2015; 6 Colominas, Schlotthauer, Torres (bb0125) 2014; 14 NPE (bb0460) 2016; 1 Zhou, Fu, Zhuang, Levy (bb0655) 2010; 118 Zhou, Jiang, Wang, Zhou (bb0660) 2014; 496 Smith, Kolenikov, Cox (bb0545) 2003; 108 Liu, Wang, Chen, Dong, Zhu, Wang (bb0405) 2011; 8 Roberts (bb0515) 2013; 182 Al-Musaylh, Deo, Li, Adamowski (bb0040) 2018; 217 Kisi, Parmar, Soni, Demir (bb0340) 2017; 10 Wu, Huang (bb0620) 2009; 1 DERM (bb0175) 2011 Banhazi, Rutley, Pitchford (bb0055) 2010; 105 Bowman (bb0070) 2000 Leitte, Schlink, Herbarth, Wiedensohler, Pan, Hu (bb0380) 2011; 119 Kim, Kim, Kim, Lee, Han (bb0330) 2006; 40 Kim, Valdés (bb0325) 2003; 8 Loomis, Castillejos, Gold, McDonnell, Borja-Aburto (bb0410) 1999 Lan, Soh, Huang (bb0365) 2009; 72 Nan-Ying, Guang-Bin, Saratchandran, Sundararajan (bb0440) 2006; 17 AIHW, Vos, Barker, Stevenson, Stanley, Lopez (bb0015) 2007; 337 Ren, Tong (bb0505) 2006; 51 Haupt, Pasini, Marzban (bb0255) 2008 Byrne, Sipe, Dodson (bb0085) 2014 Higginbotham, Freeman, Connor, Albrecht (bb0265) 2010; 16 Silva-Ramírez, Pino-Mejías, López-Coello, Cubiles-de-la-Vega (bb0535) 2011; 24 Chung, Chang, Kleeman, Perry, Cahill, Dutcher (bb0115) 2001; 51 Chai, Draxler (bb0090) 2014; 7 Mohammadi, Shamshirband, Tong, Arif, Petković, Ch (bb0430) 2015; 92 Schauer, Rogge, Hildemann, Mazurek, Cass, Simoneit (bb0525) 1996; 30 Anctil, Lauzon (bb0045) 2004; 8 Due, Watt, Salter, Trieu (bb0190) 2013 Ouyang, Lu, Xin, Zhang, Cheng, Yu (bb0480) 2016; 30 Kjellstrom, Neller, Simpson (bb0345) 2002; 177 Confalonieri, Menne, Akhtar, Ebi, Hauengue, Kovats (bb0130) 2007 Kim, Kabir, Kabir (bb0335) 2015; 74 HVRA (bb0275) 2009 Glikson, Rutherford, Simpson, Mitchell, Yago (bb0225) 1995; 29 Asadollahfardi, Madinejad, Aria, Motamadi (bb0050) 2016; 25 Li, Li (bb0385) 2016; 2016 Brook, Rajagopalan, Pope, Brook, Bhatnagar, Diez-Roux (bb0075) 2010; 121 Kukkonen, Olsson, Schultz, Baklanov, Klein, Miranda (bb0360) 2012; 12 Walsh (bb0570) 2014; 8 Al-Musaylh, Deo, Adamowski, Li (bb0035) 2018; 17 Fu, Nunifu, Leung (bb0205) 2014; 64 Mishra, Goyal, Upadhyay (bb0420) 2015; 102 Bateson, Schwartz (bb0060) 2004; 15 Willmott (bb0590) 1982; 63 Willmott (bb0595) 1984 Willmott, Robeson, Matsuura (bb0600) 2012; 32 Yadav, Ch, Mathur, Adamowski (bb0630) 2016; 92 Hyslop (bb0280) 2009; 43 Gille, Russell, Bailey, House, Flowers, McCormick (bb0220) 2017 Xiaoli, Chengwei (bb0625) 2017; 19 Huang Norden, Shen, Long Steven, Wu Manli, Shih Hsing, Zheng (bb0270) 1998; 454 Allen, Sioutas, Koutrakis, Reiss, Lurmann, Roberts (bb0030) 1997; 47 Deo, Wen, Qi (bb0165) 2016; 168 Ghimire, Deo, Raj, Mi (bb0210) 2019; 12 Rutherford, Clark, McTainsh, Simpson, Mitchell (bb0520) 1999; 42 Deo, Tiwari, Adamowski, Quilty (bb0170) 2017; 31 Mannes, Jalaludin, Morgan, Lincoln, Sheppeard, Corbett (bb0415) 2005; 62 Karatzas, Kaltsatos (bb0310) 2007; 15 Oprea, Mihalache, Popescu (bb0475) 2016 Gupta, Christopher, Box, Box (bb0245) 2007; 28 Pereira, Lee, Bell, Regan, Malacova, Mullins (bb0485) 2017; 159 Zhao, Che, Zhang, Ma, Wang, Wang (bb0645) 2013; 4 Rea, Paton-Walsh, Turquety, Cope, Griffith (bb0500) 2016; 131 Abbot, Marohasy (bb0005) 2012; 29 Colominas, Schlotthauer, Torres, Flandrin (bb0120) 2012; 4 Wang, Witten (bb0575) 1997 Li, Zhu (bb0390) 2018; 626 Legates, McCabe (bb0375) 1999; 35 Dominici, Peng, Bell, Pham, McDermott, Zeger (bb0185) 2006; 295 Chen, Jakeman, Norton (bb0105) 2008; 78 Rahimikhoob, Asadi, Mashal (bb0495) 2013; 27 Wu, Huang (bb0615) 2009; 1 CSIRO and Bureau of Meteorology (bb0135) 2015 O’Neill, Zanobetti, Schwartz (bb0470) 2003; 157 Niska, Hiltunen, Karppinen, Ruuskanen, Kolehmainen (bb0455) 2004; 17 Chen, Zhang, Zhang, Zhu, Yang, Chen (bb0110) 2019; 202 Dawson, Abrahart, See (bb0145) 2007; 22 Simpson (bb0540) 1992; 26 Abbot, Marohasy (bb0010) 2014; 138 Bhattacharya, Solomatine (bb0065) 2005; 63 Jain, Srinivasulu (bb0285) 2004; 40 Chan, Simpson, Mctainsh, Vowles, Cohen, Bailey (bb0100) 1999; 33 Sousa, Martins, Alvim-Ferraz, Pereira (bb0550) 2007; 22 Zhao, Gu, Xue, Zhang, Ren (bb0650) 2018; 13 Kaufmann, Kauppi, Mann, Stock (bb0320) 2011; 108 Ali, Prasad (bb0020) 2019; 104 Harmel, Smith, Migliaccio (bb0250) 2010; 53 Liang, Huang, Saratchandran, Sundararajan (bb0395) 2006; 17 Morgan, Sheppeard, Khalaj, Ayyar, Lincoln, Jalaludin (bb0435) 2010 Ali, Deo, Downs, Maraseni (bb0025) 2018; 213 Krzyzanowski, Bundeshaus, Negru, Salvi (bb0355) 2005; 4 Junninen, Niska, Tuppurainen, Ruuskanen, Kolehmainen (bb0305) 2004; 38 Vlachogianni, Kassomenos, Karppinen, Karakitsios, Kukkonen (bb0565) 2011; 409 Ye, Squartini, Piazza (bb0635) 2013; 116 Chaloulakou, Grivas, Spyrellis (bb0095) 2003; 53 Nash, Sutcliffe (bb0445) 1970; 10 Wu, Huang (bb0610) 2009; 1 Langrish, Li, Wang, Lee, Barnes, Miller (bb0370) 2012; 120 Gómez-Carracedo, Andrade, López-Mahía, Muniategui, Prada (bb0235) 2014; 134 Lin, Pai, Yang (bb0400) 2011; 217 Sun, Bertrand-Krajewski (bb0555) 2013; 68 CWA (bb0140) 2018 Uhlenbrook, Seibert, Leibundgut, Rodhe (bb0560) 1999; 44 Broome, Fann, Cristina, Fulcher, Duc, Morgan (bb0080) 2015; 143 Krause, Boyle, Bäse (bb0350) 2005; 5 Deo, Şahin (bb0155) 2016; 188 Jiang, Li, Li, Yang (bb0295) 2019; 164 Deo, Şahin (bb0150) 2015; 161–162 Yeh, Shieh, Huang (bb0640) 2010; 2 Willmott (bb0585) 1981; 2 Sehgal, Tiwari, Chatterjee (bb0530) 2014; 28 Prasad, Deo, Li, Maraseni (bb0490) 2018; 330 Junger, Ponce de Leon (bb0300) 2015; 102 Green, Fuller (bb0240) 2006; 40 DoE Q (bb0180) 2019 Nenes, Pandis, Pilinis (bb0450) 1999; 33 EJA (bb0195) 2016 James, Witten, Hastie, Tibshirani (bb0290) 2013; 112 Deo (10.1016/j.scitotenv.2019.135934_bb0160) 2016; 31 Liu (10.1016/j.scitotenv.2019.135934_bb0405) 2011; 8 Simpson (10.1016/j.scitotenv.2019.135934_bb0540) 1992; 26 Wu (10.1016/j.scitotenv.2019.135934_bb0615) 2009; 1 Junger (10.1016/j.scitotenv.2019.135934_bb0300) 2015; 102 Nan-Ying (10.1016/j.scitotenv.2019.135934_bb0440) 2006; 17 Pereira (10.1016/j.scitotenv.2019.135934_bb0485) 2017; 159 Mohammadi (10.1016/j.scitotenv.2019.135934_bb0425) 2015; 91 Oprea (10.1016/j.scitotenv.2019.135934_bb0475) 2016 Anctil (10.1016/j.scitotenv.2019.135934_bb0045) 2004; 8 Fu (10.1016/j.scitotenv.2019.135934_bb0205) 2014; 64 HVRA (10.1016/j.scitotenv.2019.135934_bb0275) 2009 Colominas (10.1016/j.scitotenv.2019.135934_bb0120) 2012; 4 Haupt (10.1016/j.scitotenv.2019.135934_bb0255) 2008 Ren (10.1016/j.scitotenv.2019.135934_bb0510) 2015; 6 Yadav (10.1016/j.scitotenv.2019.135934_bb0630) 2016; 92 Zhou (10.1016/j.scitotenv.2019.135934_bb0655) 2010; 118 Leitte (10.1016/j.scitotenv.2019.135934_bb0380) 2011; 119 Banhazi (10.1016/j.scitotenv.2019.135934_bb0055) 2010; 105 Junninen (10.1016/j.scitotenv.2019.135934_bb0305) 2004; 38 CSIRO and Bureau of Meteorology (10.1016/j.scitotenv.2019.135934_bb0135) 2015 Bateson (10.1016/j.scitotenv.2019.135934_bb0060) 2004; 15 Jiang (10.1016/j.scitotenv.2019.135934_bb0295) 2019; 164 Chen (10.1016/j.scitotenv.2019.135934_bb0110) 2019; 202 Sun (10.1016/j.scitotenv.2019.135934_bb0555) 2013; 68 Gupta (10.1016/j.scitotenv.2019.135934_bb0245) 2007; 28 Colominas (10.1016/j.scitotenv.2019.135934_bb0125) 2014; 14 Mishra (10.1016/j.scitotenv.2019.135934_bb0420) 2015; 102 CWA (10.1016/j.scitotenv.2019.135934_bb0140) 2018 Ali (10.1016/j.scitotenv.2019.135934_bb0025) 2018; 213 Kjellstrom (10.1016/j.scitotenv.2019.135934_bb0345) 2002; 177 Lan (10.1016/j.scitotenv.2019.135934_bb0365) 2009; 72 Due (10.1016/j.scitotenv.2019.135934_bb0190) 2013 Deo (10.1016/j.scitotenv.2019.135934_bb0155) 2016; 188 Wu (10.1016/j.scitotenv.2019.135934_bb0610) 2009; 1 DERM (10.1016/j.scitotenv.2019.135934_bb0175) 2011 Jain (10.1016/j.scitotenv.2019.135934_bb0285) 2004; 40 Ren (10.1016/j.scitotenv.2019.135934_bb0505) 2006; 51 Broome (10.1016/j.scitotenv.2019.135934_bb0080) 2015; 143 Rea (10.1016/j.scitotenv.2019.135934_bb0500) 2016; 131 Li (10.1016/j.scitotenv.2019.135934_bb0385) 2016; 2016 Krzyzanowski (10.1016/j.scitotenv.2019.135934_bb0355) 2005; 4 AIHW (10.1016/j.scitotenv.2019.135934_bb0015) 2007; 337 Ali (10.1016/j.scitotenv.2019.135934_bb0020) 2019; 104 Loomis (10.1016/j.scitotenv.2019.135934_bb0410) 1999 Gille (10.1016/j.scitotenv.2019.135934_bb0220) 2017 James (10.1016/j.scitotenv.2019.135934_bb0290) 2013; 112 DoE Q (10.1016/j.scitotenv.2019.135934_bb0180) 2019 Smith (10.1016/j.scitotenv.2019.135934_bb0545) 2003; 108 Bhattacharya (10.1016/j.scitotenv.2019.135934_bb0065) 2005; 63 Chan (10.1016/j.scitotenv.2019.135934_bb0100) 1999; 33 Harmel (10.1016/j.scitotenv.2019.135934_bb0250) 2010; 53 Silva-Ramírez (10.1016/j.scitotenv.2019.135934_bb0535) 2011; 24 Krause (10.1016/j.scitotenv.2019.135934_bb0350) 2005; 5 O’Neill (10.1016/j.scitotenv.2019.135934_bb0470) 2003; 157 Chung (10.1016/j.scitotenv.2019.135934_bb0115) 2001; 51 Deo (10.1016/j.scitotenv.2019.135934_bb0170) 2017; 31 Bowman (10.1016/j.scitotenv.2019.135934_bb0070) 2000 Kim (10.1016/j.scitotenv.2019.135934_bb0335) 2015; 74 Deo (10.1016/j.scitotenv.2019.135934_bb0165) 2016; 168 Huang Norden (10.1016/j.scitotenv.2019.135934_bb0270) 1998; 454 Liang (10.1016/j.scitotenv.2019.135934_bb0395) 2006; 17 Lin (10.1016/j.scitotenv.2019.135934_bb0400) 2011; 217 Rahimikhoob (10.1016/j.scitotenv.2019.135934_bb0495) 2013; 27 Mannes (10.1016/j.scitotenv.2019.135934_bb0415) 2005; 62 Glikson (10.1016/j.scitotenv.2019.135934_bb0225) 1995; 29 Abbot (10.1016/j.scitotenv.2019.135934_bb0005) 2012; 29 Roberts (10.1016/j.scitotenv.2019.135934_bb0515) 2013; 182 Dawson (10.1016/j.scitotenv.2019.135934_bb0145) 2007; 22 Wang (10.1016/j.scitotenv.2019.135934_bb0580) 2013; 15 Gómez-Carracedo (10.1016/j.scitotenv.2019.135934_bb0235) 2014; 134 Brook (10.1016/j.scitotenv.2019.135934_bb0075) 2010; 121 Willmott (10.1016/j.scitotenv.2019.135934_bb0600) 2012; 32 Zhao (10.1016/j.scitotenv.2019.135934_bb0645) 2013; 4 Karunanithi (10.1016/j.scitotenv.2019.135934_bb0315) 1994; 8 Witten (10.1016/j.scitotenv.2019.135934_bb0605) 2011 Abbot (10.1016/j.scitotenv.2019.135934_bb0010) 2014; 138 Allen (10.1016/j.scitotenv.2019.135934_bb0030) 1997; 47 Willmott (10.1016/j.scitotenv.2019.135934_bb0595) 1984 Zhou (10.1016/j.scitotenv.2019.135934_bb0660) 2014; 496 Al-Musaylh (10.1016/j.scitotenv.2019.135934_bb0035) 2018; 17 Kisi (10.1016/j.scitotenv.2019.135934_bb0340) 2017; 10 Sousa (10.1016/j.scitotenv.2019.135934_bb0550) 2007; 22 Nash (10.1016/j.scitotenv.2019.135934_bb0445) 1970; 10 Al-Musaylh (10.1016/j.scitotenv.2019.135934_bb0040) 2018; 217 Morgan (10.1016/j.scitotenv.2019.135934_bb0435) 2010 Wang (10.1016/j.scitotenv.2019.135934_bb0575) 1997 Kaufmann (10.1016/j.scitotenv.2019.135934_bb0320) 2011; 108 Dominici (10.1016/j.scitotenv.2019.135934_bb0185) 2006; 295 OEH N (10.1016/j.scitotenv.2019.135934_bb0465) 2019 Willmott (10.1016/j.scitotenv.2019.135934_bb0590) 1982; 63 Ghimire (10.1016/j.scitotenv.2019.135934_bb0210) 2019; 12 Foresee (10.1016/j.scitotenv.2019.135934_bb0200) 1997; 3 Ye (10.1016/j.scitotenv.2019.135934_bb0635) 2013; 116 Yeh (10.1016/j.scitotenv.2019.135934_bb0640) 2010; 2 Karatzas (10.1016/j.scitotenv.2019.135934_bb0310) 2007; 15 EJA (10.1016/j.scitotenv.2019.135934_bb0195) 2016 Hyslop (10.1016/j.scitotenv.2019.135934_bb0280) 2009; 43 Willmott (10.1016/j.scitotenv.2019.135934_bb0585) 1981; 2 Kim (10.1016/j.scitotenv.2019.135934_bb0330) 2006; 40 Byrne (10.1016/j.scitotenv.2019.135934_bb0085) 2014 Confalonieri (10.1016/j.scitotenv.2019.135934_bb0130) 2007 Deo (10.1016/j.scitotenv.2019.135934_bb0150) 2015; 161–162 Sehgal (10.1016/j.scitotenv.2019.135934_bb0530) 2014; 28 Glinianaia (10.1016/j.scitotenv.2019.135934_bb0230) 2004; 15 Niska (10.1016/j.scitotenv.2019.135934_bb0455) 2004; 17 Vlachogianni (10.1016/j.scitotenv.2019.135934_bb0565) 2011; 409 Mohammadi (10.1016/j.scitotenv.2019.135934_bb0430) 2015; 92 Rutherford (10.1016/j.scitotenv.2019.135934_bb0520) 1999; 42 Chaloulakou (10.1016/j.scitotenv.2019.135934_bb0095) 2003; 53 Green (10.1016/j.scitotenv.2019.135934_bb0240) 2006; 40 Hess (10.1016/j.scitotenv.2019.135934_bb0260) 2000; 13 Kim (10.1016/j.scitotenv.2019.135934_bb0325) 2003; 8 Kukkonen (10.1016/j.scitotenv.2019.135934_bb0360) 2012; 12 Chai (10.1016/j.scitotenv.2019.135934_bb0090) 2014; 7 NPE (10.1016/j.scitotenv.2019.135934_bb0460) 2016; 1 Xiaoli (10.1016/j.scitotenv.2019.135934_bb0625) 2017; 19 Li (10.1016/j.scitotenv.2019.135934_bb0390) 2018; 626 Chen (10.1016/j.scitotenv.2019.135934_bb0105) 2008; 78 Asadollahfardi (10.1016/j.scitotenv.2019.135934_bb0050) 2016; 25 Walsh (10.1016/j.scitotenv.2019.135934_bb0570) 2014; 8 Ghimire (10.1016/j.scitotenv.2019.135934_bb0215) 2019; 253 Legates (10.1016/j.scitotenv.2019.135934_bb0375) 1999; 35 Prasad (10.1016/j.scitotenv.2019.135934_bb0490) 2018; 330 Wu (10.1016/j.scitotenv.2019.135934_bb0620) 2009; 1 Langrish (10.1016/j.scitotenv.2019.135934_bb0370) 2012; 120 Nenes (10.1016/j.scitotenv.2019.135934_bb0450) 1999; 33 Uhlenbrook (10.1016/j.scitotenv.2019.135934_bb0560) 1999; 44 Ouyang (10.1016/j.scitotenv.2019.135934_bb0480) 2016; 30 Zhao (10.1016/j.scitotenv.2019.135934_bb0650) 2018; 13 Schauer (10.1016/j.scitotenv.2019.135934_bb0525) 1996; 30 Higginbotham (10.1016/j.scitotenv.2019.135934_bb0265) 2010; 16 |
| References_xml | – volume: 30 start-page: 3837 year: 1996 end-page: 3855 ident: bb0525 article-title: Source apportionment of airborne particulate matter using organic compounds as tracers publication-title: Atmos. Environ. – volume: 28 start-page: 4483 year: 2007 end-page: 4498 ident: bb0245 article-title: Multi year satellite remote sensing of particulate matter air quality over Sydney, Australia publication-title: Int. J. Remote Sens. – volume: 102 start-page: 96 year: 2015 end-page: 104 ident: bb0300 article-title: Imputation of missing data in time series for air pollutants publication-title: Atmos. Environ. – volume: 8 start-page: 201 year: 1994 end-page: 220 ident: bb0315 article-title: Neural networks for river flow prediction publication-title: J. Comput. Civ. Eng. – volume: 8 start-page: 319 year: 2003 end-page: 328 ident: bb0325 article-title: Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks publication-title: J. Hydrol. Eng. – volume: 27 start-page: 4815 year: 2013 end-page: 4826 ident: bb0495 article-title: A comparison between conventional and M5 model tree methods for converting pan evaporation to reference evapotranspiration for semi-arid region publication-title: Water Resour. Manag. – start-page: 443 year: 1984 end-page: 460 ident: bb0595 article-title: On the evaluation of model performance in physical geography publication-title: Spatial Statistics and Models – volume: 1 year: 2016 ident: bb0460 article-title: National Pollutant Energy, Department of the Environment and Energy – volume: 8 start-page: 940 year: 2004 end-page: 958 ident: bb0045 article-title: Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions publication-title: Hydrol. Earth Syst. Sci. Discuss. – volume: 64 year: 2014 ident: bb0205 article-title: A two-step approach for relating TEOM and dichotomous air sampler PM 2.5 measurements publication-title: J. Air Waste Manage. Assoc. – volume: 40 start-page: 1 year: 2004 end-page: 12 ident: bb0285 article-title: Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques publication-title: Water Resour. Res. – volume: 182 year: 2013 ident: bb0515 article-title: Have the short-term mortality effects of particulate matter air pollution changed in Australia over the period 1993–2007? publication-title: Environ. Pollut. – year: 2017 ident: bb0220 article-title: Observation and Measurement of Atmospheric Pollution publication-title: Tech Conf on Obs and Meas of Atmos Pollut, Proc, Pap – volume: 8 start-page: 1 year: 2014 end-page: 17 ident: bb0570 article-title: PM2.5: global progress in controlling the motor vehicle contribution publication-title: Frontiers of Environmental Science & Engineering – volume: 1 start-page: 1 year: 2009 end-page: 41 ident: bb0610 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. – volume: 118 start-page: 1204 year: 2010 end-page: 1210 ident: bb0655 article-title: Risk-based prioritization among air pollution control strategies in the Yangtze River Delta, China publication-title: Environ. Health Perspect. – volume: 337 year: 2007 ident: bb0015 article-title: The Burden of Disease and Injury in Australia 2003 – volume: 17 start-page: 1411 year: 2006 end-page: 1423 ident: bb0440 article-title: A fast and accurate online sequential learning algorithm for feedforward networks publication-title: IEEE Trans. Neural Netw. – start-page: 103 year: 2016 end-page: 108 ident: bb0475 article-title: A Comparative Study of Computational Intelligence Techniques Applied to PM2.5 Air Pollution Forecasting – start-page: 118 year: 1999 end-page: 123 ident: bb0410 article-title: Air pollution and infant mortality in Mexico City publication-title: Epidemiology – volume: 30 start-page: 2311 year: 2016 end-page: 2325 ident: bb0480 article-title: Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction publication-title: Water Resour. Manag. – year: 2011 ident: bb0605 article-title: Data Mining - Practical Machine Learning Tools and Techniques – volume: 63 start-page: 381 year: 2005 end-page: 396 ident: bb0065 article-title: Neural networks and M5 model trees in modelling water level–discharge relationship publication-title: Neurocomputing – year: 2013 ident: bb0190 article-title: Modelling October 2013 Bushfire Pollution Episode in New South Wales, Australia – volume: 168 start-page: 568 year: 2016 end-page: 593 ident: bb0165 article-title: A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset publication-title: Appl. Energy – volume: 330 start-page: 136 year: 2018 end-page: 161 ident: bb0490 article-title: Soil moisture forecasting by a hybrid machine learning technique: ELM integrated with ensemble empirical mode decomposition publication-title: Geoderma – volume: 63 start-page: 1309 year: 1982 end-page: 1313 ident: bb0590 article-title: Some comments on the evaluation of model performance publication-title: Bull. Am. Meteorol. Soc. – volume: 161–162 start-page: 65 year: 2015 end-page: 81 ident: bb0150 article-title: Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia publication-title: Atmos. Res. – volume: 4 start-page: 427 year: 2013 end-page: 434 ident: bb0645 article-title: Characteristics of visibility and particulate matter (PM) in an urban area of Northeast China publication-title: Atmospheric Pollution Research – volume: 7 start-page: 1247 year: 2014 end-page: 1250 ident: bb0090 article-title: Root mean square error (RMSE) or mean absolute error (MAE)? – arguments against avoiding RMSE in the literature publication-title: Geosci. Model Dev. – year: 2009 ident: bb0275 article-title: Hunter Valley Research Foundation – start-page: 128 year: 1997 end-page: 137 ident: bb0575 article-title: Inducing model trees for continuous classes publication-title: European Conference on Machine Learning, Prague – volume: 31 start-page: 1211 year: 2017 end-page: 1240 ident: bb0170 article-title: Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model publication-title: Stoch. Env. Res. Risk A. – volume: 22 start-page: 97 year: 2007 end-page: 103 ident: bb0550 article-title: Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations publication-title: Environ. Model Softw. – volume: 112 year: 2013 ident: bb0290 article-title: An Introduction to Statistical Learning – volume: 159 start-page: 9 year: 2017 end-page: 15 ident: bb0485 article-title: Development of a model for particulate matter pollution in Australia with implications for other satellite-based models publication-title: Environ. Res. – year: 2019 ident: bb0180 article-title: Queensland (Qld) Government Department of Environment and Science (DoE) – volume: 2 start-page: 184 year: 1981 end-page: 194 ident: bb0585 article-title: On the validation of models publication-title: Phys. Geogr. – volume: 134 start-page: 23 year: 2014 end-page: 33 ident: bb0235 article-title: A practical comparison of single and multiple imputation methods to handle complex missing data in air quality datasets publication-title: Chemom. Intell. Lab. Syst. – volume: 92 start-page: 162 year: 2015 end-page: 171 ident: bb0430 article-title: A new hybrid support vector machine–wavelet transform approach for estimation of horizontal global solar radiation publication-title: Energy Convers. Manag. – volume: 143 start-page: 19 year: 2015 end-page: 25 ident: bb0080 article-title: The health benefits of reducing air pollution in Sydney, Australia publication-title: Environ. Res. – volume: 10 start-page: 282 year: 1970 end-page: 290 ident: bb0445 article-title: River flow forecasting through conceptual models part I—a discussion of principles publication-title: J. Hydrol. – volume: 120 start-page: 367 year: 2012 end-page: 372 ident: bb0370 article-title: Reducing personal exposure to particulate air pollution improves cardiovascular health in patients with coronary heart disease publication-title: Environ. Health Perspect. – volume: 2 start-page: 135 year: 2010 end-page: 156 ident: bb0640 article-title: Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method publication-title: Adv. Adapt. Data Anal. – volume: 51 start-page: 109 year: 2001 end-page: 120 ident: bb0115 article-title: Comparison of real-time instruments used to monitor airborne particulate matter publication-title: J. Air Waste Manage. Assoc. – year: 2016 ident: bb0195 article-title: Clearing the Air: Why Australia Urgently Needs Effective National Air Pollution Laws – volume: 4 year: 2012 ident: bb0120 article-title: Noise-assisted EMD methods in action publication-title: Adv. Adapt. Data Anal. – year: 2007 ident: bb0130 article-title: Human health. climate change 2007: impacts, adaptation and vulnerability. Contribution of Working Group II to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change – volume: 44 start-page: 779 year: 1999 end-page: 797 ident: bb0560 article-title: Prediction uncertainty of conceptual rainfall-runoff models caused by problems in identifying model parameters and structure publication-title: Hydrol. Sci. J. – volume: 1 start-page: 1 year: 2009 end-page: 41 ident: bb0620 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. – volume: 14 start-page: 19 year: 2014 end-page: 29 ident: bb0125 article-title: Improved complete ensemble EMD: a suitable tool for biomedical signal processing publication-title: Biomedical Signal Processing and Control – volume: 202 start-page: 180 year: 2019 end-page: 189 ident: bb0110 article-title: Extreme gradient boosting model to estimate PM2.5 concentrations with missing-filled satellite data in China publication-title: Atmos. Environ. – volume: 42 start-page: 217 year: 1999 end-page: 225 ident: bb0520 article-title: Characteristics of rural dust events shown to impact on asthma severity in Brisbane, Australia publication-title: Int. J. Biometeorol. – volume: 105 start-page: 395 year: 2010 end-page: 401 ident: bb0055 article-title: Validation and fine-tuning of a predictive model for air quality in livestock buildings publication-title: Biosyst. Eng. – volume: 138 start-page: 166 year: 2014 end-page: 178 ident: bb0010 article-title: Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks publication-title: Atmos. Res. – volume: 119 start-page: 508 year: 2011 end-page: 513 ident: bb0380 article-title: Size-segregated particle number concentrations and respiratory emergency room visits in Beijing, China publication-title: Environ. Health Perspect. – volume: 74 start-page: 136 year: 2015 end-page: 143 ident: bb0335 article-title: A review on the human health impact of airborne particulate matter publication-title: Environ. Int. – volume: 217 start-page: 5318 year: 2011 end-page: 5327 ident: bb0400 article-title: Forecasting concentrations of air pollutants by logarithm support vector regression with immune algorithms publication-title: Appl. Math. Comput. – volume: 8 start-page: 191 year: 2011 end-page: 200 ident: bb0405 article-title: An improved particle swarm optimization for feature selection publication-title: Journal of Bionic Engineering – year: 2018 ident: bb0140 article-title: Quarterly Update of Australia’s National Greenhouse gas Inventory: March 2018, Incorporating Emissions from the NEM up to June 2018 – volume: 12 start-page: 2407 year: 2019 ident: bb0210 article-title: Deep learning neural networks trained with MODIS satellite-derived predictors for long-term global solar radiation prediction publication-title: Energies – volume: 16 start-page: 259 year: 2010 end-page: 266 ident: bb0265 article-title: Environmental injustice and air pollution in coal affected communities, Hunter Valley, Australia publication-title: Health & Place – volume: 33 start-page: 1553 year: 1999 end-page: 1560 ident: bb0450 article-title: Continued development and testing of a new thermodynamic aerosol module for urban and regional air quality models publication-title: Atmos. Environ. – volume: 53 start-page: 1183 year: 2003 end-page: 1190 ident: bb0095 article-title: Neural network and multiple regression models for PM10 prediction in Athens: a comparative assessment publication-title: J. Air Waste Manage. Assoc. – volume: 253 start-page: 113541 year: 2019 ident: bb0215 article-title: Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms publication-title: Appl. Energy – year: 2015 ident: bb0135 article-title: Climate Change in Australia Information for Australia’s Natural Resource Management Regions: Technical Report – volume: 454 start-page: 903 year: 1998 end-page: 995 ident: bb0270 article-title: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis publication-title: Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences – volume: 40 start-page: 5608 year: 2006 ident: bb0240 article-title: The implications of tapered element oscillating microbalance (TEOM) software configuration on particulate matter measurements in the UK and Europe publication-title: Atmos. Environ. – volume: 78 start-page: 379 year: 2008 end-page: 400 ident: bb0105 article-title: Artificial intelligence techniques: an introduction to their use for modelling environmental systems publication-title: Math. Comput. Simul. – volume: 24 start-page: 121 year: 2011 end-page: 129 ident: bb0535 article-title: Missing value imputation on missing completely at random data using multilayer perceptrons publication-title: Neural Netw. – volume: 32 start-page: 2088 year: 2012 end-page: 2094 ident: bb0600 article-title: A refined index of model performance publication-title: Int. J. Climatol. – volume: 121 start-page: 2331 year: 2010 end-page: 2378 ident: bb0075 article-title: Particulate matter air pollution and cardiovascular disease: an update to the scientific statement from the American Heart Association publication-title: Circulation – volume: 17 start-page: 159 year: 2004 end-page: 167 ident: bb0455 article-title: Evolving the neural network model for forecasting air pollution time series publication-title: Eng. Appl. Artif. Intell. – volume: 188 start-page: 90 year: 2016 ident: bb0155 article-title: An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland publication-title: Environ. Monit. Assess. – year: 2008 ident: bb0255 article-title: Artificial Intelligence Methods in the Environmental Sciences – year: 2019 ident: bb0465 article-title: New South Wales (NSW) Office of Environment and Heritage (OEH) – volume: 19 start-page: 380 year: 2017 ident: bb0625 article-title: Pretreatment and wavelength selection method for near-infrared spectra signal based on improved CEEMDAN energy entropy and permutation entropy publication-title: Entropy – volume: 217 start-page: 422 year: 2018 end-page: 439 ident: bb0040 article-title: Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting publication-title: Appl. Energy – volume: 13 start-page: 67 year: 2000 end-page: 73 ident: bb0260 article-title: The Australian air quality forecasting system publication-title: AMOS Bulletin – year: 2014 ident: bb0085 article-title: Australian Environmental Planning: Challenges and Future Prospects – volume: 15 start-page: 143 year: 2004 end-page: 149 ident: bb0060 article-title: Who is sensitive to the effects of particulate air pollution on mortality?: a case-crossover analysis of effect modifiers publication-title: Epidemiology – volume: 409 start-page: 1559 year: 2011 end-page: 1571 ident: bb0565 article-title: Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki publication-title: Sci. Total Environ. – volume: 47 start-page: 682 year: 1997 end-page: 689 ident: bb0030 article-title: Evaluation of the TEOM® method for measurement of ambient particulate mass in urban areas publication-title: J. Air Waste Manage. Assoc. – volume: 496 start-page: 264 year: 2014 end-page: 274 ident: bb0660 article-title: A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network publication-title: Sci. Total Environ. – volume: 2016 year: 2016 ident: bb0385 article-title: Improved CEEMDAN and PSO-SVR modeling for near-infrared noninvasive glucose detection publication-title: Computational and mathematical methods in medicine – volume: 15 start-page: 36 year: 2004 end-page: 45 ident: bb0230 article-title: Particulate air pollution and fetal health: a systematic review of the epidemiologic evidence publication-title: Epidemiology – volume: 131 start-page: 150 year: 2016 end-page: 163 ident: bb0500 article-title: Impact of the New South Wales fires during October 2013 on regional air quality in eastern Australia publication-title: Atmos. Environ. – volume: 295 start-page: 1127 year: 2006 end-page: 1134 ident: bb0185 article-title: Fine particulate air pollution and hospital admission for cardiovascular and respiratory diseases publication-title: Jama – volume: 91 start-page: 433 year: 2015 end-page: 441 ident: bb0425 article-title: Support vector regression based prediction of global solar radiation on a horizontal surface publication-title: Energy Convers. Manag. – year: 2011 ident: bb0175 article-title: Department of Environment and Resource Management – volume: 177 start-page: 604 year: 2002 end-page: 608 ident: bb0345 article-title: Air pollution and its health impacts: the changing panorama publication-title: Med. J. Aust. – volume: 29 start-page: 717 year: 2012 end-page: 730 ident: bb0005 article-title: Application of artificial neural networks to rainfall forecasting in Queensland, Australia publication-title: Adv. Atmos. Sci. – volume: 43 start-page: 182 year: 2009 end-page: 195 ident: bb0280 article-title: Impaired visibility: the air pollution people see publication-title: Atmos. Environ. – volume: 15 start-page: 1377 year: 2013 end-page: 1390 ident: bb0580 article-title: Improved annual rainfall-runoff forecasting using PSO–SVM model based on EEMD publication-title: J. Hydroinf. – volume: 29 start-page: 549 year: 1995 end-page: 562 ident: bb0225 article-title: Microscopic and submicron components of atmospheric particulate matter during high asthma periods in Brisbane, Queensland, Australia publication-title: Atmos. Environ. – volume: 108 start-page: 11790 year: 2011 end-page: 11793 ident: bb0320 article-title: Reconciling anthropogenic climate change with observed temperature 1998–2008 publication-title: Proc. Natl. Acad. Sci. – volume: 626 start-page: 1421 year: 2018 end-page: 1438 ident: bb0390 article-title: Research and application of a novel hybrid air quality early-warning system: a case study in China publication-title: Sci. Total Environ. – volume: 10 start-page: 873 year: 2017 end-page: 883 ident: bb0340 article-title: Modeling of air pollutants using least square support vector regression, multivariate adaptive regression spline, and M5 model tree models publication-title: Air Quality, Atmosphere & Health – volume: 108 year: 2003 ident: bb0545 article-title: Spatiotemporal modeling of PM2.5 data with missing values publication-title: Journal of Geophysical Research: Atmospheres – volume: 25 start-page: 71 year: 2016 end-page: 83 ident: bb0050 article-title: Predicting particulate matter (PM2.5) concentrations in the air of Shahr-e Ray City, Iran, by using an artificial neural network publication-title: Environ. Qual. Manag. – volume: 12 start-page: 1 year: 2012 end-page: 87 ident: bb0360 article-title: A review of operational, regional-scale, chemical weather forecasting models in Europe publication-title: Atmos. Chem. Phys. – volume: 116 start-page: 94 year: 2013 end-page: 101 ident: bb0635 article-title: Online sequential extreme learning machine in nonstationary environments publication-title: Neurocomputing – volume: 104 start-page: 281 year: 2019 end-page: 295 ident: bb0020 article-title: Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition publication-title: Renew. Sust. Energ. Rev. – volume: 22 start-page: 1034 year: 2007 end-page: 1052 ident: bb0145 article-title: HydroTest: a web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts publication-title: Environ. Model Softw. – volume: 33 start-page: 3237 year: 1999 end-page: 3250 ident: bb0100 article-title: Source apportionment of visibility degradation problems in Brisbane (Australia) using the multiple linear regression techniques publication-title: Atmos. Environ. – volume: 17 start-page: 1411 year: 2006 end-page: 1423 ident: bb0395 article-title: A fast and accurate online sequential learning algorithm for feedforward networks publication-title: IEEE Trans. Neural Netw. – volume: 68 start-page: 50 year: 2013 end-page: 58 ident: bb0555 article-title: Input variable selection and calibration data selection for storm water quality regression models publication-title: Water Sci. Technol. – volume: 40 start-page: 593 year: 2006 end-page: 605 ident: bb0330 article-title: Fine particulate matter characteristics and its impact on visibility impairment at two urban sites in Korea: Seoul and Incheon publication-title: Atmos. Environ. – volume: 35 start-page: 233 year: 1999 end-page: 241 ident: bb0375 article-title: Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation publication-title: Water Resour. Res. – volume: 28 start-page: 2793 year: 2014 end-page: 2811 ident: bb0530 article-title: Wavelet bootstrap multiple linear regression based hybrid modeling for daily river discharge forecasting publication-title: Water Resour. Manag. – volume: 92 start-page: 433 year: 2016 end-page: 445 ident: bb0630 article-title: Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: a case study in Neckar River, Germany publication-title: Measurement – volume: 17 start-page: 422 year: 2018 end-page: 439 ident: bb0035 article-title: Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting publication-title: Appl. Energy – volume: 31 start-page: 1211 year: 2016 end-page: 1240 ident: bb0160 article-title: Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model publication-title: Stoch. Env. Res. Risk A. – volume: 62 start-page: 524 year: 2005 end-page: 530 ident: bb0415 article-title: Impact of ambient air pollution on birth weight in Sydney, Australia publication-title: Occup. Environ. Med. – volume: 6 start-page: 236 year: 2015 end-page: 244 ident: bb0510 article-title: A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods publication-title: IEEE Transactions on Sustainable Energy – volume: 3 start-page: 1930 year: 1997 end-page: 1935 ident: bb0200 article-title: Gauss-Newton approximation to Bayesian learning publication-title: Proceedings of International Conference on Neural Networks (ICNN’97) – volume: 157 start-page: 1074 year: 2003 end-page: 1082 ident: bb0470 article-title: Modifiers of the temperature and mortality association in seven US cities publication-title: Am. J. Epidemiol. – volume: 53 start-page: 55 year: 2010 end-page: 63 ident: bb0250 article-title: Modifying goodness-of-fit indicators to incorporate both measurement and model uncertainty in model calibration and validation publication-title: Trans. ASABE – volume: 4 start-page: 14 year: 2005 ident: bb0355 article-title: Particulate Matter Air Pollution: How it Harms Health – volume: 15 start-page: 1310 year: 2007 end-page: 1319 ident: bb0310 article-title: Air pollution modelling with the aid of computational intelligence methods in Thessaloniki, Greece publication-title: Simul. Model. Pract. Theory – volume: 72 start-page: 3391 year: 2009 end-page: 3395 ident: bb0365 article-title: Ensemble of online sequential extreme learning machine publication-title: Neurocomputing – volume: 164 start-page: 174 year: 2019 end-page: 192 ident: bb0295 article-title: An innovative hybrid air pollution early-warning system based on pollutants forecasting and Extenics evaluation publication-title: Knowl.-Based Syst. – volume: 102 start-page: 239 year: 2015 end-page: 248 ident: bb0420 article-title: Artificial intelligence based approach to forecast PM2.5 during haze episodes: a case study of Delhi, India publication-title: Atmos. Environ. – volume: 38 start-page: 2895 year: 2004 end-page: 2907 ident: bb0305 article-title: Methods for imputation of missing values in air quality data sets publication-title: Atmos. Environ. – year: 2000 ident: bb0070 article-title: Australian Rainforests: Islands of Green in a Land of Fire – volume: 213 start-page: 450 year: 2018 end-page: 464 ident: bb0025 article-title: Multi-stage hybridized online sequential extreme learning machine integrated with Markov Chain Monte Carlo copula-Bat algorithm for rainfall forecasting publication-title: Atmos. Res. – volume: 26 start-page: 99 year: 1992 end-page: 105 ident: bb0540 article-title: A statistical analysis of particulate data sets in Brisbane, Australia publication-title: Atmospheric Environment. Part B. Urban Atmosphere – volume: 5 start-page: 89 year: 2005 end-page: 97 ident: bb0350 article-title: Comparison of different efficiency criteria for hydrological model assessment publication-title: Adv. Geosci. – start-page: 47 year: 2010 end-page: 55 ident: bb0435 article-title: Effects of bushfire smoke on daily mortality and hospital admissions in Sydney, Australia publication-title: Epidemiology – volume: 13 start-page: e0201011 year: 2018 ident: bb0650 article-title: Short period PM2.5 prediction based on multivariate linear regression model publication-title: PLoS One – volume: 51 start-page: 87 year: 2006 end-page: 96 ident: bb0505 article-title: Temperature modifies the health effects of particulate matter in Brisbane, Australia publication-title: Int. J. Biometeorol. – volume: 1 start-page: 1 year: 2009 end-page: 41 ident: bb0615 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. – year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0085 – volume: 53 start-page: 55 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0250 article-title: Modifying goodness-of-fit indicators to incorporate both measurement and model uncertainty in model calibration and validation publication-title: Trans. ASABE doi: 10.13031/2013.29502 – volume: 40 start-page: 1 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0285 article-title: Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques publication-title: Water Resour. Res. doi: 10.1029/2003WR002355 – volume: 17 start-page: 1411 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0440 article-title: A fast and accurate online sequential learning algorithm for feedforward networks publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2006.880583 – volume: 134 start-page: 23 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0235 article-title: A practical comparison of single and multiple imputation methods to handle complex missing data in air quality datasets publication-title: Chemom. Intell. Lab. Syst. doi: 10.1016/j.chemolab.2014.02.007 – volume: 43 start-page: 182 year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0280 article-title: Impaired visibility: the air pollution people see publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2008.09.067 – volume: 15 start-page: 143 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0060 article-title: Who is sensitive to the effects of particulate air pollution on mortality?: a case-crossover analysis of effect modifiers publication-title: Epidemiology doi: 10.1097/01.ede.0000112210.68754.fa – volume: 4 start-page: 14 year: 2005 ident: 10.1016/j.scitotenv.2019.135934_bb0355 – volume: 91 start-page: 433 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0425 article-title: Support vector regression based prediction of global solar radiation on a horizontal surface publication-title: Energy Convers. Manag. doi: 10.1016/j.enconman.2014.12.015 – volume: 28 start-page: 2793 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0530 article-title: Wavelet bootstrap multiple linear regression based hybrid modeling for daily river discharge forecasting publication-title: Water Resour. Manag. doi: 10.1007/s11269-014-0638-7 – volume: 53 start-page: 1183 year: 2003 ident: 10.1016/j.scitotenv.2019.135934_bb0095 article-title: Neural network and multiple regression models for PM10 prediction in Athens: a comparative assessment publication-title: J. Air Waste Manage. Assoc. doi: 10.1080/10473289.2003.10466276 – year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0195 – volume: 112 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0290 – volume: 16 start-page: 259 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0265 article-title: Environmental injustice and air pollution in coal affected communities, Hunter Valley, Australia publication-title: Health & Place doi: 10.1016/j.healthplace.2009.10.007 – volume: 68 start-page: 50 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0555 article-title: Input variable selection and calibration data selection for storm water quality regression models publication-title: Water Sci. Technol. doi: 10.2166/wst.2013.222 – volume: 32 start-page: 2088 year: 2012 ident: 10.1016/j.scitotenv.2019.135934_bb0600 article-title: A refined index of model performance publication-title: Int. J. Climatol. doi: 10.1002/joc.2419 – volume: 157 start-page: 1074 year: 2003 ident: 10.1016/j.scitotenv.2019.135934_bb0470 article-title: Modifiers of the temperature and mortality association in seven US cities publication-title: Am. J. Epidemiol. doi: 10.1093/aje/kwg096 – start-page: 103 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0475 – volume: 44 start-page: 779 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0560 article-title: Prediction uncertainty of conceptual rainfall-runoff models caused by problems in identifying model parameters and structure publication-title: Hydrol. Sci. J. doi: 10.1080/02626669909492273 – year: 2000 ident: 10.1016/j.scitotenv.2019.135934_bb0070 – volume: 8 start-page: 319 year: 2003 ident: 10.1016/j.scitotenv.2019.135934_bb0325 article-title: Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks publication-title: J. Hydrol. Eng. doi: 10.1061/(ASCE)1084-0699(2003)8:6(319) – volume: 35 start-page: 233 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0375 article-title: Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation publication-title: Water Resour. Res. doi: 10.1029/1998WR900018 – volume: 92 start-page: 162 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0430 article-title: A new hybrid support vector machine–wavelet transform approach for estimation of horizontal global solar radiation publication-title: Energy Convers. Manag. doi: 10.1016/j.enconman.2014.12.050 – volume: 27 start-page: 4815 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0495 article-title: A comparison between conventional and M5 model tree methods for converting pan evaporation to reference evapotranspiration for semi-arid region publication-title: Water Resour. Manag. doi: 10.1007/s11269-013-0440-y – volume: 26 start-page: 99 year: 1992 ident: 10.1016/j.scitotenv.2019.135934_bb0540 article-title: A statistical analysis of particulate data sets in Brisbane, Australia publication-title: Atmospheric Environment. Part B. Urban Atmosphere doi: 10.1016/0957-1272(92)90041-P – year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0190 – volume: 14 start-page: 19 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0125 article-title: Improved complete ensemble EMD: a suitable tool for biomedical signal processing publication-title: Biomedical Signal Processing and Control doi: 10.1016/j.bspc.2014.06.009 – volume: 330 start-page: 136 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0490 article-title: Soil moisture forecasting by a hybrid machine learning technique: ELM integrated with ensemble empirical mode decomposition publication-title: Geoderma doi: 10.1016/j.geoderma.2018.05.035 – volume: 13 start-page: e0201011 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0650 article-title: Short period PM2.5 prediction based on multivariate linear regression model publication-title: PLoS One doi: 10.1371/journal.pone.0201011 – volume: 22 start-page: 1034 year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0145 article-title: HydroTest: a web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts publication-title: Environ. Model Softw. doi: 10.1016/j.envsoft.2006.06.008 – volume: 10 start-page: 282 year: 1970 ident: 10.1016/j.scitotenv.2019.135934_bb0445 article-title: River flow forecasting through conceptual models part I—a discussion of principles publication-title: J. Hydrol. doi: 10.1016/0022-1694(70)90255-6 – volume: 116 start-page: 94 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0635 article-title: Online sequential extreme learning machine in nonstationary environments publication-title: Neurocomputing doi: 10.1016/j.neucom.2011.12.064 – volume: 118 start-page: 1204 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0655 article-title: Risk-based prioritization among air pollution control strategies in the Yangtze River Delta, China publication-title: Environ. Health Perspect. doi: 10.1289/ehp.1001991 – volume: 72 start-page: 3391 year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0365 article-title: Ensemble of online sequential extreme learning machine publication-title: Neurocomputing doi: 10.1016/j.neucom.2009.02.013 – start-page: 128 year: 1997 ident: 10.1016/j.scitotenv.2019.135934_bb0575 article-title: Inducing model trees for continuous classes – volume: 78 start-page: 379 year: 2008 ident: 10.1016/j.scitotenv.2019.135934_bb0105 article-title: Artificial intelligence techniques: an introduction to their use for modelling environmental systems publication-title: Math. Comput. Simul. doi: 10.1016/j.matcom.2008.01.028 – volume: 119 start-page: 508 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0380 article-title: Size-segregated particle number concentrations and respiratory emergency room visits in Beijing, China publication-title: Environ. Health Perspect. doi: 10.1289/ehp.1002203 – volume: 15 start-page: 36 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0230 article-title: Particulate air pollution and fetal health: a systematic review of the epidemiologic evidence publication-title: Epidemiology doi: 10.1097/01.ede.0000101023.41844.ac – volume: 25 start-page: 71 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0050 article-title: Predicting particulate matter (PM2.5) concentrations in the air of Shahr-e Ray City, Iran, by using an artificial neural network publication-title: Environ. Qual. Manag. doi: 10.1002/tqem.21464 – volume: 120 start-page: 367 year: 2012 ident: 10.1016/j.scitotenv.2019.135934_bb0370 article-title: Reducing personal exposure to particulate air pollution improves cardiovascular health in patients with coronary heart disease publication-title: Environ. Health Perspect. doi: 10.1289/ehp.1103898 – volume: 131 start-page: 150 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0500 article-title: Impact of the New South Wales fires during October 2013 on regional air quality in eastern Australia publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2016.01.034 – volume: 337 year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0015 – volume: 188 start-page: 90 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0155 article-title: An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland publication-title: Environ. Monit. Assess. doi: 10.1007/s10661-016-5094-9 – volume: 182 issue: 9 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0515 article-title: Have the short-term mortality effects of particulate matter air pollution changed in Australia over the period 1993–2007? publication-title: Environ. Pollut. – year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0135 – volume: 92 start-page: 433 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0630 article-title: Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: a case study in Neckar River, Germany publication-title: Measurement doi: 10.1016/j.measurement.2016.06.042 – volume: 161–162 start-page: 65 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0150 article-title: Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia publication-title: Atmos. Res. doi: 10.1016/j.atmosres.2015.03.018 – volume: 7 start-page: 1247 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0090 article-title: Root mean square error (RMSE) or mean absolute error (MAE)? – arguments against avoiding RMSE in the literature publication-title: Geosci. Model Dev. doi: 10.5194/gmd-7-1247-2014 – year: 2017 ident: 10.1016/j.scitotenv.2019.135934_bb0220 article-title: Observation and Measurement of Atmospheric Pollution – volume: 10 start-page: 873 year: 2017 ident: 10.1016/j.scitotenv.2019.135934_bb0340 article-title: Modeling of air pollutants using least square support vector regression, multivariate adaptive regression spline, and M5 model tree models publication-title: Air Quality, Atmosphere & Health doi: 10.1007/s11869-017-0477-9 – volume: 51 start-page: 87 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0505 article-title: Temperature modifies the health effects of particulate matter in Brisbane, Australia publication-title: Int. J. Biometeorol. doi: 10.1007/s00484-006-0054-7 – volume: 2 start-page: 184 year: 1981 ident: 10.1016/j.scitotenv.2019.135934_bb0585 article-title: On the validation of models publication-title: Phys. Geogr. doi: 10.1080/02723646.1981.10642213 – volume: 138 start-page: 166 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0010 article-title: Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks publication-title: Atmos. Res. doi: 10.1016/j.atmosres.2013.11.002 – volume: 217 start-page: 5318 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0400 article-title: Forecasting concentrations of air pollutants by logarithm support vector regression with immune algorithms publication-title: Appl. Math. Comput. – volume: 19 start-page: 380 year: 2017 ident: 10.1016/j.scitotenv.2019.135934_bb0625 article-title: Pretreatment and wavelength selection method for near-infrared spectra signal based on improved CEEMDAN energy entropy and permutation entropy publication-title: Entropy doi: 10.3390/e19070380 – volume: 74 start-page: 136 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0335 article-title: A review on the human health impact of airborne particulate matter publication-title: Environ. Int. doi: 10.1016/j.envint.2014.10.005 – volume: 213 start-page: 450 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0025 article-title: Multi-stage hybridized online sequential extreme learning machine integrated with Markov Chain Monte Carlo copula-Bat algorithm for rainfall forecasting publication-title: Atmos. Res. doi: 10.1016/j.atmosres.2018.07.005 – year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0175 – volume: 102 start-page: 239 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0420 article-title: Artificial intelligence based approach to forecast PM2.5 during haze episodes: a case study of Delhi, India publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2014.11.050 – volume: 40 start-page: 5608 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0240 article-title: The implications of tapered element oscillating microbalance (TEOM) software configuration on particulate matter measurements in the UK and Europe publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2006.04.052 – volume: 1 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0460 – volume: 253 start-page: 113541 year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0215 article-title: Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms publication-title: Appl. Energy doi: 10.1016/j.apenergy.2019.113541 – volume: 15 start-page: 1310 year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0310 article-title: Air pollution modelling with the aid of computational intelligence methods in Thessaloniki, Greece publication-title: Simul. Model. Pract. Theory doi: 10.1016/j.simpat.2007.09.005 – volume: 29 start-page: 549 year: 1995 ident: 10.1016/j.scitotenv.2019.135934_bb0225 article-title: Microscopic and submicron components of atmospheric particulate matter during high asthma periods in Brisbane, Queensland, Australia publication-title: Atmos. Environ. doi: 10.1016/1352-2310(94)00278-S – volume: 105 start-page: 395 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0055 article-title: Validation and fine-tuning of a predictive model for air quality in livestock buildings publication-title: Biosyst. Eng. doi: 10.1016/j.biosystemseng.2009.12.011 – volume: 6 start-page: 236 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0510 article-title: A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods publication-title: IEEE Transactions on Sustainable Energy doi: 10.1109/TSTE.2014.2365580 – volume: 13 start-page: 67 year: 2000 ident: 10.1016/j.scitotenv.2019.135934_bb0260 article-title: The Australian air quality forecasting system publication-title: AMOS Bulletin – volume: 33 start-page: 3237 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0100 article-title: Source apportionment of visibility degradation problems in Brisbane (Australia) using the multiple linear regression techniques publication-title: Atmos. Environ. doi: 10.1016/S1352-2310(99)00091-6 – volume: 108 year: 2003 ident: 10.1016/j.scitotenv.2019.135934_bb0545 article-title: Spatiotemporal modeling of PM2.5 data with missing values publication-title: Journal of Geophysical Research: Atmospheres doi: 10.1029/2002JD002914 – year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0180 – volume: 40 start-page: 593 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0330 article-title: Fine particulate matter characteristics and its impact on visibility impairment at two urban sites in Korea: Seoul and Incheon publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2005.11.076 – volume: 38 start-page: 2895 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0305 article-title: Methods for imputation of missing values in air quality data sets publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2004.02.026 – volume: 8 start-page: 1 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0570 article-title: PM2.5: global progress in controlling the motor vehicle contribution publication-title: Frontiers of Environmental Science & Engineering doi: 10.1007/s11783-014-0634-4 – volume: 104 start-page: 281 year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0020 article-title: Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition publication-title: Renew. Sust. Energ. Rev. doi: 10.1016/j.rser.2019.01.014 – volume: 295 start-page: 1127 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0185 article-title: Fine particulate air pollution and hospital admission for cardiovascular and respiratory diseases publication-title: Jama doi: 10.1001/jama.295.10.1127 – year: 2008 ident: 10.1016/j.scitotenv.2019.135934_bb0255 – volume: 626 start-page: 1421 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0390 article-title: Research and application of a novel hybrid air quality early-warning system: a case study in China publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2018.01.195 – volume: 177 start-page: 604 year: 2002 ident: 10.1016/j.scitotenv.2019.135934_bb0345 article-title: Air pollution and its health impacts: the changing panorama publication-title: Med. J. Aust. doi: 10.5694/j.1326-5377.2002.tb04982.x – volume: 17 start-page: 159 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0455 article-title: Evolving the neural network model for forecasting air pollution time series publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2004.02.002 – year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0605 – volume: 47 start-page: 682 year: 1997 ident: 10.1016/j.scitotenv.2019.135934_bb0030 article-title: Evaluation of the TEOM® method for measurement of ambient particulate mass in urban areas publication-title: J. Air Waste Manage. Assoc. doi: 10.1080/10473289.1997.10463923 – volume: 454 start-page: 903 year: 1998 ident: 10.1016/j.scitotenv.2019.135934_bb0270 article-title: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis publication-title: Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences doi: 10.1098/rspa.1998.0193 – volume: 63 start-page: 381 year: 2005 ident: 10.1016/j.scitotenv.2019.135934_bb0065 article-title: Neural networks and M5 model trees in modelling water level–discharge relationship publication-title: Neurocomputing doi: 10.1016/j.neucom.2004.04.016 – volume: 12 start-page: 2407 year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0210 article-title: Deep learning neural networks trained with MODIS satellite-derived predictors for long-term global solar radiation prediction publication-title: Energies doi: 10.3390/en12122407 – volume: 22 start-page: 97 year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0550 article-title: Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations publication-title: Environ. Model Softw. doi: 10.1016/j.envsoft.2005.12.002 – volume: 62 start-page: 524 year: 2005 ident: 10.1016/j.scitotenv.2019.135934_bb0415 article-title: Impact of ambient air pollution on birth weight in Sydney, Australia publication-title: Occup. Environ. Med. doi: 10.1136/oem.2004.014282 – volume: 1 start-page: 1 year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0615 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536909000047 – volume: 4 year: 2012 ident: 10.1016/j.scitotenv.2019.135934_bb0120 article-title: Noise-assisted EMD methods in action publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536912500252 – volume: 51 start-page: 109 year: 2001 ident: 10.1016/j.scitotenv.2019.135934_bb0115 article-title: Comparison of real-time instruments used to monitor airborne particulate matter publication-title: J. Air Waste Manage. Assoc. doi: 10.1080/10473289.2001.10464254 – volume: 102 start-page: 96 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0300 article-title: Imputation of missing data in time series for air pollutants publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2014.11.049 – volume: 3 start-page: 1930 year: 1997 ident: 10.1016/j.scitotenv.2019.135934_bb0200 article-title: Gauss-Newton approximation to Bayesian learning – volume: 24 start-page: 121 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0535 article-title: Missing value imputation on missing completely at random data using multilayer perceptrons publication-title: Neural Netw. doi: 10.1016/j.neunet.2010.09.008 – volume: 159 start-page: 9 year: 2017 ident: 10.1016/j.scitotenv.2019.135934_bb0485 article-title: Development of a model for particulate matter pollution in Australia with implications for other satellite-based models publication-title: Environ. Res. doi: 10.1016/j.envres.2017.07.044 – volume: 8 start-page: 191 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0405 article-title: An improved particle swarm optimization for feature selection publication-title: Journal of Bionic Engineering doi: 10.1016/S1672-6529(11)60020-6 – volume: 31 start-page: 1211 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0160 article-title: Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model publication-title: Stoch. Env. Res. Risk A. doi: 10.1007/s00477-016-1265-z – volume: 33 start-page: 1553 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0450 article-title: Continued development and testing of a new thermodynamic aerosol module for urban and regional air quality models publication-title: Atmos. Environ. doi: 10.1016/S1352-2310(98)00352-5 – volume: 4 start-page: 427 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0645 article-title: Characteristics of visibility and particulate matter (PM) in an urban area of Northeast China publication-title: Atmospheric Pollution Research doi: 10.5094/APR.2013.049 – volume: 108 start-page: 11790 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0320 article-title: Reconciling anthropogenic climate change with observed temperature 1998–2008 publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.1102467108 – volume: 42 start-page: 217 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0520 article-title: Characteristics of rural dust events shown to impact on asthma severity in Brisbane, Australia publication-title: Int. J. Biometeorol. doi: 10.1007/s004840050108 – year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0130 – volume: 17 start-page: 1411 year: 2006 ident: 10.1016/j.scitotenv.2019.135934_bb0395 article-title: A fast and accurate online sequential learning algorithm for feedforward networks publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2006.880583 – volume: 28 start-page: 4483 year: 2007 ident: 10.1016/j.scitotenv.2019.135934_bb0245 article-title: Multi year satellite remote sensing of particulate matter air quality over Sydney, Australia publication-title: Int. J. Remote Sens. doi: 10.1080/01431160701241738 – year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0140 – volume: 63 start-page: 1309 year: 1982 ident: 10.1016/j.scitotenv.2019.135934_bb0590 article-title: Some comments on the evaluation of model performance publication-title: Bull. Am. Meteorol. Soc. doi: 10.1175/1520-0477(1982)063<1309:SCOTEO>2.0.CO;2 – volume: 121 start-page: 2331 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0075 article-title: Particulate matter air pollution and cardiovascular disease: an update to the scientific statement from the American Heart Association publication-title: Circulation doi: 10.1161/CIR.0b013e3181dbece1 – start-page: 118 year: 1999 ident: 10.1016/j.scitotenv.2019.135934_bb0410 article-title: Air pollution and infant mortality in Mexico City publication-title: Epidemiology doi: 10.1097/00001648-199903000-00006 – volume: 30 start-page: 2311 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0480 article-title: Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction publication-title: Water Resour. Manag. doi: 10.1007/s11269-016-1288-8 – start-page: 47 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0435 article-title: Effects of bushfire smoke on daily mortality and hospital admissions in Sydney, Australia publication-title: Epidemiology doi: 10.1097/EDE.0b013e3181c15d5a – volume: 202 start-page: 180 year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0110 article-title: Extreme gradient boosting model to estimate PM2.5 concentrations with missing-filled satellite data in China publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2019.01.027 – volume: 2 start-page: 135 year: 2010 ident: 10.1016/j.scitotenv.2019.135934_bb0640 article-title: Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536910000422 – volume: 8 start-page: 201 year: 1994 ident: 10.1016/j.scitotenv.2019.135934_bb0315 article-title: Neural networks for river flow prediction publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)0887-3801(1994)8:2(201) – volume: 15 start-page: 1377 year: 2013 ident: 10.1016/j.scitotenv.2019.135934_bb0580 article-title: Improved annual rainfall-runoff forecasting using PSO–SVM model based on EEMD publication-title: J. Hydroinf. doi: 10.2166/hydro.2013.134 – volume: 168 start-page: 568 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0165 article-title: A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset publication-title: Appl. Energy doi: 10.1016/j.apenergy.2016.01.130 – volume: 217 start-page: 422 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0040 article-title: Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting publication-title: Appl. Energy doi: 10.1016/j.apenergy.2018.02.140 – volume: 12 start-page: 1 year: 2012 ident: 10.1016/j.scitotenv.2019.135934_bb0360 article-title: A review of operational, regional-scale, chemical weather forecasting models in Europe publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-12-1-2012 – year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0275 – volume: 5 start-page: 89 year: 2005 ident: 10.1016/j.scitotenv.2019.135934_bb0350 article-title: Comparison of different efficiency criteria for hydrological model assessment publication-title: Adv. Geosci. doi: 10.5194/adgeo-5-89-2005 – year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0465 – volume: 30 start-page: 3837 year: 1996 ident: 10.1016/j.scitotenv.2019.135934_bb0525 article-title: Source apportionment of airborne particulate matter using organic compounds as tracers publication-title: Atmos. Environ. doi: 10.1016/1352-2310(96)00085-4 – volume: 8 start-page: 940 year: 2004 ident: 10.1016/j.scitotenv.2019.135934_bb0045 article-title: Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions publication-title: Hydrol. Earth Syst. Sci. Discuss. doi: 10.5194/hess-8-940-2004 – volume: 2016 year: 2016 ident: 10.1016/j.scitotenv.2019.135934_bb0385 article-title: Improved CEEMDAN and PSO-SVR modeling for near-infrared noninvasive glucose detection publication-title: Computational and mathematical methods in medicine doi: 10.1155/2016/8301962 – volume: 17 start-page: 422 year: 2018 ident: 10.1016/j.scitotenv.2019.135934_bb0035 article-title: Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting publication-title: Appl. Energy doi: 10.1016/j.apenergy.2018.02.140 – volume: 31 start-page: 1211 year: 2017 ident: 10.1016/j.scitotenv.2019.135934_bb0170 article-title: Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model publication-title: Stoch. Env. Res. Risk A. doi: 10.1007/s00477-016-1265-z – volume: 409 start-page: 1559 year: 2011 ident: 10.1016/j.scitotenv.2019.135934_bb0565 article-title: Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2010.12.040 – volume: 143 start-page: 19 year: 2015 ident: 10.1016/j.scitotenv.2019.135934_bb0080 article-title: The health benefits of reducing air pollution in Sydney, Australia publication-title: Environ. Res. doi: 10.1016/j.envres.2015.09.007 – volume: 64 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0205 article-title: A two-step approach for relating TEOM and dichotomous air sampler PM 2.5 measurements publication-title: J. Air Waste Manage. Assoc. doi: 10.1080/10962247.2014.934484 – volume: 164 start-page: 174 year: 2019 ident: 10.1016/j.scitotenv.2019.135934_bb0295 article-title: An innovative hybrid air pollution early-warning system based on pollutants forecasting and Extenics evaluation publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2018.10.036 – volume: 1 start-page: 1 year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0620 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536909000047 – start-page: 443 year: 1984 ident: 10.1016/j.scitotenv.2019.135934_bb0595 article-title: On the evaluation of model performance in physical geography – volume: 29 start-page: 717 year: 2012 ident: 10.1016/j.scitotenv.2019.135934_bb0005 article-title: Application of artificial neural networks to rainfall forecasting in Queensland, Australia publication-title: Adv. Atmos. Sci. doi: 10.1007/s00376-012-1259-9 – volume: 1 start-page: 1 year: 2009 ident: 10.1016/j.scitotenv.2019.135934_bb0610 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536909000047 – volume: 496 start-page: 264 year: 2014 ident: 10.1016/j.scitotenv.2019.135934_bb0660 article-title: A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2014.07.051 |
| SSID | ssj0000781 |
| Score | 2.588708 |
| Snippet | Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 135934 |
| SubjectTerms | air quality algorithms Artificial intelligence atmospheric visibility autocorrelation health care costs ICEEMDAN monitoring mortality Particulate matter (PM2.5, PM10) particulates public health Real-time air quality forecasts risk reduction trees Visibility |
| Title | A hybrid air quality early-warning framework: An hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms |
| URI | https://dx.doi.org/10.1016/j.scitotenv.2019.135934 https://www.ncbi.nlm.nih.gov/pubmed/31869708 https://www.proquest.com/docview/2330337165 https://www.proquest.com/docview/2388784624 |
| Volume | 709 |
| WOSCitedRecordID | wos000512281700035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-1026 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000781 issn: 0048-9697 databaseCode: AIEXJ dateStart: 19950106 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6lLaBKCEGgDx7VInGzXDl-rd1bBEGAUBVVRcrNWm_WJCF1IscNzR_i__CPmPXs2olKKBy4OJHtHXs1n2dnZudByJsOd4ZcxMyOY6mKaseZzbMwtKXrB8wJQFHCROHP7Pw8Ggzifqv10-TCLKcsz6Obm3j-X1kN54DZKnX2H9hdE4UT8B-YDkdgOxz_ivFda7RSaVgWHxc6Z3JlSVXH2P6u3SCZicjSbsER0J1WkZtS8EUVCF11yEEvLRbTsDDoulQedhDoyq1oWk7A3VVIpsR6z_JqPsbCI4qINZQqbF3Hhll8-nVWAFVdJH3SgNVIGR20UM5UmuZaHl7tC6qKbVcy_FtZLyrv0Od7wZfqPUaN87df8AXC-AImnQ-Lekhf9V8cY5ZPNp7pcF_tAQFz1_FsFzdzJErtiMWwnmDqvRHrzInXBHPHC2L0mt5aM9B9MTkFlQOmBvNSAX_x6e0RwJP5VYUaTzXyYk7ULKJ1aKO5tEP2XBbEIGj3uh97g0-NesCizkag4W-fu08eGErbNKZtFlGlGV0-Jo-0SUO7CMUnpCXzNrmPTU5XbXLQa3gIt2k2L9rkIbqMKWbCPSU_uhSRSwG5VCOXbiCX1sg9o92cIm7pGm5phVuqcEsRt7TBLdW4pQa31OCWAm5pjduKCN3ALW1w-4x8ed-7fPvB1m1EbOE7fmkzKYaBZGka-WkaZKEIpSu4DITncl-orWgvVN1nfFCuWRqJLAMrwEtTJ-Cg1mXSOyC7-SyXR4SCcj-UWepEDOwQwdVvpspbcTBKUjcSxyQ0rEqErrGvWr1MExNMOUlqdieK3Qmy-5g49cA5lpm5e8iZwUKitWXUghMA9t2DXxv0JLCeqE1CnsvZ9SJxPVBqPdYJgz_dA6oJGC4u0DlE6NVvbVD7fOuVF2S_-Ypfkt2yuJavyD2xLMeL4oTssEF0oj-aXzRjCMQ |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+hybrid+air+quality+early-warning+framework%3A+An+hourly+forecasting+model+with+online+sequential+extreme+learning+machines+and+empirical+mode+decomposition+algorithms&rft.jtitle=The+Science+of+the+total+environment&rft.au=Sharma%2C+Ekta&rft.au=Deo%2C+Ravinesh+C&rft.au=Prasad%2C+Ramendra&rft.au=Parisi%2C+Alfio+V&rft.date=2020-03-20&rft.eissn=1879-1026&rft.volume=709&rft.spage=135934&rft_id=info:doi/10.1016%2Fj.scitotenv.2019.135934&rft_id=info%3Apmid%2F31869708&rft.externalDocID=31869708 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0048-9697&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0048-9697&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0048-9697&client=summon |