Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation

Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial corr...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Environmental pollution (1987) Ročník 231; číslo Pt 1; s. 997 - 1004
Hlavní autoři:	Li, Xiang, Peng, Ling, Yao, Xiaojing, Cui, Shaolong, Hu, Yuan, You, Chengzeng, Chi, Tianhe
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	England Elsevier Ltd 01.12.2017
Témata:	Air pollutant concentration predictions air pollutants Air Pollutants - analysis air pollution Air Pollution - statistics & numerical data air quality Beijing China Cities data collection Environmental Monitoring - methods Forecasting Long short-term memory neural network (LSTM NN) memory meteorological data model validation Models, Statistical Models, Theoretical monitoring Multiscale prediction neural networks Neural Networks (Computer) Particulate Matter - analysis particulates prediction public health Recurrent neural network Spatiotemporal correlation China Air pollutant concentration predictions Long short-term memory neural network (LSTM NN) Spatiotemporal correlation Multiscale prediction Recurrent neural network
ISSN:	0269-7491, 1873-6424, 1873-6424
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13–24 h prediction tasks (MAPE = 31.47%). [Display omitted] •Regional air pollutant concentration shows an obvious spatiotemporal correlation.•Our prediction model presents superior performance.•Climate data and metadata can significantly improve the prediction performance. This paper presents a high-accuracy model of air pollutant concentration prediction based on an LSTM neural network, and spatiotemporal correlations are inherently considered.
AbstractList	Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13–24 h prediction tasks (MAPE = 31.47%). Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13–24 h prediction tasks (MAPE = 31.47%). [Display omitted] •Regional air pollutant concentration shows an obvious spatiotemporal correlation.•Our prediction model presents superior performance.•Climate data and metadata can significantly improve the prediction performance. This paper presents a high-accuracy model of air pollutant concentration prediction based on an LSTM neural network, and spatiotemporal correlations are inherently considered. Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13-24 h prediction tasks (MAPE = 31.47%). Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13-24 h prediction tasks (MAPE = 31.47%).Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13-24 h prediction tasks (MAPE = 31.47%).
Author	You, Chengzeng Li, Xiang Peng, Ling Hu, Yuan Cui, Shaolong Chi, Tianhe Yao, Xiaojing
Author_xml	– sequence: 1 givenname: Xiang surname: Li fullname: Li, Xiang organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 2 givenname: Ling surname: Peng fullname: Peng, Ling organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 3 givenname: Xiaojing orcidid: 0000-0001-9745-3150 surname: Yao fullname: Yao, Xiaojing email: yaoxj@radi.ac.cn organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 4 givenname: Shaolong surname: Cui fullname: Cui, Shaolong organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 5 givenname: Yuan surname: Hu fullname: Hu, Yuan organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 6 givenname: Chengzeng orcidid: 0000-0002-4265-3961 surname: You fullname: You, Chengzeng organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China – sequence: 7 givenname: Tianhe surname: Chi fullname: Chi, Tianhe organization: Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/28898956$$D View this record in MEDLINE/PubMed
BookMark	eNqFkU9v1DAQxS1URLeFb4CQj1wS7Nhx7B6QUMU_aREXOFuOPUu9JHawna367fF22wsHepo5_N4bzXsX6CzEAAi9pqSlhIp3-xbCYYlT2xE6tES2lPJnaEPlwBrBO36GNqQTqhm4oufoIuc9IYQzxl6g805KJVUvNqhsY_iF801MpSmQZjzDHNMdDrAmM9VRbmP6jXcxYeMTrvemtZhQsI3BQijJFB8DXhI4b49rvsLfoNxEhx0cYIrLXClsgsNwMNN6j79Ez3dmyvDqYV6in58-_rj-0my_f_56_WHbWC5oacww8mFHCNiBCjZAR6UQjjtOJFFqtD0wwygd3ag6x-rGiOtFP_Sqd6ZThl2ityffJcU_K-SiZ58tTJMJENesu5pIL1ivuidRqpgUNWghKvrmAV3HGZxekp9NutOPoVbg6gTYFHNOsNPWl_vHa1x-0pToY4N6r08N6mODmkhdG6xi_o_40f8J2fuTDGqeBw9JZ-uhVuR8Alu0i_7_Bn8Bwae47Q
CitedBy_id	crossref_primary_10_1016_j_scitotenv_2023_168672 crossref_primary_10_1016_j_jhazmat_2021_125546 crossref_primary_10_3390_sym12122045 crossref_primary_10_1080_13675567_2020_1870674 crossref_primary_10_1016_j_buildenv_2022_109087 crossref_primary_10_3390_info13050223 crossref_primary_10_1007_s12517_021_08484_3 crossref_primary_10_3390_a18030167 crossref_primary_10_1007_s13762_024_05722_5 crossref_primary_10_1155_2020_8854649 crossref_primary_10_1007_s40012_020_00309_0 crossref_primary_10_1007_s00607_020_00849_y crossref_primary_10_1007_s00500_020_05470_x crossref_primary_10_1016_j_bdr_2021_100269 crossref_primary_10_1016_j_ecoinf_2025_103337 crossref_primary_10_1371_journal_pone_0328532 crossref_primary_10_1016_j_apr_2025_102738 crossref_primary_10_1016_j_eswa_2022_118017 crossref_primary_10_1016_j_conengprac_2020_104330 crossref_primary_10_1038_s41598_019_44469_9 crossref_primary_10_1007_s00500_019_04495_1 crossref_primary_10_1007_s12517_021_08628_5 crossref_primary_10_1177_1420326X211011698 crossref_primary_10_1016_j_jocs_2021_101508 crossref_primary_10_1109_ACCESS_2020_3039002 crossref_primary_10_1002_ese3_1037 crossref_primary_10_1007_s11600_024_01486_1 crossref_primary_10_1016_j_chemosphere_2020_127176 crossref_primary_10_1016_j_chemosphere_2024_141284 crossref_primary_10_1016_j_engappai_2023_107559 crossref_primary_10_1016_j_jes_2024_01_057 crossref_primary_10_3390_su15097624 crossref_primary_10_1016_j_scitotenv_2021_151204 crossref_primary_10_3390_s19173740 crossref_primary_10_1016_j_knosys_2022_109996 crossref_primary_10_1007_s12257_020_0253_9 crossref_primary_10_1016_j_asoc_2022_109858 crossref_primary_10_1016_j_apr_2024_102256 crossref_primary_10_1016_j_scitotenv_2024_175233 crossref_primary_10_1016_j_scitotenv_2020_144507 crossref_primary_10_3390_app11135853 crossref_primary_10_1002_for_3098 crossref_primary_10_1016_j_atmosenv_2020_118021 crossref_primary_10_1109_ACCESS_2022_3177604 crossref_primary_10_1016_j_atmosenv_2020_118022 crossref_primary_10_1016_j_jclepro_2019_118955 crossref_primary_10_1016_j_atmosenv_2023_120161 crossref_primary_10_3390_atmos15010131 crossref_primary_10_1016_j_aei_2020_101092 crossref_primary_10_1177_1420326X20974738 crossref_primary_10_1016_j_rser_2019_01_049 crossref_primary_10_1177_0309524X221113013 crossref_primary_10_3390_atmos11040348 crossref_primary_10_1016_j_jclepro_2020_121169 crossref_primary_10_5194_acp_22_4615_2022 crossref_primary_10_1016_j_jclepro_2019_117729 crossref_primary_10_1007_s11356_021_17442_1 crossref_primary_10_1038_s41598_018_34584_4 crossref_primary_10_3390_atmos14091413 crossref_primary_10_1016_j_jag_2025_104774 crossref_primary_10_1109_TGRS_2023_3251375 crossref_primary_10_3390_w15061095 crossref_primary_10_3390_app14167152 crossref_primary_10_1016_j_atmosenv_2023_120077 crossref_primary_10_1016_j_atmosenv_2023_120194 crossref_primary_10_1016_j_envpol_2022_118972 crossref_primary_10_1016_j_jobe_2025_112407 crossref_primary_10_1007_s11869_023_01322_3 crossref_primary_10_1038_s41598_023_39286_0 crossref_primary_10_1016_j_jclepro_2020_123231 crossref_primary_10_3389_fenvs_2022_984879 crossref_primary_10_1016_j_envpol_2021_118569 crossref_primary_10_1007_s12517_021_06982_y crossref_primary_10_3390_atmos12070881 crossref_primary_10_1016_j_scitotenv_2021_145082 crossref_primary_10_1155_2021_6638130 crossref_primary_10_1007_s11869_019_00696_7 crossref_primary_10_1016_j_envpol_2018_05_072 crossref_primary_10_1007_s00521_019_04287_6 crossref_primary_10_1155_2021_6631614 crossref_primary_10_3390_systems10050139 crossref_primary_10_1016_j_apr_2025_102647 crossref_primary_10_1016_j_jclepro_2021_129072 crossref_primary_10_2147_IDR_S232854 crossref_primary_10_3390_rs13234834 crossref_primary_10_1109_ACCESS_2024_3411777 crossref_primary_10_1109_TITS_2022_3166585 crossref_primary_10_1038_s41598_024_56390_x crossref_primary_10_3390_su15118927 crossref_primary_10_1016_j_energy_2023_130045 crossref_primary_10_3390_a15110434 crossref_primary_10_1080_19942060_2022_2126528 crossref_primary_10_3390_s22124418 crossref_primary_10_1002_sd_2706 crossref_primary_10_1016_j_atmosenv_2019_116885 crossref_primary_10_1016_j_asoc_2024_112624 crossref_primary_10_1016_j_jclepro_2024_141259 crossref_primary_10_3390_mi14091804 crossref_primary_10_1080_00032719_2020_1788050 crossref_primary_10_1155_2021_6630944 crossref_primary_10_1016_j_energy_2024_132636 crossref_primary_10_3390_s25010095 crossref_primary_10_1007_s11869_021_01002_0 crossref_primary_10_1007_s10661_022_10603_w crossref_primary_10_1007_s11042_022_12539_2 crossref_primary_10_1016_j_buildenv_2021_108436 crossref_primary_10_1088_1755_1315_237_2_022027 crossref_primary_10_1016_j_jhydrol_2021_126573 crossref_primary_10_1007_s11063_022_11119_7 crossref_primary_10_1016_j_jksuci_2022_02_025 crossref_primary_10_3389_fpubh_2022_933665 crossref_primary_10_1007_s00521_021_06067_7 crossref_primary_10_1038_s41598_023_31569_w crossref_primary_10_1002_er_7341 crossref_primary_10_1016_j_jastp_2025_106583 crossref_primary_10_3390_ijerph18031024 crossref_primary_10_1016_j_apr_2020_09_003 crossref_primary_10_1016_j_isprsjprs_2022_03_002 crossref_primary_10_1016_j_hazadv_2025_100782 crossref_primary_10_3390_atmos13060874 crossref_primary_10_3390_ijerph15071322 crossref_primary_10_3390_sym12050861 crossref_primary_10_1007_s11518_023_5562_z crossref_primary_10_3390_atmos10120740 crossref_primary_10_1177_00219983241248216 crossref_primary_10_3390_atmos13060959 crossref_primary_10_1007_s13762_024_05944_7 crossref_primary_10_1016_j_scitotenv_2021_149654 crossref_primary_10_1016_j_asoc_2020_106957 crossref_primary_10_1080_0952813X_2019_1572658 crossref_primary_10_3390_atmos14111604 crossref_primary_10_3390_environments10120218 crossref_primary_10_3390_su132111889 crossref_primary_10_1016_j_jclepro_2018_10_129 crossref_primary_10_3390_e24040457 crossref_primary_10_3390_atmos13091462 crossref_primary_10_1016_j_buildenv_2021_108537 crossref_primary_10_1038_s41598_024_71269_7 crossref_primary_10_1155_2018_3506394 crossref_primary_10_1007_s11069_025_07408_8 crossref_primary_10_3390_atmos15070856 crossref_primary_10_1016_j_scs_2021_103427 crossref_primary_10_1080_1064119X_2022_2136045 crossref_primary_10_3390_atmos13101719 crossref_primary_10_1007_s11042_019_07993_4 crossref_primary_10_1016_j_heliyon_2023_e22569 crossref_primary_10_1016_j_scitotenv_2022_155324 crossref_primary_10_2298_TSCI2503951Z crossref_primary_10_1016_j_envsoft_2022_105329 crossref_primary_10_1016_j_atmosenv_2024_120730 crossref_primary_10_3390_info14040243 crossref_primary_10_3390_pr10010171 crossref_primary_10_1109_ACCESS_2022_3174853 crossref_primary_10_3390_s18072220 crossref_primary_10_1109_ACCESS_2023_3314490 crossref_primary_10_1109_TBDATA_2020_3005368 crossref_primary_10_3390_atmos12060686 crossref_primary_10_1016_j_buildenv_2020_107135 crossref_primary_10_1016_j_watres_2022_118040 crossref_primary_10_3390_atmos14050816 crossref_primary_10_1007_s00521_022_08036_0 crossref_primary_10_1016_j_compchemeng_2024_108659 crossref_primary_10_1016_j_dche_2023_100093 crossref_primary_10_3390_w10111655 crossref_primary_10_1016_j_scs_2020_102237 crossref_primary_10_1080_13658816_2024_2310737 crossref_primary_10_3390_rs15133348 crossref_primary_10_1016_j_ecoenv_2023_115572 crossref_primary_10_1016_j_ecolmodel_2020_109017 crossref_primary_10_3390_app122010433 crossref_primary_10_1007_s11356_022_20375_y crossref_primary_10_1016_j_cscm_2025_e04486 crossref_primary_10_3390_atmos14050832 crossref_primary_10_1016_j_autcon_2020_103178 crossref_primary_10_3390_e26121062 crossref_primary_10_1016_j_uclim_2025_102338 crossref_primary_10_1016_j_matpr_2021_04_239 crossref_primary_10_1002_cjce_23665 crossref_primary_10_1016_j_heliyon_2023_e14526 crossref_primary_10_3390_atmos14081228 crossref_primary_10_1016_j_eswa_2023_121487 crossref_primary_10_1016_j_scitotenv_2023_167892 crossref_primary_10_1007_s00704_020_03305_1 crossref_primary_10_1007_s41810_025_00300_9 crossref_primary_10_1016_j_jclepro_2020_125341 crossref_primary_10_1155_2021_6660102 crossref_primary_10_1007_s00477_024_02694_3 crossref_primary_10_3390_ai2040030 crossref_primary_10_3390_su17062546 crossref_primary_10_1109_ACCESS_2020_3016289 crossref_primary_10_1038_s41598_024_70152_9 crossref_primary_10_1016_j_jenvman_2021_112438 crossref_primary_10_1007_s11269_020_02759_2 crossref_primary_10_1016_j_jwpe_2025_106941 crossref_primary_10_1002_cpe_7035 crossref_primary_10_1016_j_scitotenv_2024_174229 crossref_primary_10_3390_atmos15070799 crossref_primary_10_1016_j_buildenv_2019_106282 crossref_primary_10_1016_j_procs_2024_04_139 crossref_primary_10_1038_s41598_024_67626_1 crossref_primary_10_1016_j_envint_2022_107691 crossref_primary_10_3390_atmos13081221 crossref_primary_10_1007_s10462_021_09991_1 crossref_primary_10_1016_j_knosys_2019_105239 crossref_primary_10_1007_s11069_021_04504_3 crossref_primary_10_1016_j_atmosenv_2024_120531 crossref_primary_10_1016_j_scitotenv_2021_149509 crossref_primary_10_1016_j_uclim_2025_102359 crossref_primary_10_1007_s11227_020_03182_5 crossref_primary_10_3390_atmos13091377 crossref_primary_10_3390_info14110598 crossref_primary_10_1007_s11432_020_2951_1 crossref_primary_10_1109_TITS_2022_3219882 crossref_primary_10_1016_j_jclepro_2019_119841 crossref_primary_10_3390_app15179274 crossref_primary_10_1002_srin_202400656 crossref_primary_10_1109_TKDE_2020_3047634 crossref_primary_10_3390_su14095104 crossref_primary_10_3390_su16010165 crossref_primary_10_1016_j_apr_2022_101363 crossref_primary_10_1007_s12517_021_07164_6 crossref_primary_10_1016_j_chemosphere_2021_133124 crossref_primary_10_3390_s21041064 crossref_primary_10_3390_atmos15040460 crossref_primary_10_1016_j_ast_2019_105423 crossref_primary_10_1007_s10666_023_09902_4 crossref_primary_10_1007_s11071_020_05646_y crossref_primary_10_1007_s00703_022_00946_x crossref_primary_10_1016_j_apr_2023_101765 crossref_primary_10_3390_atmos13101527 crossref_primary_10_3233_IDT_220111 crossref_primary_10_3390_ijerph18094905 crossref_primary_10_1016_j_psep_2023_04_008 crossref_primary_10_3390_rs13071284 crossref_primary_10_1016_j_eswa_2024_125931 crossref_primary_10_1016_j_ecoenv_2023_114911 crossref_primary_10_1109_ACCESS_2024_3368034 crossref_primary_10_1016_j_chemosphere_2019_01_121 crossref_primary_10_3390_su142013191 crossref_primary_10_1016_j_techfore_2024_123684 crossref_primary_10_1016_j_uclim_2022_101363 crossref_primary_10_3390_app122111155 crossref_primary_10_1016_j_envpol_2024_124040 crossref_primary_10_3390_w13040516 crossref_primary_10_1007_s11356_022_18913_9 crossref_primary_10_1016_j_scs_2020_102567 crossref_primary_10_1007_s40726_020_00159_z crossref_primary_10_1016_j_envpol_2020_115216 crossref_primary_10_1016_j_asoc_2021_107988 crossref_primary_10_1080_19942060_2025_2507753 crossref_primary_10_1016_j_jes_2025_07_011 crossref_primary_10_1016_j_apr_2021_101168 crossref_primary_10_1016_j_engappai_2024_108231 crossref_primary_10_1016_j_envint_2018_11_042 crossref_primary_10_4218_etrij_2021_0396 crossref_primary_10_1016_j_atmosenv_2022_119362 crossref_primary_10_1016_j_compeleceng_2025_110718 crossref_primary_10_1016_j_jhazmat_2022_128730 crossref_primary_10_1016_j_neucom_2023_126280 crossref_primary_10_1007_s12517_021_07897_4 crossref_primary_10_1007_s11081_024_09904_5 crossref_primary_10_3390_w12061822 crossref_primary_10_1007_s00477_020_01776_2 crossref_primary_10_3390_su15097367 crossref_primary_10_3390_ijerph15122886 crossref_primary_10_1016_j_wasman_2023_08_004 crossref_primary_10_1029_2019EA000641 crossref_primary_10_1016_j_buildenv_2024_112463 crossref_primary_10_3389_feart_2025_1509489 crossref_primary_10_1016_j_jclepro_2020_121941 crossref_primary_10_1016_j_scitotenv_2019_01_333 crossref_primary_10_3390_j5020015 crossref_primary_10_1007_s11356_019_05116_y crossref_primary_10_1007_s11869_025_01713_8 crossref_primary_10_1016_j_apr_2021_101144 crossref_primary_10_1029_2023MS003789 crossref_primary_10_1016_j_atmosenv_2022_119347 crossref_primary_10_3390_atmos14081274 crossref_primary_10_1038_s41598_022_21769_1 crossref_primary_10_1007_s11356_023_28877_z crossref_primary_10_3390_ijerph19073988 crossref_primary_10_3390_jmse9111231 crossref_primary_10_1007_s11356_022_21768_9 crossref_primary_10_3390_ijerph16224482 crossref_primary_10_3390_atmos10040223 crossref_primary_10_1007_s11356_022_22454_6 crossref_primary_10_3233_JIFS_222920 crossref_primary_10_1016_j_ecolmodel_2022_109913 crossref_primary_10_1016_j_jclepro_2020_120983 crossref_primary_10_1155_2022_9759988 crossref_primary_10_21324_dacd_1628030 crossref_primary_10_3390_en14206501 crossref_primary_10_1016_j_ecoinf_2023_102437 crossref_primary_10_3390_s23218863 crossref_primary_10_1016_j_envpol_2023_121509 crossref_primary_10_1038_s41598_020_60102_6 crossref_primary_10_1080_19942060_2021_1926328 crossref_primary_10_3390_pr8080976 crossref_primary_10_1016_j_eswa_2022_118422 crossref_primary_10_1016_j_envsci_2020_10_004 crossref_primary_10_1038_s41598_025_16664_4 crossref_primary_10_3390_app10010014 crossref_primary_10_1016_j_envpol_2019_113187 crossref_primary_10_3390_s21062160 crossref_primary_10_1007_s10651_021_00501_8 crossref_primary_10_1109_ACCESS_2019_2932445 crossref_primary_10_1007_s00521_021_06082_8 crossref_primary_10_1186_s40537_024_01002_8 crossref_primary_10_1016_j_jclepro_2021_126493 crossref_primary_10_1109_ACCESS_2020_3028852 crossref_primary_10_1007_s00521_019_04282_x crossref_primary_10_1016_j_envpol_2024_125071 crossref_primary_10_1016_j_chemosphere_2018_12_128 crossref_primary_10_1016_j_jclepro_2020_122835 crossref_primary_10_1016_j_jclepro_2020_122956 crossref_primary_10_1016_j_eswa_2020_114513 crossref_primary_10_1007_s12145_024_01330_6 crossref_primary_10_1109_ACCESS_2019_2932118 crossref_primary_10_1109_TIM_2021_3091511 crossref_primary_10_1016_j_apr_2023_101832 crossref_primary_10_3390_su15129713 crossref_primary_10_1109_JIOT_2023_3322862 crossref_primary_10_1016_j_jconhyd_2023_104262 crossref_primary_10_1016_j_scitotenv_2022_153948 crossref_primary_10_1111_coin_12399 crossref_primary_10_1109_ACCESS_2023_3327707 crossref_primary_10_3390_atmos14020340 crossref_primary_10_1016_j_jclepro_2020_122722 crossref_primary_10_1109_TKDE_2023_3270118 crossref_primary_10_1007_s12652_022_04422_7 crossref_primary_10_1186_s42834_023_00175_w crossref_primary_10_1007_s00521_019_04678_9 crossref_primary_10_1016_j_envpol_2023_122402 crossref_primary_10_1111_exsy_12511 crossref_primary_10_1016_j_envsci_2020_10_015 crossref_primary_10_1016_j_atmosenv_2025_121328 crossref_primary_10_1016_j_jclepro_2021_129660 crossref_primary_10_1016_j_scitotenv_2019_07_367 crossref_primary_10_3390_atmos15050594 crossref_primary_10_15407_srenergy2025_03_081 crossref_primary_10_1371_journal_pone_0330465 crossref_primary_10_1109_ACCESS_2020_3038853 crossref_primary_10_3390_atmos16040366 crossref_primary_10_1016_j_envint_2025_109705 crossref_primary_10_1016_j_jweia_2024_105869 crossref_primary_10_1088_1742_6596_1780_1_012015 crossref_primary_10_1109_TGRS_2024_3514158 crossref_primary_10_1016_j_apr_2024_102144 crossref_primary_10_1016_j_atech_2025_101105 crossref_primary_10_1016_j_jclepro_2021_128358 crossref_primary_10_1016_j_scitotenv_2019_135771 crossref_primary_10_1016_j_cie_2019_106246 crossref_primary_10_3390_atmos16030320 crossref_primary_10_1155_2019_1934796 crossref_primary_10_5194_acp_19_10009_2019 crossref_primary_10_3390_electronics10202518 crossref_primary_10_1016_j_envsoft_2025_106501 crossref_primary_10_1038_s41598_025_94654_2 crossref_primary_10_1109_TIM_2023_3341116 crossref_primary_10_2112_JCOASTRES_D_21_00011_1 crossref_primary_10_1038_s41598_022_17754_3 crossref_primary_10_1038_s41598_019_50177_1 crossref_primary_10_1155_2021_5573650 crossref_primary_10_3390_su14042068 crossref_primary_10_3389_fenvs_2022_979918 crossref_primary_10_1002_cjce_25181 crossref_primary_10_1016_j_apr_2024_102162 crossref_primary_10_3390_ijerph18147650 crossref_primary_10_1016_j_asoc_2018_07_030 crossref_primary_10_1061_JPCFEV_CFENG_4390 crossref_primary_10_1155_2021_1616806 crossref_primary_10_1016_j_atmosenv_2020_118182 crossref_primary_10_1016_j_psep_2024_03_042 crossref_primary_10_3233_JIFS_202481 crossref_primary_10_5194_acp_19_12935_2019 crossref_primary_10_1007_s11356_021_12658_7 crossref_primary_10_1016_j_inffus_2020_01_002 crossref_primary_10_3390_ijerph17249471 crossref_primary_10_1016_j_jclepro_2023_137568 crossref_primary_10_1038_s41598_023_28287_8 crossref_primary_10_3390_w15193515 crossref_primary_10_4018_IJIIT_2019100105 crossref_primary_10_3390_atmos16040359 crossref_primary_10_1016_j_cie_2024_110662 crossref_primary_10_3390_atmos14030467 crossref_primary_10_3390_aerospace8040115 crossref_primary_10_1007_s40747_021_00476_w crossref_primary_10_3390_su15118881 crossref_primary_10_1007_s11356_022_22512_z crossref_primary_10_1177_23998083221111162 crossref_primary_10_3390_app10061953 crossref_primary_10_1002_for_2599 crossref_primary_10_3390_a17100457 crossref_primary_10_1016_j_jes_2023_02_026
Cites_doi	10.1016/j.apr.2016.01.004 10.1016/j.atmosenv.2005.01.050 10.1061/(ASCE)0733-9372(2002)128:12(1146) 10.1016/j.atmosenv.2009.10.045 10.1504/IJEP.2013.059921 10.1016/j.atmosenv.2008.07.020 10.1016/j.atmosenv.2011.04.032 10.3155/1047-3289.61.1.69 10.1098/rspl.1895.0041 10.1016/j.scitotenv.2012.10.110 10.1016/j.atmosenv.2008.01.068 10.1023/A:1013833217916 10.1016/j.atmosenv.2011.02.001 10.5194/acp-8-523-2008 10.1078/1438-4639-00306 10.1007/s10666-011-9270-6 10.1162/neco.1997.9.8.1735 10.1016/j.atmosenv.2006.07.039 10.1001/jama.287.9.1132 10.1016/j.eswa.2010.05.093 10.1056/NEJM199312093292401 10.4209/aaqr.2015.04.0249 10.1016/j.atmosenv.2011.01.022 10.1016/j.atmosenv.2003.12.044 10.1162/neco.1990.2.4.490 10.1016/j.atmosenv.2005.07.030 10.1016/j.jhydrol.2010.11.002 10.1016/j.atmosenv.2010.11.031 10.1007/s00521-015-1955-3 10.1016/j.atmosenv.2013.04.002 10.1007/s11356-016-7812-9 10.1016/j.trc.2015.03.014 10.1007/s11356-010-0375-2 10.1016/j.atmosenv.2014.04.030 10.1016/S1352-2310(00)00385-X
ContentType	Journal Article
Copyright	2017 Elsevier Ltd Copyright © 2017 Elsevier Ltd. All rights reserved.
Copyright_xml	– notice: 2017 Elsevier Ltd – notice: Copyright © 2017 Elsevier Ltd. All rights reserved.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 7S9 L.6
DOI	10.1016/j.envpol.2017.08.114
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic AGRICOLA AGRICOLA - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic AGRICOLA AGRICOLA - Academic
DatabaseTitleList	AGRICOLA MEDLINE MEDLINE - Academic
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	Engineering Anatomy & Physiology Environmental Sciences Public Health
EISSN	1873-6424
EndPage	1004
ExternalDocumentID	28898956 10_1016_j_envpol_2017_08_114 S0269749117307534
Genre	Journal Article
GeographicLocations	China
GeographicLocations_xml	– name: China
GroupedDBID	--- --K --M -~X .~1 0R~ 1B1 1RT 1~. 29G 4.4 457 53G 5GY 5VS 6TJ 71M 8P~ 9JM AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABEFU ABFNM ABFYP ABJNI ABLST ABMAC ABXDB ABYKQ ACDAQ ACGFS ACIUM ACRLP ADBBV ADEZE ADMUD AEBSH AEKER AENEX AFFNX AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AI. AIEXJ AIKHN AITUG AJBFU AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG AVWKF AXJTR AZFZN BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HLV HMC HVGLF HZ~ IHE J1W KCYFY KOM LW9 LY9 M41 MO0 N9A O-L O9- OAUVE OHT OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SAB SCC SCU SDF SDG SDP SEN SES SEW SPCBC SSJ SSZ T5K TWZ VH1 WH7 WUQ XJT XOL XPP ZMT ~G- 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEGFY AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD CGR CUY CVF ECM EIF NPM 7X8 7S9 L.6
ID	FETCH-LOGICAL-c461t-a7b47f00ec71637e21866d4d408099bc5e3a311bdb92d331130d5657595da29a3
ISICitedReferencesCount	481
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000414881000101&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0269-7491 1873-6424
IngestDate	Thu Oct 02 09:20:47 EDT 2025 Sun Nov 09 11:00:10 EST 2025 Wed Feb 19 02:40:46 EST 2025 Tue Nov 18 21:29:49 EST 2025 Sat Nov 29 02:06:50 EST 2025 Fri Feb 23 02:28:07 EST 2024
IsPeerReviewed	true
IsScholarly	true
Issue	Pt 1
Keywords	Air pollutant concentration predictions Long short-term memory neural network (LSTM NN) Spatiotemporal correlation Multiscale prediction Recurrent neural network
Language	English
License	Copyright © 2017 Elsevier Ltd. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c461t-a7b47f00ec71637e21866d4d408099bc5e3a311bdb92d331130d5657595da29a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0001-9745-3150 0000-0002-4265-3961
PMID	28898956
PQID	1938601766
PQPubID	23479
PageCount	8
ParticipantIDs	proquest_miscellaneous_2000563592 proquest_miscellaneous_1938601766 pubmed_primary_28898956 crossref_citationtrail_10_1016_j_envpol_2017_08_114 crossref_primary_10_1016_j_envpol_2017_08_114 elsevier_sciencedirect_doi_10_1016_j_envpol_2017_08_114
PublicationCentury	2000
PublicationDate	2017-12-01
PublicationDateYYYYMMDD	2017-12-01
PublicationDate_xml	– month: 12 year: 2017 text: 2017-12-01 day: 01
PublicationDecade	2010
PublicationPlace	England
PublicationPlace_xml	– name: England
PublicationTitle	Environmental pollution (1987)
PublicationTitleAlternate	Environ Pollut
PublicationYear	2017
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Bruckman (bib7) 1993 Feng, Zhang, Sun, Zhang (bib14) 2011; 45 He, Yu, Liu, Zhao (bib16) 2013; 53 Box, Jenkins (bib5) 1976; 22 Neuberger, Schimek, Horak, Moshammer, Kundi, Frischer, Gomiscek, Puxbaum, Hauck (bib33) 2004; 38 Kurt, Oktay (bib26) 2010; 37 Wilson, Kingham, Pearce, Sturman (bib45) 2005; 39 Dockery, Pope, Xu, Spengler, Ware, Fay, Ferris, Benjamin, Speizer (bib12) 1993; 329 Díaz-Robles, Ortega, Fu, Reed, Chow, Watson, Moncada-Herrera (bib11) 2008; 42 Ma, Tao, Wang, Yu, Wang (bib31) 2015; 54 Nieto, Combarro, Del Coz Díaz, Montañés (bib48) 2013; 219 Prakash, Kumar, Kumar, Jain (bib37) 2011; 16 Yoon, Jun, Hyun, Bae, Lee (bib46) 2011; 396 Guocai (bib15) 2004; 12 Williams, Peng (bib44) 1990; 2 Chen, Shi, Shu, Gao (bib9) 2013; 74 Wang, Maeda, Hayashi, Hsiao, Liu (bib43) 2001; 130 Kappos, Bruckmann, Eikmann, Englert, Heinrich, Höppe, Koch, Krause, Kreyling, Rauchfuss (bib22) 2004; 207 Alahi, Goel, Ramanathan, Robicquet, Fei-Fei, Savarese (bib1) 2016 Ong, Sugiura, Zettsu (bib34) 2016; 27 Baklanov, Mestayer, Clappier, Zilitinkevich, Joffre, Mahura, Nielsen (bib4) 2008; 8 Kolehmainen, Martikainen, Ruuskanen (bib24) 2001; 35 Sak, Yang, Li, Li (bib40) 2016 Felder, Kaifel, Graves (bib13) 2010 Coats (bib10) 1996 Krewski, Jerrett, Burnett, Ma, Hughes, Shi, Turner, Pope, Thurston, Calle, Thun, Beckerman, DeLuca, Finkelstein, Ito, Moore, Newbold, Ramsay, Ross, Shin, Tempalski (bib25) 2009; 140 Lu, Wang, Fan, Leung, Xu, Lo, Wong (bib29) 2002; 128 Bravo, Bell (bib6) 2011; 61 Hooyberghs, Mensink, Dumont, Fierens, Brasseur (bib19) 2005; 39 Vautard, Builtjes, Thunis, Cuvelier, Bedogni, Bessagnet, Honore, Moussiopoulos, Pirovano, Schaap (bib42) 2007; 41 Jeong, Park, Woo, Han, Yi (bib21) 2011; 45 Kim, Fu, Miller (bib23) 2010; 44 Bai, Li, Wang, Xie, Li (bib3) 2016; 7 Iii, Burnett, Thun, Calle, Krewski, Ito, Thurston (bib20) 2002; 287 Li, Peng, Hu, Shao, Chi (bib28) 2016; 23 Robinson, Fallside (bib38) 1987 Zheng, Liu, Hsieh (bib47) 2013 Antanasijević, Pocajt, Povrenović, Ristić, Perić-Grujić (bib2) 2013; 443 Lurmann (bib30) 2000 Paschalidou, Karakitsios, Kleanthous, Kassomenos (bib35) 2011; 18 Li, Hsu, Tsay (bib27) 2011; 45 Hochreiter, Schmidhuber (bib18) 1997; 9 Chen, Lu, Avise, DaMassa, Kleeman, Kaduwela (bib8) 2014; 92 Mishra, Goyal (bib32) 2016; 16 Stern, Builtjes, Schaap, Timmermans, Vautard, Hodzic, Memmesheimer, Feldmann, Renner, Wolke (bib41) 2008; 42 Lv, Duan, Kang, Li, Wang (bib49) 2015; 16 Pearson (bib36) 1895; 58 Saide, Carmichael, Spak, Gallardo, Osses, Mena-Carrasco, Pagowski (bib39) 2011; 45 Baklanov (10.1016/j.envpol.2017.08.114_bib4) 2008; 8 Chen (10.1016/j.envpol.2017.08.114_bib9) 2013; 74 Coats (10.1016/j.envpol.2017.08.114_bib10) 1996 Kolehmainen (10.1016/j.envpol.2017.08.114_bib24) 2001; 35 Yoon (10.1016/j.envpol.2017.08.114_bib46) 2011; 396 Box (10.1016/j.envpol.2017.08.114_bib5) 1976; 22 Prakash (10.1016/j.envpol.2017.08.114_bib37) 2011; 16 Wang (10.1016/j.envpol.2017.08.114_bib43) 2001; 130 Neuberger (10.1016/j.envpol.2017.08.114_bib33) 2004; 38 Robinson (10.1016/j.envpol.2017.08.114_bib38) 1987 Kim (10.1016/j.envpol.2017.08.114_bib23) 2010; 44 Hooyberghs (10.1016/j.envpol.2017.08.114_bib19) 2005; 39 Sak (10.1016/j.envpol.2017.08.114_bib40) 2016 Kappos (10.1016/j.envpol.2017.08.114_bib22) 2004; 207 Lv (10.1016/j.envpol.2017.08.114_bib49) 2015; 16 Saide (10.1016/j.envpol.2017.08.114_bib39) 2011; 45 Díaz-Robles (10.1016/j.envpol.2017.08.114_bib11) 2008; 42 Krewski (10.1016/j.envpol.2017.08.114_bib25) 2009; 140 Feng (10.1016/j.envpol.2017.08.114_bib14) 2011; 45 Guocai (10.1016/j.envpol.2017.08.114_bib15) 2004; 12 Paschalidou (10.1016/j.envpol.2017.08.114_bib35) 2011; 18 Ma (10.1016/j.envpol.2017.08.114_bib31) 2015; 54 Lu (10.1016/j.envpol.2017.08.114_bib29) 2002; 128 Mishra (10.1016/j.envpol.2017.08.114_bib32) 2016; 16 Stern (10.1016/j.envpol.2017.08.114_bib41) 2008; 42 Bravo (10.1016/j.envpol.2017.08.114_bib6) 2011; 61 He (10.1016/j.envpol.2017.08.114_bib16) 2013; 53 Kurt (10.1016/j.envpol.2017.08.114_bib26) 2010; 37 Vautard (10.1016/j.envpol.2017.08.114_bib42) 2007; 41 Alahi (10.1016/j.envpol.2017.08.114_bib1) 2016 Ong (10.1016/j.envpol.2017.08.114_bib34) 2016; 27 Chen (10.1016/j.envpol.2017.08.114_bib8) 2014; 92 Nieto (10.1016/j.envpol.2017.08.114_bib48) 2013; 219 Li (10.1016/j.envpol.2017.08.114_bib27) 2011; 45 Zheng (10.1016/j.envpol.2017.08.114_bib47) 2013 Wilson (10.1016/j.envpol.2017.08.114_bib45) 2005; 39 Pearson (10.1016/j.envpol.2017.08.114_bib36) 1895; 58 Bruckman (10.1016/j.envpol.2017.08.114_bib7) 1993 Dockery (10.1016/j.envpol.2017.08.114_bib12) 1993; 329 Iii (10.1016/j.envpol.2017.08.114_bib20) 2002; 287 Williams (10.1016/j.envpol.2017.08.114_bib44) 1990; 2 Antanasijević (10.1016/j.envpol.2017.08.114_bib2) 2013; 443 Jeong (10.1016/j.envpol.2017.08.114_bib21) 2011; 45 Bai (10.1016/j.envpol.2017.08.114_bib3) 2016; 7 Li (10.1016/j.envpol.2017.08.114_bib28) 2016; 23 Hochreiter (10.1016/j.envpol.2017.08.114_bib18) 1997; 9 Felder (10.1016/j.envpol.2017.08.114_bib13) 2010 Lurmann (10.1016/j.envpol.2017.08.114_bib30) 2000
References_xml	– start-page: 961 year: 2016 end-page: 971 ident: bib1 article-title: Social lstm: human trajectory prediction in crowded spaces publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 443 start-page: 511 year: 2013 end-page: 519 ident: bib2 article-title: PM 10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization publication-title: Sci. Total Environ. – volume: 2 start-page: 490 year: 1990 end-page: 501 ident: bib44 article-title: An efficient gradient-based algorithm for on-line training of recurrent network trajectories publication-title: Neural Comput. – start-page: 562 year: 1993 ident: bib7 article-title: Overview of the enhanced geocoded emissions modeling and projection (Enhanced GEMAP) system publication-title: Proceeding of the Air & Waste Management Association's Regional Photochemical Measurements and Modeling Studies Conference – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: bib18 article-title: Long short-term memory publication-title: Neural Comput. – volume: 37 start-page: 7986 year: 2010 end-page: 7992 ident: bib26 article-title: Forecasting air pollutant indicator levels with geographic models 3days in advance using neural networks publication-title: Expert Syst. Appl. – year: 2000 ident: bib30 article-title: Simplification of the UAMAERO Model for Seasonal and Annual Modeling: the UAMAERO-LT Model – volume: 16 start-page: 166 year: 2016 end-page: 174 ident: bib32 article-title: Neuro-fuzzy approach to forecast NO2 pollutants addressed to air quality dispersion model over Delhi, India publication-title: Aerosol Air Qual. Res. – volume: 61 start-page: 69 year: 2011 end-page: 77 ident: bib6 article-title: Spatial heterogeneity of PM10 and O3 in Săo Paulo, Brazil, and implications for human health studies publication-title: J. Air & Waste Manag. Assoc. – volume: 39 start-page: 3279 year: 2005 end-page: 3289 ident: bib19 article-title: A neural network forecast for daily average PM 10 concentrations in Belgium publication-title: Atmos. Environ. – volume: 92 start-page: 182 year: 2014 end-page: 190 ident: bib8 article-title: Seasonal modeling of PM 2.5 in California's san Joaquin valley publication-title: Atmos. Environ. – volume: 74 start-page: 346 year: 2013 end-page: 359 ident: bib9 article-title: Ensemble and enhanced PM10 concentration forecast model based on stepwise regression and wavelet analysis publication-title: Atmos. Environ. – volume: 42 start-page: 4567 year: 2008 end-page: 4588 ident: bib41 article-title: A model inter-comparison study focussing on episodes with elevated PM10 concentrations publication-title: Atmos. Environ. – volume: 42 start-page: 8331 year: 2008 end-page: 8340 ident: bib11 article-title: A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile publication-title: Atmos. Environ. – volume: 39 start-page: 6444 year: 2005 end-page: 6462 ident: bib45 article-title: A review of intraurban variations in particulate air pollution: implications for epidemiological research publication-title: Atmos. Environ. – volume: 23 start-page: 22408 year: 2016 end-page: 22417 ident: bib28 article-title: Deep learning architecture for air quality predictions publication-title: Environ. Sci. Pollut. Res. – volume: 7 start-page: 557 year: 2016 end-page: 566 ident: bib3 article-title: Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions publication-title: Atmos. Pollut. Res. – volume: 58 start-page: 240 year: 1895 end-page: 242 ident: bib36 article-title: Note on regression and inheritance in the case of two parents publication-title: Proc. R. Soc. Lond. – year: 2010 ident: bib13 article-title: Wind power prediction using mixture density recurrent neural networks publication-title: Poster Presentation gehalten auf der European Wind Energy Conference – volume: 45 start-page: 1116 year: 2011 end-page: 1125 ident: bib21 article-title: Source contributions to carbonaceous aerosol concentrations in Korea publication-title: Atmos. Environ. – volume: 44 start-page: 523 year: 2010 end-page: 532 ident: bib23 article-title: Improving ozone modeling in complex terrain at a fine grid resolution: Part I–examination of analysis nudging and all PBL schemes associated with LSMs in meteorological model publication-title: Atmos. Environ. – volume: 54 start-page: 187 year: 2015 end-page: 197 ident: bib31 article-title: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data publication-title: Transp. Res. Part C Emerg. Technol. – volume: 329 start-page: 1753 year: 1993 end-page: 1759 ident: bib12 article-title: An association between air pollution and mortality in six U.S. cities publication-title: N. Engl. J. Med. – volume: 45 start-page: 1979 year: 2011 end-page: 1985 ident: bib14 article-title: Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification publication-title: Atmos. Environ. – volume: 45 start-page: 3663 year: 2011 end-page: 3675 ident: bib27 article-title: A study on the potential applications of satellite data in air quality monitoring and forecasting publication-title: Atmos. Environ. – volume: 41 start-page: 173 year: 2007 end-page: 188 ident: bib42 article-title: Evaluation and intercomparison of Ozone and PM10 simulations by several chemistry transport models over four European cities within the CityDelta project publication-title: Atmos. Environ. – start-page: 584 year: 1996 end-page: 588 ident: bib10 article-title: High-performance algorithms in the sparse matrix operator kernel emissions (SMOKE) modeling system publication-title: Proc. Ninth AMS Joint Conference on Applications of Air Pollution Meteorology with A&WMA, Amer. Meteor. Soc. – volume: 16 start-page: 503 year: 2011 end-page: 517 ident: bib37 article-title: A wavelet-based neural network model to predict ambient air pollutants' concentration publication-title: Environ. Model. Assess. – volume: 8 start-page: 523 year: 2008 end-page: 543 ident: bib4 article-title: Towards improving the simulation of meteorological fields in urban areas through updated/advanced surface fluxes description publication-title: Atmos. Chem. Phys. – year: 2016 ident: bib40 article-title: Modeling Dependence Dynamics of Air Pollution: Pollution Risk Simulation and Prediction of PM $ _ {2.5} $ Levels – volume: 27 start-page: 1553 year: 2016 end-page: 1566 ident: bib34 article-title: Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5 publication-title: Neural Comput. Appl. – volume: 18 start-page: 316 year: 2011 end-page: 327 ident: bib35 article-title: Forecasting hourly PM10 concentration in Cyprus through artificial neural networks and multiple regression models: implications to local environmental management publication-title: Environ. Sci. Pollut. Res. – volume: 22 start-page: 199 year: 1976 end-page: 201 ident: bib5 article-title: Time series analysis: forecasting and control publication-title: J. Operational Res. Soc. – volume: 130 start-page: 391 year: 2001 end-page: 396 ident: bib43 article-title: A nested air quality prediction modeling system for urban and regional scales: application for high-ozone episode in Taiwan publication-title: Water, Air, Soil Pollut. – volume: 45 start-page: 2769 year: 2011 end-page: 2780 ident: bib39 article-title: Forecasting urban PM10 and PM2. 5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF–Chem CO tracer model publication-title: Atmos. Environ. – start-page: 1436 year: 2013 end-page: 1444 ident: bib47 article-title: U-Air: when urban air quality inference meets big data publication-title: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – volume: 207 start-page: 399 year: 2004 end-page: 407 ident: bib22 article-title: Health effects of particles in ambient air publication-title: Int. J. Hyg. Environ. Health – volume: 287 start-page: 1132 year: 2002 end-page: 1141 ident: bib20 article-title: Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution publication-title: Jama J. Am. Med. Assoc. – volume: 128 start-page: 1146 year: 2002 end-page: 1157 ident: bib29 article-title: Prediction of pollutant levels in causeway bay area of Hong Kong using an improved neural network model publication-title: J. Environ. Eng.-ASCE – volume: 38 start-page: 3971 year: 2004 end-page: 3981 ident: bib33 article-title: Acute effects of particulate matter on respiratory diseases, symptoms and functions:: epidemiological results of the Austrian Project on Health Effects of Particulate Matter (AUPHEP) publication-title: Atmos. Environ. – year: 1987 ident: bib38 article-title: The Utility Driven Dynamic Error Propagation Network – volume: 219 start-page: 8923 year: 2013 end-page: 8937 ident: bib48 article-title: A SVM-based regression model to study the air quality at local scale in Oviedo urban area (Northern Spain): a case study publication-title: Appl. Math. Comput. – volume: 12 start-page: 5 year: 2004 ident: bib15 article-title: Progress of weather research and forecast (WRF) model and application in the United States publication-title: Meteorol. Mon. – volume: 16 start-page: 1 year: 2015 end-page: 9 ident: bib49 article-title: Traffic flow prediction with big data: a deep learning approach publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 140 start-page: 5 year: 2009 ident: bib25 article-title: Extended follow-up and spatial analysis of the American Cancer Society study linking particulate air pollution and mortality publication-title: Res. Rep. Health Eff. Inst. – volume: 53 start-page: 265 year: 2013 end-page: 286 ident: bib16 article-title: Numerical model-based relationship between meteorological conditions and air quality and its implication for urban air quality management publication-title: Int. J. Environ. Pollut. – volume: 396 start-page: 128 year: 2011 end-page: 138 ident: bib46 article-title: A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer publication-title: J. Hydrol. – volume: 35 start-page: 815 year: 2001 end-page: 825 ident: bib24 article-title: Neural networks and periodic components used in air quality forecasting publication-title: Atmos. Environ. – volume: 7 start-page: 557 year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib3 article-title: Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions publication-title: Atmos. Pollut. Res. doi: 10.1016/j.apr.2016.01.004 – volume: 39 start-page: 3279 year: 2005 ident: 10.1016/j.envpol.2017.08.114_bib19 article-title: A neural network forecast for daily average PM 10 concentrations in Belgium publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2005.01.050 – volume: 219 start-page: 8923 year: 2013 ident: 10.1016/j.envpol.2017.08.114_bib48 article-title: A SVM-based regression model to study the air quality at local scale in Oviedo urban area (Northern Spain): a case study publication-title: Appl. Math. Comput. – start-page: 1436 year: 2013 ident: 10.1016/j.envpol.2017.08.114_bib47 article-title: U-Air: when urban air quality inference meets big data – volume: 128 start-page: 1146 year: 2002 ident: 10.1016/j.envpol.2017.08.114_bib29 article-title: Prediction of pollutant levels in causeway bay area of Hong Kong using an improved neural network model publication-title: J. Environ. Eng.-ASCE doi: 10.1061/(ASCE)0733-9372(2002)128:12(1146) – year: 2000 ident: 10.1016/j.envpol.2017.08.114_bib30 – volume: 44 start-page: 523 year: 2010 ident: 10.1016/j.envpol.2017.08.114_bib23 article-title: Improving ozone modeling in complex terrain at a fine grid resolution: Part I–examination of analysis nudging and all PBL schemes associated with LSMs in meteorological model publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2009.10.045 – volume: 53 start-page: 265 year: 2013 ident: 10.1016/j.envpol.2017.08.114_bib16 article-title: Numerical model-based relationship between meteorological conditions and air quality and its implication for urban air quality management publication-title: Int. J. Environ. Pollut. doi: 10.1504/IJEP.2013.059921 – volume: 42 start-page: 8331 year: 2008 ident: 10.1016/j.envpol.2017.08.114_bib11 article-title: A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2008.07.020 – volume: 45 start-page: 3663 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib27 article-title: A study on the potential applications of satellite data in air quality monitoring and forecasting publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2011.04.032 – volume: 61 start-page: 69 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib6 article-title: Spatial heterogeneity of PM10 and O3 in Săo Paulo, Brazil, and implications for human health studies publication-title: J. Air & Waste Manag. Assoc. doi: 10.3155/1047-3289.61.1.69 – start-page: 961 year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib1 article-title: Social lstm: human trajectory prediction in crowded spaces – volume: 58 start-page: 240 year: 1895 ident: 10.1016/j.envpol.2017.08.114_bib36 article-title: Note on regression and inheritance in the case of two parents publication-title: Proc. R. Soc. Lond. doi: 10.1098/rspl.1895.0041 – volume: 443 start-page: 511 year: 2013 ident: 10.1016/j.envpol.2017.08.114_bib2 article-title: PM 10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2012.10.110 – volume: 42 start-page: 4567 year: 2008 ident: 10.1016/j.envpol.2017.08.114_bib41 article-title: A model inter-comparison study focussing on episodes with elevated PM10 concentrations publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2008.01.068 – volume: 12 start-page: 5 year: 2004 ident: 10.1016/j.envpol.2017.08.114_bib15 article-title: Progress of weather research and forecast (WRF) model and application in the United States publication-title: Meteorol. Mon. – year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib40 – volume: 130 start-page: 391 year: 2001 ident: 10.1016/j.envpol.2017.08.114_bib43 article-title: A nested air quality prediction modeling system for urban and regional scales: application for high-ozone episode in Taiwan publication-title: Water, Air, Soil Pollut. doi: 10.1023/A:1013833217916 – year: 2010 ident: 10.1016/j.envpol.2017.08.114_bib13 article-title: Wind power prediction using mixture density recurrent neural networks – volume: 45 start-page: 2769 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib39 article-title: Forecasting urban PM10 and PM2. 5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF–Chem CO tracer model publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2011.02.001 – volume: 8 start-page: 523 year: 2008 ident: 10.1016/j.envpol.2017.08.114_bib4 article-title: Towards improving the simulation of meteorological fields in urban areas through updated/advanced surface fluxes description publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-8-523-2008 – volume: 207 start-page: 399 year: 2004 ident: 10.1016/j.envpol.2017.08.114_bib22 article-title: Health effects of particles in ambient air publication-title: Int. J. Hyg. Environ. Health doi: 10.1078/1438-4639-00306 – volume: 16 start-page: 503 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib37 article-title: A wavelet-based neural network model to predict ambient air pollutants' concentration publication-title: Environ. Model. Assess. doi: 10.1007/s10666-011-9270-6 – volume: 9 start-page: 1735 year: 1997 ident: 10.1016/j.envpol.2017.08.114_bib18 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – volume: 16 start-page: 1 year: 2015 ident: 10.1016/j.envpol.2017.08.114_bib49 article-title: Traffic flow prediction with big data: a deep learning approach publication-title: IEEE Trans. Intell. Transport. Syst. – volume: 41 start-page: 173 year: 2007 ident: 10.1016/j.envpol.2017.08.114_bib42 article-title: Evaluation and intercomparison of Ozone and PM10 simulations by several chemistry transport models over four European cities within the CityDelta project publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2006.07.039 – volume: 287 start-page: 1132 year: 2002 ident: 10.1016/j.envpol.2017.08.114_bib20 article-title: Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution publication-title: Jama J. Am. Med. Assoc. doi: 10.1001/jama.287.9.1132 – volume: 140 start-page: 5 year: 2009 ident: 10.1016/j.envpol.2017.08.114_bib25 article-title: Extended follow-up and spatial analysis of the American Cancer Society study linking particulate air pollution and mortality publication-title: Res. Rep. Health Eff. Inst. – volume: 37 start-page: 7986 year: 2010 ident: 10.1016/j.envpol.2017.08.114_bib26 article-title: Forecasting air pollutant indicator levels with geographic models 3days in advance using neural networks publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2010.05.093 – volume: 329 start-page: 1753 year: 1993 ident: 10.1016/j.envpol.2017.08.114_bib12 article-title: An association between air pollution and mortality in six U.S. cities publication-title: N. Engl. J. Med. doi: 10.1056/NEJM199312093292401 – volume: 16 start-page: 166 year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib32 article-title: Neuro-fuzzy approach to forecast NO2 pollutants addressed to air quality dispersion model over Delhi, India publication-title: Aerosol Air Qual. Res. doi: 10.4209/aaqr.2015.04.0249 – volume: 45 start-page: 1979 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib14 article-title: Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2011.01.022 – volume: 38 start-page: 3971 year: 2004 ident: 10.1016/j.envpol.2017.08.114_bib33 article-title: Acute effects of particulate matter on respiratory diseases, symptoms and functions:: epidemiological results of the Austrian Project on Health Effects of Particulate Matter (AUPHEP) publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2003.12.044 – volume: 2 start-page: 490 year: 1990 ident: 10.1016/j.envpol.2017.08.114_bib44 article-title: An efficient gradient-based algorithm for on-line training of recurrent network trajectories publication-title: Neural Comput. doi: 10.1162/neco.1990.2.4.490 – volume: 22 start-page: 199 year: 1976 ident: 10.1016/j.envpol.2017.08.114_bib5 article-title: Time series analysis: forecasting and control publication-title: J. Operational Res. Soc. – year: 1987 ident: 10.1016/j.envpol.2017.08.114_bib38 – volume: 39 start-page: 6444 year: 2005 ident: 10.1016/j.envpol.2017.08.114_bib45 article-title: A review of intraurban variations in particulate air pollution: implications for epidemiological research publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2005.07.030 – volume: 396 start-page: 128 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib46 article-title: A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2010.11.002 – volume: 45 start-page: 1116 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib21 article-title: Source contributions to carbonaceous aerosol concentrations in Korea publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2010.11.031 – start-page: 562 year: 1993 ident: 10.1016/j.envpol.2017.08.114_bib7 article-title: Overview of the enhanced geocoded emissions modeling and projection (Enhanced GEMAP) system – volume: 27 start-page: 1553 year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib34 article-title: Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5 publication-title: Neural Comput. Appl. doi: 10.1007/s00521-015-1955-3 – volume: 74 start-page: 346 year: 2013 ident: 10.1016/j.envpol.2017.08.114_bib9 article-title: Ensemble and enhanced PM10 concentration forecast model based on stepwise regression and wavelet analysis publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2013.04.002 – volume: 23 start-page: 22408 year: 2016 ident: 10.1016/j.envpol.2017.08.114_bib28 article-title: Deep learning architecture for air quality predictions publication-title: Environ. Sci. Pollut. Res. doi: 10.1007/s11356-016-7812-9 – volume: 54 start-page: 187 year: 2015 ident: 10.1016/j.envpol.2017.08.114_bib31 article-title: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data publication-title: Transp. Res. Part C Emerg. Technol. doi: 10.1016/j.trc.2015.03.014 – volume: 18 start-page: 316 year: 2011 ident: 10.1016/j.envpol.2017.08.114_bib35 article-title: Forecasting hourly PM10 concentration in Cyprus through artificial neural networks and multiple regression models: implications to local environmental management publication-title: Environ. Sci. Pollut. Res. doi: 10.1007/s11356-010-0375-2 – volume: 92 start-page: 182 year: 2014 ident: 10.1016/j.envpol.2017.08.114_bib8 article-title: Seasonal modeling of PM 2.5 in California's san Joaquin valley publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2014.04.030 – start-page: 584 year: 1996 ident: 10.1016/j.envpol.2017.08.114_bib10 article-title: High-performance algorithms in the sparse matrix operator kernel emissions (SMOKE) modeling system – volume: 35 start-page: 815 year: 2001 ident: 10.1016/j.envpol.2017.08.114_bib24 article-title: Neural networks and periodic components used in air quality forecasting publication-title: Atmos. Environ. doi: 10.1016/S1352-2310(00)00385-X
SSID	ssj0004333
Score	2.6723447
Snippet	Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants....
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	997
SubjectTerms	Air pollutant concentration predictions air pollutants Air Pollutants - analysis air pollution Air Pollution - statistics & numerical data air quality Beijing China Cities data collection Environmental Monitoring - methods Forecasting Long short-term memory neural network (LSTM NN) memory meteorological data model validation Models, Statistical Models, Theoretical monitoring Multiscale prediction neural networks Neural Networks (Computer) Particulate Matter - analysis particulates prediction public health Recurrent neural network Spatiotemporal correlation
Title	Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation
URI	https://dx.doi.org/10.1016/j.envpol.2017.08.114 https://www.ncbi.nlm.nih.gov/pubmed/28898956 https://www.proquest.com/docview/1938601766 https://www.proquest.com/docview/2000563592
Volume	231
WOSCitedRecordID	wos000414881000101&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: 1873-6424 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004333 issn: 0269-7491 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLe6jgMcEGwMysdkJLRLFdTESW1zq6ZOgEKZRIfCKXISd2u1paVNq-3_4Q_l-SNNyqg2DlyiyLJrp-_nZz_7995D6J3w0sRLYaYFLAkcPyPCgWVh5KQpAwhIXzAdeP57SAcDFkX8tNH4VfrCrC5pnrPraz77r6KGMhC2cp39B3GvfxQK4B2EDk8QOzzvJfhQZQ9aXMC22lFqt32luLQ3bRW4EsSRG9q3IU-O5ypJAwwG_l7FPzdMTY2I2Vzd4OhRqkODLzrRdOlitSamV7HCN074K-c55eelezAoY38cPoSaSxABRM8rHW20Tziuyn6Iqa03ndSKj5e6-bcLARrcFtsDDFgUKzKI0bmMEgfMIHOuIP9SZhW1R9waIk-LtlvTvNzQfG-tCOZwYvJe5iv4XsXloypmq-v61QpY3voPvsYnZ2EYD_vR8Gj201G5ydQdvk3UsoN2PRpw1kS7vU_96HPlf0uIduQoB126aGoe4e2Ot22Btpk4eqszfIIeWxsF9wy2nqKGzPfQfi8XxfTqBh9hzRrW1zF76FEtoOUeOtgQPbYLx2IfFQqVuEIlNqjEBpXYohIDKjGgEq9RiTdQiWuo_IANJnENkxgwiStMPkNnJ_3h8UfHJvxwUr_rFo6giU9HnY5MwYonVKp8ad3Mz3wwazhP0kASQVw3yRLuZQTeSCdT1_YBDzLhcUEOUDOf5vIFwoR1JB0lIx5Izw-SlFNPgOIRmRekXZG6LURKGcSpjYavkrJcxiXtcRIbycVKcnGHKf_9FnLWrWYmGswd9Wkp3tjuaM1ONQZ43tHybYmGGBS-usUTuZwuFzFYXKzbUXFdt9dR_ncBmBLca6HnBkrr8XpMZYwNui_v0cMr9LCasa9Rs5gv5Rv0IF0V48X8EO3QiB3ayfAbrr3oOQ
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=Long+short-term+memory+neural+network+for+air+pollutant+concentration+predictions%3A+Method+development+and+evaluation&rft.jtitle=Environmental+pollution+%281987%29&rft.au=Li%2C+Xiang&rft.au=Peng%2C+Ling&rft.au=Yao%2C+Xiaojing&rft.au=Cui%2C+Shaolong&rft.date=2017-12-01&rft.issn=1873-6424&rft.eissn=1873-6424&rft.volume=231&rft.issue=Pt+1&rft.spage=997&rft_id=info:doi/10.1016%2Fj.envpol.2017.08.114&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0269-7491&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0269-7491&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0269-7491&client=summon