Fusing stacked autoencoder and long short-term memory for regional multistep-ahead flood inundation forecasts
•Use Stacked Autoencoder (SAE) to reduce the dimension of regional inundation data.•Use PCA to adjust the network structure and initialize network weights of the SAE.•SAE-RNN nowcasts multistep-ahead regional inundation maps of typhoon events.•Offer 2D-visualization of spatio-temporal distribution o...
Gespeichert in:
| Veröffentlicht in: | Journal of hydrology (Amsterdam) Jg. 598; S. 126371 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier B.V
01.07.2021
|
| Schlagworte: | |
| ISSN: | 0022-1694, 1879-2707 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | •Use Stacked Autoencoder (SAE) to reduce the dimension of regional inundation data.•Use PCA to adjust the network structure and initialize network weights of the SAE.•SAE-RNN nowcasts multistep-ahead regional inundation maps of typhoon events.•Offer 2D-visualization of spatio-temporal distribution of regional inundation depths.
Reliable and accurate regional multistep-ahead flood forecasts during extreme events are crucial and beneficial to flood disaster management and preparedness. Hydrologic uncertainty associated with the nonlinear dependence structure of flood inundation dynamics makes flood inundation forecasting fundamentally challenging. This study proposes a novel machine learning-based model (SAE-RNN) that hybrids the stacked autoencoder (SAE) with a recurrent neural network (RNN) for providing accurate and timely information to support emergency management in areas impacted by flood hazards. The proposed SAE-RNN model uses SAE to compress (encode) the high-dimensional flood inundation depths in a wide region into a low-dimensional latent space representation (flood features), uses RNN to forecast multistep-ahead flood features based on regional rainfall patterns, and finally uses SAE to reconstruct (decode) the multistep-ahead forecasts of flood features into regional flood inundation depths. A large number of hourly datasets of flood inundation depths collected in Yilan County of Taiwan formed the case study, where each dataset contains 169,797 grids of inundation depth. The datasets were divided into three independent datasets for use in training, validating and testing stages. The models’ results showed that RMSE values were very small (<0.09 m) and R2 values were high (>0.95) in all the cases (1- up to 3-hour-ahead forecasts in three stages). We conclude that the reason why the proposed SAE-RNN models are capable of attaining favorable regional multistep-ahead flood inundation forecasts could be owing to two core strategies: the effective continual extraction of the nonlinear dependence structure from flood inundation dynamics for lessening hydrologic uncertainty by virtue of SAE; and the nonlinear conversion of rainfall sequences into future flood features by virtue of RNN. |
|---|---|
| AbstractList | Reliable and accurate regional multistep-ahead flood forecasts during extreme events are crucial and beneficial to flood disaster management and preparedness. Hydrologic uncertainty associated with the nonlinear dependence structure of flood inundation dynamics makes flood inundation forecasting fundamentally challenging. This study proposes a novel machine learning-based model (SAE-RNN) that hybrids the stacked autoencoder (SAE) with a recurrent neural network (RNN) for providing accurate and timely information to support emergency management in areas impacted by flood hazards. The proposed SAE-RNN model uses SAE to compress (encode) the high-dimensional flood inundation depths in a wide region into a low-dimensional latent space representation (flood features), uses RNN to forecast multistep-ahead flood features based on regional rainfall patterns, and finally uses SAE to reconstruct (decode) the multistep-ahead forecasts of flood features into regional flood inundation depths. A large number of hourly datasets of flood inundation depths collected in Yilan County of Taiwan formed the case study, where each dataset contains 169,797 grids of inundation depth. The datasets were divided into three independent datasets for use in training, validating and testing stages. The models’ results showed that RMSE values were very small (<0.09 m) and R² values were high (>0.95) in all the cases (1- up to 3-hour-ahead forecasts in three stages). We conclude that the reason why the proposed SAE-RNN models are capable of attaining favorable regional multistep-ahead flood inundation forecasts could be owing to two core strategies: the effective continual extraction of the nonlinear dependence structure from flood inundation dynamics for lessening hydrologic uncertainty by virtue of SAE; and the nonlinear conversion of rainfall sequences into future flood features by virtue of RNN. •Use Stacked Autoencoder (SAE) to reduce the dimension of regional inundation data.•Use PCA to adjust the network structure and initialize network weights of the SAE.•SAE-RNN nowcasts multistep-ahead regional inundation maps of typhoon events.•Offer 2D-visualization of spatio-temporal distribution of regional inundation depths. Reliable and accurate regional multistep-ahead flood forecasts during extreme events are crucial and beneficial to flood disaster management and preparedness. Hydrologic uncertainty associated with the nonlinear dependence structure of flood inundation dynamics makes flood inundation forecasting fundamentally challenging. This study proposes a novel machine learning-based model (SAE-RNN) that hybrids the stacked autoencoder (SAE) with a recurrent neural network (RNN) for providing accurate and timely information to support emergency management in areas impacted by flood hazards. The proposed SAE-RNN model uses SAE to compress (encode) the high-dimensional flood inundation depths in a wide region into a low-dimensional latent space representation (flood features), uses RNN to forecast multistep-ahead flood features based on regional rainfall patterns, and finally uses SAE to reconstruct (decode) the multistep-ahead forecasts of flood features into regional flood inundation depths. A large number of hourly datasets of flood inundation depths collected in Yilan County of Taiwan formed the case study, where each dataset contains 169,797 grids of inundation depth. The datasets were divided into three independent datasets for use in training, validating and testing stages. The models’ results showed that RMSE values were very small (<0.09 m) and R2 values were high (>0.95) in all the cases (1- up to 3-hour-ahead forecasts in three stages). We conclude that the reason why the proposed SAE-RNN models are capable of attaining favorable regional multistep-ahead flood inundation forecasts could be owing to two core strategies: the effective continual extraction of the nonlinear dependence structure from flood inundation dynamics for lessening hydrologic uncertainty by virtue of SAE; and the nonlinear conversion of rainfall sequences into future flood features by virtue of RNN. |
| ArticleNumber | 126371 |
| Author | Kao, I-Feng Lee, Meng-Hsin Chang, Fi-John Liou, Jia-Yi |
| Author_xml | – sequence: 1 givenname: I-Feng surname: Kao fullname: Kao, I-Feng – sequence: 2 givenname: Jia-Yi surname: Liou fullname: Liou, Jia-Yi – sequence: 3 givenname: Meng-Hsin surname: Lee fullname: Lee, Meng-Hsin – sequence: 4 givenname: Fi-John surname: Chang fullname: Chang, Fi-John email: changfj@ntu.edu.tw |
| BookMark | eNqFkE9rGzEQxUVwIHaajxDQsZd1JO0_LT2UYpqmEMglPYuxNBvL1UqupC3421eOc-rFcxmGee_B-63IwgePhNxztuaMdw_79X53NDG4tWCCr7no6p5fkSWX_VCJnvULsmRMiIp3Q3NDVintWZm6bpZkepyT9W80ZdC_0VCYc0Cvg8FIwRvqwum5CzFXGeNEJ5xCPNIxRBrxzQYPjk6zyzZlPFSwQzB0dCEYav3sDeQiOalRQ8rpE7kewSW8-9i35Nfj99fNU_X88uPn5ttzpetG5EpqKUsLLbFlnGGjZYu63RrZmI4NWxhNudpB8rEfa8m6LUJds05Dr7ttC1Dfks_n3EMMf2ZMWU02aXQOPIY5KdG2fBCNlF2RtmepjiGliKM6RDtBPCrO1Amv2qsPvOqEV53xFt-X_3za5ve6OYJ1F91fz24sFP5ajCppW7ijsQVVVibYCwn_AGOVnwg |
| CitedBy_id | crossref_primary_10_1016_j_jhydrol_2024_131737 crossref_primary_10_1061_JHYEFF_HEENG_6262 crossref_primary_10_1016_j_jhydrol_2022_128122 crossref_primary_10_1017_eds_2024_14 crossref_primary_10_1029_2025WR040433 crossref_primary_10_1111_mice_13484 crossref_primary_10_1007_s11069_025_07494_8 crossref_primary_10_1016_j_jhydrol_2024_131819 crossref_primary_10_1016_j_jhydrol_2025_133954 crossref_primary_10_1016_j_envsoft_2025_106599 crossref_primary_10_1016_j_jhydrol_2022_128086 crossref_primary_10_1017_eds_2024_19 crossref_primary_10_1029_2022RG000788 crossref_primary_10_1016_j_jhydrol_2024_131250 crossref_primary_10_1016_j_jhydrol_2024_131494 crossref_primary_10_3390_su162410958 crossref_primary_10_3390_app122412567 crossref_primary_10_1016_j_jhydrol_2022_127515 crossref_primary_10_3390_w16131771 crossref_primary_10_3390_w14162492 crossref_primary_10_3390_w16101407 crossref_primary_10_1016_j_jhydrol_2023_130117 crossref_primary_10_1016_j_jhydrol_2023_129688 crossref_primary_10_3390_w14244029 crossref_primary_10_1016_j_jhydrol_2024_130937 crossref_primary_10_1016_j_jhydrol_2023_129684 crossref_primary_10_1016_j_jhydrol_2023_129521 crossref_primary_10_3390_w16091286 crossref_primary_10_1007_s43832_024_00173_y crossref_primary_10_1016_j_jhydrol_2023_129163 crossref_primary_10_3390_hydrology11090152 crossref_primary_10_1016_j_jhydrol_2025_132737 crossref_primary_10_1016_j_ijdrr_2022_103276 crossref_primary_10_1016_j_jhydrol_2023_129480 crossref_primary_10_1109_JSTARS_2023_3349162 crossref_primary_10_1016_j_jhydrol_2021_126975 crossref_primary_10_1016_j_jhydrol_2022_128025 crossref_primary_10_1016_j_jhydrol_2022_128388 crossref_primary_10_3390_w15223928 crossref_primary_10_1007_s11069_024_06846_0 crossref_primary_10_1016_j_jhydrol_2022_128265 crossref_primary_10_3390_rs17172943 crossref_primary_10_1007_s11227_022_04827_3 crossref_primary_10_1016_j_jhydrol_2021_127255 crossref_primary_10_3390_rs16203889 crossref_primary_10_1029_2022WR033214 crossref_primary_10_1016_j_eswa_2022_118481 crossref_primary_10_1016_j_jhydrol_2024_130862 crossref_primary_10_1016_j_jhydrol_2024_131996 crossref_primary_10_1038_s44304_025_00122_2 crossref_primary_10_1007_s11269_024_03833_9 crossref_primary_10_1016_j_jhydrol_2024_131275 crossref_primary_10_1016_j_jclepro_2023_139825 crossref_primary_10_3390_smartcities8030091 crossref_primary_10_3390_hydrology9110202 crossref_primary_10_1007_s11269_023_03725_4 crossref_primary_10_1016_j_jhydrol_2023_129956 crossref_primary_10_1016_j_watres_2024_122162 crossref_primary_10_1016_j_ijggc_2024_104124 crossref_primary_10_1016_j_scitotenv_2024_172246 crossref_primary_10_1016_j_jhydrol_2022_128431 crossref_primary_10_1016_j_jhydrol_2022_127781 crossref_primary_10_1016_j_jenvman_2023_119789 crossref_primary_10_1007_s11269_024_03937_2 crossref_primary_10_1016_j_jhydrol_2024_130993 crossref_primary_10_1016_j_jenvman_2025_124835 crossref_primary_10_2166_hydro_2024_036 crossref_primary_10_1109_TSG_2024_3481894 crossref_primary_10_1007_s12524_025_02277_x crossref_primary_10_1016_j_asoc_2024_112352 crossref_primary_10_1016_j_jhydrol_2024_131082 crossref_primary_10_3390_w15101846 crossref_primary_10_1007_s11069_022_05766_1 crossref_primary_10_1016_j_jhydrol_2021_126831 crossref_primary_10_2166_hydro_2023_001 crossref_primary_10_5194_hess_26_4345_2022 crossref_primary_10_3390_w14142211 crossref_primary_10_2166_hydro_2023_006 |
| Cites_doi | 10.1016/j.jhydrol.2016.06.026 10.1002/met.1533 10.1109/ACCESS.2019.2963819 10.1016/j.jcp.2018.04.018 10.1016/j.neucom.2015.08.104 10.1016/j.jhydrol.2019.06.036 10.1007/s11269-019-02399-1 10.1016/j.jhydrol.2015.07.057 10.1016/j.jhydrol.2015.08.008 10.1016/j.jhydrol.2018.04.065 10.3390/w11010009 10.1016/j.jhydrol.2014.06.013 10.1016/j.jhydrol.2015.11.050 10.1016/j.jhydrol.2019.02.051 10.1016/j.isprsjprs.2017.11.009 10.1016/j.neucom.2020.04.110 10.1002/hyp.9559 10.3390/w12020578 10.1109/ACCESS.2018.2818108 10.18653/v1/D16-1137 10.1016/j.jhydrol.2016.01.056 10.1029/2019WR025326 10.1515/jwld-2016-0003 10.2166/wst.2020.369 10.5194/hess-2019-368 10.1016/j.jhydrol.2019.124296 10.5194/hess-22-6005-2018 10.3390/w11071387 10.3390/w11091848 10.1016/j.jhydrol.2013.05.038 10.1016/j.jhydrol.2019.05.051 10.1007/s11269-017-1796-1 10.3390/w10091283 10.1007/s11269-016-1474-8 10.1016/j.jhydrol.2018.01.015 10.1016/j.ins.2018.12.027 10.1016/j.jpdc.2017.06.007 10.1007/s11263-017-1033-7 10.1016/j.jhydrol.2014.03.057 10.1190/geo2018-0668.1 10.1016/S1005-8885(17)60243-7 10.1016/j.jhydrol.2016.11.033 10.1162/neco.1997.9.8.1735 10.1038/s41598-018-30024-5 10.1038/s41467-020-15734-7 10.2463/mrms.mp.2019-0018 10.1016/j.neucom.2016.12.038 10.1016/j.jclepro.2018.10.243 10.3390/en12122445 10.1007/s11600-019-00330-1 10.1109/TASE.2019.2895801 10.1016/j.neucom.2015.11.044 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier B.V. |
| Copyright_xml | – notice: 2021 Elsevier B.V. |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.jhydrol.2021.126371 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography |
| EISSN | 1879-2707 |
| ExternalDocumentID | 10_1016_j_jhydrol_2021_126371 S0022169421004182 |
| GeographicLocations | Taiwan |
| GeographicLocations_xml | – name: Taiwan |
| GroupedDBID | --K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 29K 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AABVA AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALCJ AALRI AAOAW AAQFI AAQXK AATLK AAXUO ABEFU ABFNM ABGRD ABJNI ABMAC ABQEM ABQYD ABTAH ABXDB ABYKQ ACDAQ ACGFS ACIUM ACLVX ACNCT ACRLP ACSBN ADBBV ADEZE ADMUD ADQTV AEBSH AEKER AENEX AEQOU AFFNX AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHHHB AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG ATOGT AVWKF AXJTR AZFZN BKOJK BLXMC CBWCG CS3 D-I DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FA8 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HLV HMA HVGLF HZ~ H~9 IHE IMUCA J1W K-O KOM LW9 LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SAB SCC SDF SDG SDP SEP SES SEW SPC SPCBC SPD SSA SSE SSZ T5K TN5 UQL VOH WUQ Y6R ZCA ZMT ZY4 ~02 ~G- ~KM 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABUFD ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c342t-8c88126c8e5010e4c85ec5bd84d609bafdc5b5981f7f3806bea3306ca7c6b5aa3 |
| ISICitedReferencesCount | 85 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000661813200131&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0022-1694 |
| IngestDate | Sun Nov 09 09:29:45 EST 2025 Tue Nov 18 20:43:13 EST 2025 Sat Nov 29 06:57:39 EST 2025 Fri Feb 23 02:42:28 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Stacked autoencoder (SAE) Regional flood inundation Multistep-ahead forecast Long short-term memory (LSTM) Recurrent neural network (RNN) |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c342t-8c88126c8e5010e4c85ec5bd84d609bafdc5b5981f7f3806bea3306ca7c6b5aa3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 2551924886 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_2551924886 crossref_primary_10_1016_j_jhydrol_2021_126371 crossref_citationtrail_10_1016_j_jhydrol_2021_126371 elsevier_sciencedirect_doi_10_1016_j_jhydrol_2021_126371 |
| PublicationCentury | 2000 |
| PublicationDate | July 2021 2021-07-00 20210701 |
| PublicationDateYYYYMMDD | 2021-07-01 |
| PublicationDate_xml | – month: 07 year: 2021 text: July 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of hydrology (Amsterdam) |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Xiang, Z., Yan, J., Demir, I., 2020. A rainfall‐runoff model with LSTM‐based sequen‐to‐sequence learning. Water resources research, 56(1), e2019WR025326. Tong, Li, Lang, Kong, Niu, Rodrigues (b0250) 2018; 117 Liu, Xu, Yang (b0140) 2017 Kidoh, Shinoda, Kitajima, Isogawa, Nambu, Uetani, Yamashita (b0105) 2020; 19 Taormina, Chau, Sivakumar (b0245) 2015; 529 Sit, Demiray, Xiang, Ewing, Sermet, Demir (b0230) 2020; 82 Zabalza, Ren, Zheng, Zhao, Qing, Yang, Qing, Yang, Du, Marshall (b0295) 2016; 185 Nanda, Sahoo, Chatterjee (b0170) 2019; 575 Jiao, Huang, Ma, Han, Tian (b0095) 2018; 6 Liu, Wang, Liu, Zeng, Liu, Alsaadi (b0145) 2017; 234 Zaytar, El Amrani (b0300) 2016; 143 Marmanis, Schindler, Wegner, Galliani, Datcu, Stilla (b0165) 2018; 135 Tsai, Abrahart, Mount, Chang (b0255) 2014; 28 Le, Ho, Lee, Jung (b0125) 2019; 11 Li, Bai, Zeng (b0135) 2016; 30 Li, Du, Volkow, Pan (b0130) 2020; 13 Ni, Wang, Singh, Wu, Wang, Tao, Zhang (b0175) 2020; 583 Xie, Zhang, Hou, Xie, Lv, Liu (b0285) 2019; 123915 Noori, Kalin (b0180) 2016; 533 Chang, Tsai (b0035) 2016; 535 Zhang, Zhu, Zhang, Ye, Yang (b0310) 2018; 561 Xiang, Z., Yan, J., Demir, I., 2020. A rainfall‐runoff model with LSTM‐based sequence‐to‐sequence learning. Water Resources Research 56(1), e2019WR025326. Chiu, Sainath, Wu, Prabhavalkar, Nguyen, Chen, Kannan, Weiss, Rao, Gonina, Jaitly, Li, Chorowski, Bacchiani (b0055) 2018 Shoaib, Shamseldin, Khan, Khan, Khan, Sultan, Melville (b0225) 2018; 32 Sahoo, Jha, Singh, Kumar (b0210) 2019; 67 Badrzadeh, Sarukkalige, Jayawardena (b0010) 2015; 529 Bai, Bezak, Sapač, Klun, Zhang (b0015) 2019; 33 Luo, Mu, Xue, Ngo-Duc, Dang-Dinh, Takara, Nover, Schladow (b0160) 2018; 8 Chang, L. C., Chang, F. J., Yang, S. N., Kao, I., Ku, Y. Y., Kuo, C. L., Amin, I., 2019. Building an Intelligent Hydroinformatics Integration Platform for Regional Flood Inundation Warning Systems. Water 2019, 11(1), 9. Puttinaovarat, Horkaew (b0200) 2020; 8 Chang, Amin, Yang, Chang (b0040) 2018; 10 Hochreiter, Schmidhuber (b0080) 1997; 9 Chen, Chang, Chang (b0050) 2013; 497 Jeong, Park (b0090) 2019; 572 Nourani, Baghanam, Adamowski, Kisi (b0190) 2014; 514 Valipour (b0260) 2016; 23 Wiseman, S., Rush, A. M., 2016. Sequence-to-sequence learning as beam-search optimization. arXiv 1606.02960v2. Kratzert, Klotz, Brenner, Schulz, Herrnegger (b0110) 2018; 22 Abbasi, Farokhnia, Bahreinimotlagh, Roozbahani (b0005) 2020; 125717 Tan, Lei, Wang, Wang, Wen, Ji, Kang (b0240) 2018; 567 Chang (bib336) 2020; 11 Ding, Zhu, Feng, Zhang, Cheng (b0060) 2020; 403 Liu, Zheng, Chen (b0150) 2019; 12 Zhou, Chang, Chang, Kao, Wang (b0320) 2019; 209 Zhang, Zhu, Zhang, Ye, Yang (b0305) 2018; 561 Du, Li, Horng (b0065) 2018 Sezen, Bezak, Bai, Šraj (b0215) 2019; 576 Bi, Yuan, Zhou (b0025) 2019; 16 Orland, Roering, Thomas, Mirus (b0195) 2019; e2020GL088731 Chang, Chen, Lu, Huang, Chang (b0030) 2014; 517 Shafaei, Adamowski, Fakheri-Fard, Dinpashoh, Adamowski (b0220) 2016; 28 Zhu, Xu, Yang, Hauptmann (b0330) 2017; 124 Zhou, Guo, Xu, Chang, Yin (b0325) 2020; 12 Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., Nearing, G., 2019. Benchmarking a catchment-aware Long Short-Term Memory Network (LSTM for large-scale hydrological modeling. arXiv preprint arXiv 1907.08456. Kratzert, Klotz, Brenner, Schulz, Herrnegger (b0115) 2018; 22 Zhu, Zabaras (b0335) 2018; 366 Wang, Yao, Zhao (b0265) 2016; 184 Kao, Zhou, Chang, Chang (b0100) 2020; 124631 Nourani (b0185) 2017; 544 Yu, Ma, Wang (b0290) 2019; 84 Bi, Yuan, Zhang, Zhang (b0020) 2019; 481 Humphrey, Gibbs, Dandy, Maier (b0085) 2016; 540 Fengming, Shufang, Zhimin, Bo, Shiming, Mingming (b0070) 2017; 24 Ren, Ren, Zhang, Zheng (b0205) 2019; 11 Chen (10.1016/j.jhydrol.2021.126371_b0050) 2013; 497 Du (10.1016/j.jhydrol.2021.126371_b0065) 2018 Ren (10.1016/j.jhydrol.2021.126371_b0205) 2019; 11 10.1016/j.jhydrol.2021.126371_b0275 Li (10.1016/j.jhydrol.2021.126371_b0130) 2020; 13 Zhou (10.1016/j.jhydrol.2021.126371_b0325) 2020; 12 Chiu (10.1016/j.jhydrol.2021.126371_b0055) 2018 Zaytar (10.1016/j.jhydrol.2021.126371_b0300) 2016; 143 Bi (10.1016/j.jhydrol.2021.126371_b0025) 2019; 16 Yu (10.1016/j.jhydrol.2021.126371_b0290) 2019; 84 Orland (10.1016/j.jhydrol.2021.126371_b0195) 2019; e2020GL088731 Liu (10.1016/j.jhydrol.2021.126371_b0140) 2017 10.1016/j.jhydrol.2021.126371_b0280 Jeong (10.1016/j.jhydrol.2021.126371_b0090) 2019; 572 Nanda (10.1016/j.jhydrol.2021.126371_b0170) 2019; 575 Bai (10.1016/j.jhydrol.2021.126371_b0015) 2019; 33 Zhu (10.1016/j.jhydrol.2021.126371_b0335) 2018; 366 Zabalza (10.1016/j.jhydrol.2021.126371_b0295) 2016; 185 Sahoo (10.1016/j.jhydrol.2021.126371_b0210) 2019; 67 Bi (10.1016/j.jhydrol.2021.126371_b0020) 2019; 481 Xie (10.1016/j.jhydrol.2021.126371_b0285) 2019; 123915 10.1016/j.jhydrol.2021.126371_b0270 Chang (10.1016/j.jhydrol.2021.126371_b0035) 2016; 535 Kratzert (10.1016/j.jhydrol.2021.126371_b0110) 2018; 22 Liu (10.1016/j.jhydrol.2021.126371_b0150) 2019; 12 Luo (10.1016/j.jhydrol.2021.126371_b0160) 2018; 8 Kratzert (10.1016/j.jhydrol.2021.126371_b0115) 2018; 22 Sit (10.1016/j.jhydrol.2021.126371_b0230) 2020; 82 Zhang (10.1016/j.jhydrol.2021.126371_b0310) 2018; 561 Tan (10.1016/j.jhydrol.2021.126371_b0240) 2018; 567 Humphrey (10.1016/j.jhydrol.2021.126371_b0085) 2016; 540 Shoaib (10.1016/j.jhydrol.2021.126371_b0225) 2018; 32 Li (10.1016/j.jhydrol.2021.126371_b0135) 2016; 30 Marmanis (10.1016/j.jhydrol.2021.126371_b0165) 2018; 135 Puttinaovarat (10.1016/j.jhydrol.2021.126371_b0200) 2020; 8 Taormina (10.1016/j.jhydrol.2021.126371_b0245) 2015; 529 Zhu (10.1016/j.jhydrol.2021.126371_b0330) 2017; 124 Jiao (10.1016/j.jhydrol.2021.126371_b0095) 2018; 6 Valipour (10.1016/j.jhydrol.2021.126371_b0260) 2016; 23 Nourani (10.1016/j.jhydrol.2021.126371_b0190) 2014; 514 Tsai (10.1016/j.jhydrol.2021.126371_b0255) 2014; 28 Kao (10.1016/j.jhydrol.2021.126371_b0100) 2020; 124631 Chang (10.1016/j.jhydrol.2021.126371_bib336) 2020; 11 Fengming (10.1016/j.jhydrol.2021.126371_b0070) 2017; 24 Hochreiter (10.1016/j.jhydrol.2021.126371_b0080) 1997; 9 10.1016/j.jhydrol.2021.126371_b0120 Wang (10.1016/j.jhydrol.2021.126371_b0265) 2016; 184 10.1016/j.jhydrol.2021.126371_b0045 Tong (10.1016/j.jhydrol.2021.126371_b0250) 2018; 117 Zhang (10.1016/j.jhydrol.2021.126371_b0305) 2018; 561 Zhou (10.1016/j.jhydrol.2021.126371_b0320) 2019; 209 Badrzadeh (10.1016/j.jhydrol.2021.126371_b0010) 2015; 529 Le (10.1016/j.jhydrol.2021.126371_b0125) 2019; 11 Ni (10.1016/j.jhydrol.2021.126371_b0175) 2020; 583 Nourani (10.1016/j.jhydrol.2021.126371_b0185) 2017; 544 Sezen (10.1016/j.jhydrol.2021.126371_b0215) 2019; 576 Noori (10.1016/j.jhydrol.2021.126371_b0180) 2016; 533 Kidoh (10.1016/j.jhydrol.2021.126371_b0105) 2020; 19 Chang (10.1016/j.jhydrol.2021.126371_b0030) 2014; 517 Liu (10.1016/j.jhydrol.2021.126371_b0145) 2017; 234 Ding (10.1016/j.jhydrol.2021.126371_b0060) 2020; 403 Abbasi (10.1016/j.jhydrol.2021.126371_b0005) 2020; 125717 Chang (10.1016/j.jhydrol.2021.126371_b0040) 2018; 10 Shafaei (10.1016/j.jhydrol.2021.126371_b0220) 2016; 28 |
| References_xml | – volume: e2020GL088731 year: 2019 ident: b0195 article-title: Deep Learning as a tool to forecast hydrologic response for landslide-prone hillslopes publication-title: Geophys. Res. Lett. – start-page: 4774 year: 2018 end-page: 4778 ident: b0055 article-title: State-of-the-art speech recognition with sequence-to-sequence models publication-title: In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing – volume: 567 start-page: 767 year: 2018 end-page: 780 ident: b0240 article-title: An adaptive middle and long-term runoff forecast model using EEMD-ANN hybrid approach publication-title: J. Hydrol. – volume: 28 start-page: 27 year: 2016 end-page: 36 ident: b0220 article-title: A wavelet-SARIMA-ANN hybrid model for precipitation forecasting publication-title: J. Water Land Develop. – start-page: 58 year: 2017 end-page: 61 ident: b0140 publication-title: A flood forecasting model based on deep learning algorithm via integrating stacked autoencoders with BP neural network – volume: 24 start-page: 67 year: 2017 end-page: 73 ident: b0070 article-title: Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network publication-title: J. China Univ Posts Telecommun – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b0080 article-title: Long short-term memory publication-title: Neural Comput. – volume: 533 start-page: 141 year: 2016 end-page: 151 ident: b0180 article-title: Coupling SWAT and ANN models for enhanced daily streamflow prediction publication-title: J. Hydrol. – volume: 514 start-page: 358 year: 2014 end-page: 377 ident: b0190 article-title: Applications of hybrid wavelet–artificial intelligence models in hydrology: A review publication-title: J. Hydrol. – volume: 576 start-page: 98 year: 2019 end-page: 110 ident: b0215 article-title: Hydrological modelling of karst catchment using lumped conceptual and data mining models publication-title: J. Hydrol. – volume: 33 start-page: 4783 year: 2019 end-page: 4797 ident: b0015 article-title: Short-Term Streamflow Forecasting Using the Feature-Enhanced Regression Model publication-title: Water Resour. Manage. – volume: 403 start-page: 348 year: 2020 end-page: 359 ident: b0060 article-title: Interpretable spatio-temporal attention LSTM model for flood forecasting publication-title: Neurocomputing – volume: 11 start-page: 1 year: 2020 end-page: 13 ident: bib336 article-title: Self-organizing maps of typhoon tracks allow for flood forecasts up to two days in advance publication-title: Nat. Commun. – volume: 535 start-page: 256 year: 2016 end-page: 269 ident: b0035 article-title: A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques publication-title: J. Hydrol. – volume: 23 start-page: 91 year: 2016 end-page: 100 ident: b0260 article-title: Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms publication-title: Meteorol. Appl. – volume: 544 start-page: 267 year: 2017 end-page: 277 ident: b0185 article-title: An emotional ANN (EANN) approach to modeling rainfall-runoff process publication-title: J. Hydrol. – volume: 481 start-page: 57 year: 2019 end-page: 68 ident: b0020 article-title: SGW-SCN: An integrated machine learning approach for workload forecasting in geo-distributed cloud data centers publication-title: Inf. Sci. – volume: 28 start-page: 1055 year: 2014 end-page: 1070 ident: b0255 article-title: Including spatial distribution in a data-driven rainfall-runoff model to improve reservoir inflow forecasting in Taiwan publication-title: Hydrol. Process. – volume: 22 start-page: 6005 year: 2018 end-page: 6022 ident: b0110 article-title: Rainfall–runoff modelling using long short-term memory (LSTM networks publication-title: Hydrol. Earth Syst. Sci. – volume: 32 start-page: 83 year: 2018 end-page: 103 ident: b0225 article-title: A comparative study of various hybrid wavelet feedforward neural network models for runoff forecasting publication-title: Water Resour. Manage. – reference: Xiang, Z., Yan, J., Demir, I., 2020. A rainfall‐runoff model with LSTM‐based sequen‐to‐sequence learning. Water resources research, 56(1), e2019WR025326. – volume: 540 start-page: 623 year: 2016 end-page: 640 ident: b0085 article-title: A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network publication-title: J. Hydrol. – volume: 67 start-page: 1471 year: 2019 end-page: 1481 ident: b0210 article-title: Long short-term memory (LSTM recurrent neural network for low-flow hydrological time series forecasting publication-title: Acta Geophys. – volume: 125717 year: 2020 ident: b0005 article-title: A hybrid of Random Forest and Deep Auto-Encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction publication-title: J. Hydrol. – reference: Wiseman, S., Rush, A. M., 2016. Sequence-to-sequence learning as beam-search optimization. arXiv 1606.02960v2. – volume: 561 start-page: 918 year: 2018 end-page: 929 ident: b0310 article-title: Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas publication-title: J. Hydrol. – volume: 19 start-page: 195 year: 2020 ident: b0105 article-title: Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers publication-title: Magnetic Resonance Med. Sci. – reference: Xiang, Z., Yan, J., Demir, I., 2020. A rainfall‐runoff model with LSTM‐based sequence‐to‐sequence learning. Water Resources Research 56(1), e2019WR025326. – volume: 184 start-page: 232 year: 2016 end-page: 242 ident: b0265 article-title: Auto-encoder based dimensionality reduction publication-title: Neurocomputing – volume: 22 start-page: 6005 year: 2018 end-page: 6022 ident: b0115 article-title: Rainfall–runoff modelling using long short-term memory (LSTM) networks publication-title: Hydrol. Earth Syst. Sci. – volume: 529 start-page: 1633 year: 2015 end-page: 1643 ident: b0010 article-title: Hourly runoff forecasting for flood risk management: Application of various computational intelligence models publication-title: J. Hydrol. – volume: 561 start-page: 918 year: 2018 end-page: 929 ident: b0305 article-title: Developing a Long Short-Term Memory (LSTM based model for predicting water table depth in agricultural areas publication-title: J. Hydrol. – start-page: 171 year: 2018 end-page: 176 ident: b0065 publication-title: December. Time series forecasting using sequence-to-sequence deep learning framework – volume: 6 start-page: 17851 year: 2018 end-page: 17858 ident: b0095 article-title: A model combining stacked auto encoder and back propagation algorithm for short-term wind power forecasting publication-title: IEEE Access – volume: 12 start-page: 2445 year: 2019 ident: b0150 article-title: Deep learning with stacked denoising auto-encoder for short-term electric load forecasting publication-title: Energies – volume: 135 start-page: 158 year: 2018 end-page: 172 ident: b0165 article-title: Classification with an edge: improving semantic image segmentation with boundary detection publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 124 start-page: 409 year: 2017 end-page: 421 ident: b0330 article-title: Uncovering the temporal context for video question answering publication-title: Int. J. Comput. Vision – volume: 497 start-page: 71 year: 2013 end-page: 79 ident: b0050 article-title: Reinforced recurrent neural networks for multi-step-ahead flood forecasts publication-title: J. Hydrol. – volume: 209 start-page: 134 year: 2019 end-page: 145 ident: b0320 article-title: Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts publication-title: J. Cleaner Prod. – reference: Chang, L. C., Chang, F. J., Yang, S. N., Kao, I., Ku, Y. Y., Kuo, C. L., Amin, I., 2019. Building an Intelligent Hydroinformatics Integration Platform for Regional Flood Inundation Warning Systems. Water 2019, 11(1), 9. – volume: 123915 year: 2019 ident: b0285 article-title: Hybrid Forecasting Model for Non-stationary Daily Runoff Series: A Case Study in the Han River Basin, China publication-title: J. Hydrol. – volume: 11 start-page: 1848 year: 2019 ident: b0205 article-title: A novel hybrid extreme learning machine approach improved by K nearest neighbor method and fireworks algorithm for flood forecasting in medium and small watershed of loess region publication-title: Water – volume: 124631 year: 2020 ident: b0100 article-title: Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting publication-title: J. Hydrol. – volume: 366 start-page: 415 year: 2018 end-page: 447 ident: b0335 article-title: Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification publication-title: J. Comput. Phys. – volume: 575 start-page: 890 year: 2019 end-page: 910 ident: b0170 article-title: Enhancing real-time streamflow forecasts with wavelet-neural network based error-updating schemes and ECMWF meteorological predictions in Variable Infiltration Capacity model publication-title: J. Hydrol. – volume: 16 start-page: 1763 year: 2019 end-page: 1773 ident: b0025 article-title: Temporal prediction of multiapplication consolidated workloads in distributed clouds publication-title: IEEE Trans. Autom. Sci. Eng. – volume: 117 start-page: 267 year: 2018 end-page: 273 ident: b0250 article-title: An efficient deep model for day-ahead electricity load forecasting with stacked denoising auto-encoders publication-title: J. Parallel Distrib. Comput. – volume: 84 start-page: V333 year: 2019 end-page: V350 ident: b0290 article-title: Deep learning for denoising publication-title: Geophysics – volume: 82 start-page: 2635 year: 2020 end-page: 2670 ident: b0230 article-title: A comprehensive review of deep learning applications in hydrology and water resources publication-title: Water Sci. Technol. – volume: 30 start-page: 5145 year: 2016 end-page: 5161 ident: b0135 article-title: Deep feature learning architectures for daily reservoir inflow forecasting publication-title: Water Resour. Manage. – volume: 234 start-page: 11 year: 2017 end-page: 26 ident: b0145 article-title: A survey of deep neural network architectures and their applications publication-title: Neurocomputing – volume: 572 start-page: 261 year: 2019 end-page: 273 ident: b0090 article-title: Comparative applications of data-driven models representing water table fluctuations publication-title: J. Hydrol. – volume: 583 year: 2020 ident: b0175 article-title: Streamflow and rainfall forecasting by two long short-term memory-based models publication-title: J. Hydrol. – volume: 13 year: 2020 ident: b0130 publication-title: A deep-learning-based approach for Biophotonics – volume: 10 start-page: 1283 year: 2018 ident: b0040 article-title: Building ANN-based regional multi-step-ahead flood inundation forecast models publication-title: Water – reference: Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., Nearing, G., 2019. Benchmarking a catchment-aware Long Short-Term Memory Network (LSTM for large-scale hydrological modeling. arXiv preprint arXiv 1907.08456. – volume: 8 start-page: 1 year: 2018 end-page: 11 ident: b0160 article-title: Flood inundation assessment for the Hanoi Central Area, Vietnam under historical and extreme rainfall conditions publication-title: Sci. Rep. – volume: 529 start-page: 1788 year: 2015 end-page: 1797 ident: b0245 article-title: Neural network river forecasting through baseflow separation and binary-coded swarm optimization publication-title: J. Hydrol. – volume: 185 start-page: 1 year: 2016 end-page: 10 ident: b0295 article-title: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging publication-title: Neurocomputing – volume: 12 start-page: 578 year: 2020 ident: b0325 article-title: Improving the reliability of probabilistic multi-step-ahead flood forecasting by fusing unscented Kalman filter with recurrent neural network publication-title: Water – volume: 517 start-page: 836 year: 2014 end-page: 846 ident: b0030 article-title: Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control publication-title: J. Hydrol. – volume: 143 start-page: 7 year: 2016 end-page: 11 ident: b0300 article-title: Sequence to sequence weather forecasting with long short-term memory recurrent neural networks publication-title: Int. J. Computer Appl. – volume: 8 start-page: 5885 year: 2020 end-page: 5905 ident: b0200 article-title: Flood forecasting system based on integrated big and crowdsource data by using machine learning techniques publication-title: IEEE Access – volume: 11 start-page: 1387 year: 2019 ident: b0125 article-title: Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting publication-title: Water – start-page: 58 year: 2017 ident: 10.1016/j.jhydrol.2021.126371_b0140 – volume: 540 start-page: 623 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0085 article-title: A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2016.06.026 – volume: 23 start-page: 91 issue: 1 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0260 article-title: Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms publication-title: Meteorol. Appl. doi: 10.1002/met.1533 – start-page: 171 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0065 – volume: 8 start-page: 5885 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0200 article-title: Flood forecasting system based on integrated big and crowdsource data by using machine learning techniques publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2963819 – volume: 366 start-page: 415 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0335 article-title: Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2018.04.018 – volume: 184 start-page: 232 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0265 article-title: Auto-encoder based dimensionality reduction publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.08.104 – volume: 576 start-page: 98 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0215 article-title: Hydrological modelling of karst catchment using lumped conceptual and data mining models publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2019.06.036 – volume: 33 start-page: 4783 issue: 14 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0015 article-title: Short-Term Streamflow Forecasting Using the Feature-Enhanced Regression Model publication-title: Water Resour. Manage. doi: 10.1007/s11269-019-02399-1 – volume: 529 start-page: 1633 year: 2015 ident: 10.1016/j.jhydrol.2021.126371_b0010 article-title: Hourly runoff forecasting for flood risk management: Application of various computational intelligence models publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2015.07.057 – volume: 13 issue: 10 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0130 publication-title: A deep-learning-based approach for Biophotonics – volume: 529 start-page: 1788 year: 2015 ident: 10.1016/j.jhydrol.2021.126371_b0245 article-title: Neural network river forecasting through baseflow separation and binary-coded swarm optimization publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2015.08.008 – volume: 561 start-page: 918 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0310 article-title: Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2018.04.065 – ident: 10.1016/j.jhydrol.2021.126371_b0045 doi: 10.3390/w11010009 – volume: 517 start-page: 836 year: 2014 ident: 10.1016/j.jhydrol.2021.126371_b0030 article-title: Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2014.06.013 – volume: 533 start-page: 141 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0180 article-title: Coupling SWAT and ANN models for enhanced daily streamflow prediction publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2015.11.050 – volume: 572 start-page: 261 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0090 article-title: Comparative applications of data-driven models representing water table fluctuations publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2019.02.051 – volume: 135 start-page: 158 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0165 article-title: Classification with an edge: improving semantic image segmentation with boundary detection publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2017.11.009 – volume: 403 start-page: 348 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0060 article-title: Interpretable spatio-temporal attention LSTM model for flood forecasting publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.04.110 – volume: 28 start-page: 1055 issue: 3 year: 2014 ident: 10.1016/j.jhydrol.2021.126371_b0255 article-title: Including spatial distribution in a data-driven rainfall-runoff model to improve reservoir inflow forecasting in Taiwan publication-title: Hydrol. Process. doi: 10.1002/hyp.9559 – volume: 12 start-page: 578 issue: 2 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0325 article-title: Improving the reliability of probabilistic multi-step-ahead flood forecasting by fusing unscented Kalman filter with recurrent neural network publication-title: Water doi: 10.3390/w12020578 – volume: 6 start-page: 17851 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0095 article-title: A model combining stacked auto encoder and back propagation algorithm for short-term wind power forecasting publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2818108 – ident: 10.1016/j.jhydrol.2021.126371_b0270 doi: 10.18653/v1/D16-1137 – volume: e2020GL088731 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0195 article-title: Deep Learning as a tool to forecast hydrologic response for landslide-prone hillslopes publication-title: Geophys. Res. Lett. – volume: 535 start-page: 256 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0035 article-title: A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2016.01.056 – ident: 10.1016/j.jhydrol.2021.126371_b0280 doi: 10.1029/2019WR025326 – volume: 123915 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0285 article-title: Hybrid Forecasting Model for Non-stationary Daily Runoff Series: A Case Study in the Han River Basin, China publication-title: J. Hydrol. – volume: 124631 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0100 article-title: Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting publication-title: J. Hydrol. – volume: 28 start-page: 27 issue: 1 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0220 article-title: A wavelet-SARIMA-ANN hybrid model for precipitation forecasting publication-title: J. Water Land Develop. doi: 10.1515/jwld-2016-0003 – volume: 561 start-page: 918 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0305 article-title: Developing a Long Short-Term Memory (LSTM based model for predicting water table depth in agricultural areas publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2018.04.065 – volume: 82 start-page: 2635 issue: 12 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0230 article-title: A comprehensive review of deep learning applications in hydrology and water resources publication-title: Water Sci. Technol. doi: 10.2166/wst.2020.369 – ident: 10.1016/j.jhydrol.2021.126371_b0120 doi: 10.5194/hess-2019-368 – volume: 583 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0175 article-title: Streamflow and rainfall forecasting by two long short-term memory-based models publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2019.124296 – volume: 22 start-page: 6005 issue: 11 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0110 article-title: Rainfall–runoff modelling using long short-term memory (LSTM networks publication-title: Hydrol. Earth Syst. Sci. doi: 10.5194/hess-22-6005-2018 – volume: 11 start-page: 1387 issue: 7 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0125 article-title: Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting publication-title: Water doi: 10.3390/w11071387 – volume: 22 start-page: 6005 issue: 11 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0115 article-title: Rainfall–runoff modelling using long short-term memory (LSTM) networks publication-title: Hydrol. Earth Syst. Sci. doi: 10.5194/hess-22-6005-2018 – volume: 11 start-page: 1848 issue: 9 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0205 article-title: A novel hybrid extreme learning machine approach improved by K nearest neighbor method and fireworks algorithm for flood forecasting in medium and small watershed of loess region publication-title: Water doi: 10.3390/w11091848 – volume: 497 start-page: 71 year: 2013 ident: 10.1016/j.jhydrol.2021.126371_b0050 article-title: Reinforced recurrent neural networks for multi-step-ahead flood forecasts publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2013.05.038 – volume: 575 start-page: 890 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0170 article-title: Enhancing real-time streamflow forecasts with wavelet-neural network based error-updating schemes and ECMWF meteorological predictions in Variable Infiltration Capacity model publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2019.05.051 – volume: 32 start-page: 83 issue: 1 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0225 article-title: A comparative study of various hybrid wavelet feedforward neural network models for runoff forecasting publication-title: Water Resour. Manage. doi: 10.1007/s11269-017-1796-1 – volume: 10 start-page: 1283 issue: 9 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0040 article-title: Building ANN-based regional multi-step-ahead flood inundation forecast models publication-title: Water doi: 10.3390/w10091283 – volume: 30 start-page: 5145 issue: 14 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0135 article-title: Deep feature learning architectures for daily reservoir inflow forecasting publication-title: Water Resour. Manage. doi: 10.1007/s11269-016-1474-8 – volume: 143 start-page: 7 issue: 11 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0300 article-title: Sequence to sequence weather forecasting with long short-term memory recurrent neural networks publication-title: Int. J. Computer Appl. – volume: 567 start-page: 767 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0240 article-title: An adaptive middle and long-term runoff forecast model using EEMD-ANN hybrid approach publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2018.01.015 – volume: 125717 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0005 article-title: A hybrid of Random Forest and Deep Auto-Encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction publication-title: J. Hydrol. – volume: 481 start-page: 57 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0020 article-title: SGW-SCN: An integrated machine learning approach for workload forecasting in geo-distributed cloud data centers publication-title: Inf. Sci. doi: 10.1016/j.ins.2018.12.027 – volume: 117 start-page: 267 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0250 article-title: An efficient deep model for day-ahead electricity load forecasting with stacked denoising auto-encoders publication-title: J. Parallel Distrib. Comput. doi: 10.1016/j.jpdc.2017.06.007 – volume: 124 start-page: 409 issue: 3 year: 2017 ident: 10.1016/j.jhydrol.2021.126371_b0330 article-title: Uncovering the temporal context for video question answering publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-017-1033-7 – volume: 514 start-page: 358 year: 2014 ident: 10.1016/j.jhydrol.2021.126371_b0190 article-title: Applications of hybrid wavelet–artificial intelligence models in hydrology: A review publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2014.03.057 – volume: 84 start-page: V333 issue: 6 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0290 article-title: Deep learning for denoising publication-title: Geophysics doi: 10.1190/geo2018-0668.1 – volume: 24 start-page: 67 issue: 6 year: 2017 ident: 10.1016/j.jhydrol.2021.126371_b0070 article-title: Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network publication-title: J. China Univ Posts Telecommun doi: 10.1016/S1005-8885(17)60243-7 – volume: 544 start-page: 267 year: 2017 ident: 10.1016/j.jhydrol.2021.126371_b0185 article-title: An emotional ANN (EANN) approach to modeling rainfall-runoff process publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2016.11.033 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.jhydrol.2021.126371_b0080 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – volume: 8 start-page: 1 issue: 1 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0160 article-title: Flood inundation assessment for the Hanoi Central Area, Vietnam under historical and extreme rainfall conditions publication-title: Sci. Rep. doi: 10.1038/s41598-018-30024-5 – ident: 10.1016/j.jhydrol.2021.126371_b0275 doi: 10.1029/2019WR025326 – volume: 11 start-page: 1 issue: 1 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_bib336 article-title: Self-organizing maps of typhoon tracks allow for flood forecasts up to two days in advance publication-title: Nat. Commun. doi: 10.1038/s41467-020-15734-7 – volume: 19 start-page: 195 issue: 3 year: 2020 ident: 10.1016/j.jhydrol.2021.126371_b0105 article-title: Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers publication-title: Magnetic Resonance Med. Sci. doi: 10.2463/mrms.mp.2019-0018 – volume: 234 start-page: 11 year: 2017 ident: 10.1016/j.jhydrol.2021.126371_b0145 article-title: A survey of deep neural network architectures and their applications publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.12.038 – start-page: 4774 year: 2018 ident: 10.1016/j.jhydrol.2021.126371_b0055 article-title: State-of-the-art speech recognition with sequence-to-sequence models – volume: 209 start-page: 134 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0320 article-title: Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts publication-title: J. Cleaner Prod. doi: 10.1016/j.jclepro.2018.10.243 – volume: 12 start-page: 2445 issue: 12 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0150 article-title: Deep learning with stacked denoising auto-encoder for short-term electric load forecasting publication-title: Energies doi: 10.3390/en12122445 – volume: 67 start-page: 1471 issue: 5 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0210 article-title: Long short-term memory (LSTM recurrent neural network for low-flow hydrological time series forecasting publication-title: Acta Geophys. doi: 10.1007/s11600-019-00330-1 – volume: 16 start-page: 1763 issue: 4 year: 2019 ident: 10.1016/j.jhydrol.2021.126371_b0025 article-title: Temporal prediction of multiapplication consolidated workloads in distributed clouds publication-title: IEEE Trans. Autom. Sci. Eng. doi: 10.1109/TASE.2019.2895801 – volume: 185 start-page: 1 year: 2016 ident: 10.1016/j.jhydrol.2021.126371_b0295 article-title: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.11.044 |
| SSID | ssj0000334 |
| Score | 2.6028411 |
| Snippet | •Use Stacked Autoencoder (SAE) to reduce the dimension of regional inundation data.•Use PCA to adjust the network structure and initialize network weights of... Reliable and accurate regional multistep-ahead flood forecasts during extreme events are crucial and beneficial to flood disaster management and preparedness.... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 126371 |
| SubjectTerms | case studies data collection disaster preparedness hydrology Long short-term memory (LSTM) Multistep-ahead forecast neural networks rain Recurrent neural network (RNN) Regional flood inundation Stacked autoencoder (SAE) Taiwan uncertainty |
| Title | Fusing stacked autoencoder and long short-term memory for regional multistep-ahead flood inundation forecasts |
| URI | https://dx.doi.org/10.1016/j.jhydrol.2021.126371 https://www.proquest.com/docview/2551924886 |
| Volume | 598 |
| WOSCitedRecordID | wos000661813200131&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: 1879-2707 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000334 issn: 0022-1694 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBZZO9hexq6su6HB3oKy-CbLj6E0a_dQ9tBB9mRkWVodEifEcel-Rf9yz7Fku6Qd3QZ7MYmJLKLvk3R0fM53CPmkgTaZCAzLEhTV5h5MKa04k0k8FkYLX2WqKTYRn56K2Sz5NhhctbkwF4u4LMXlZbL-r1DDPQAbU2f_Au7uoXADPgPocAXY4fpHwE_ryvkIYILmQ1lvVyhWiZoR6CRfYHGh6hysboar8nCJobY2ahOLNDSOwSbKEOBfMwlrdT40GN0-LMq2AhP-WitZWRWoO2zb81_5xoo7gQE7WaIYQ47M6yO7ZeOiPWEwdD-7oKBiVTesKiT7UeyECmH4LTuuio7Mh62re1qwLqDY-S98r4t1dU61W4k1XZKBx23945G2a7OIE0yfi28u3pGtYX1rI7A-iflobv_wCHseeT4PbMGXHY1tfGXtY3c-CujBkesB2ffjKIFlcn9ycjT72m_uQRC2AvTYoE8K-3xnZ78zd3Y2_saaOXtKnjio6MTS5xkZ6PI5efRFOwHzF2RpaUQdjegNGlGgEUUa0Z5G1NKIAjFoSyO6QyPa0Ij2NKIdjV6S79Ojs8Nj5kpzMBWE_pYJJcAy5EroCA70OlQi0irKchHmfJxk0uTwDbDxTGwCMeaZlgEcTpWMFc8iKYNXZK9clfo1oSI3gZIemK6-CeM8knqccQNmvzDCzyLvgITtCKbK6dZj-ZRF2gYozlM38CkOfGoH_oCMumZrK9xyXwPRwpM669NalSlw6r6mH1s4U1id8ZWbLPWqrlI4sKOHQwj-5t8f_5Y87ifOO7K33dT6PXmoLgDDzQfH0Gtol7vi |
| 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=Fusing+stacked+autoencoder+and+long+short-term+memory+for+regional+multistep-ahead+flood+inundation+forecasts&rft.jtitle=Journal+of+hydrology+%28Amsterdam%29&rft.au=Kao%2C+I-Feng&rft.au=Liou%2C+Jia-Yi&rft.au=Lee%2C+Meng-Hsin&rft.au=Chang%2C+Fi-John&rft.date=2021-07-01&rft.pub=Elsevier+B.V&rft.issn=0022-1694&rft.eissn=1879-2707&rft.volume=598&rft_id=info:doi/10.1016%2Fj.jhydrol.2021.126371&rft.externalDocID=S0022169421004182 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0022-1694&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0022-1694&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0022-1694&client=summon |