Long short-term memory models of water quality in inland water environments
Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Water Research X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589914723000439 |
| _version_ | 1797405383668531200 |
|---|---|
| author | JongCheol Pyo Yakov Pachepsky Soobin Kim Ather Abbas Minjeong Kim Yong Sung Kwon Mayzonee Ligaray Kyung Hwa Cho |
| author_facet | JongCheol Pyo Yakov Pachepsky Soobin Kim Ather Abbas Minjeong Kim Yong Sung Kwon Mayzonee Ligaray Kyung Hwa Cho |
| author_sort | JongCheol Pyo |
| collection | DOAJ |
| description | Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review. |
| first_indexed | 2024-03-09T03:09:21Z |
| format | Article |
| id | doaj.art-c57d1792701f4337b2ac592906a46a05 |
| institution | Directory Open Access Journal |
| issn | 2589-9147 |
| language | English |
| last_indexed | 2024-03-09T03:09:21Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Water Research X |
| spelling | doaj.art-c57d1792701f4337b2ac592906a46a052023-12-04T05:23:53ZengElsevierWater Research X2589-91472023-12-0121100207Long short-term memory models of water quality in inland water environmentsJongCheol Pyo0Yakov Pachepsky1Soobin Kim2Ather Abbas3Minjeong Kim4Yong Sung Kwon5Mayzonee Ligaray6Kyung Hwa Cho7Department for Environmental Engineering, Pusan National University, Busan 46241, Republic of KoreaEnvironmental Microbial and Food Safety Laboratory, USDA-ARS, Beltsville, MD, USASchool of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulju-gun, Ulsan 44919, Republic of Korea; Disposal Safety Evaluation R&D Division, Korea Atomic Energy Research Institute (KAERI), 111, Daedeok-daero 989 beon-gil, Yuseong-gu, Daejeon 34057, Republic of KoreaPhysical Sciences and Engineering, King Abdullah University of Science and Technology, Thuwal 23955-6900, Kingdom of Saudi ArabiaDisposal Safety Evaluation R&D Division, Korea Atomic Energy Research Institute (KAERI), 111, Daedeok-daero 989 beon-gil, Yuseong-gu, Daejeon 34057, Republic of KoreaEnvironmental Impact Assessment Team, Division of Ecological Assessment Research, National Institute of Ecology, Seocheon, Republic of KoreaInstitute of Environmental Science and Meteorology, College of Science, University of the Philippines Diliman, Quezon City 1101, PhilippinesSchool of Civil, Environmental and Architectural Engineering, Korea University, Seoul 02841, Republic of Korea; Corresponding author.Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review.http://www.sciencedirect.com/science/article/pii/S2589914723000439Long short-term memoryInland waterWater qualityEnsemble LSTMDeep learning models |
| spellingShingle | JongCheol Pyo Yakov Pachepsky Soobin Kim Ather Abbas Minjeong Kim Yong Sung Kwon Mayzonee Ligaray Kyung Hwa Cho Long short-term memory models of water quality in inland water environments Water Research X Long short-term memory Inland water Water quality Ensemble LSTM Deep learning models |
| title | Long short-term memory models of water quality in inland water environments |
| title_full | Long short-term memory models of water quality in inland water environments |
| title_fullStr | Long short-term memory models of water quality in inland water environments |
| title_full_unstemmed | Long short-term memory models of water quality in inland water environments |
| title_short | Long short-term memory models of water quality in inland water environments |
| title_sort | long short term memory models of water quality in inland water environments |
| topic | Long short-term memory Inland water Water quality Ensemble LSTM Deep learning models |
| url | http://www.sciencedirect.com/science/article/pii/S2589914723000439 |
| work_keys_str_mv | AT jongcheolpyo longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT yakovpachepsky longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT soobinkim longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT atherabbas longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT minjeongkim longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT yongsungkwon longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT mayzoneeligaray longshorttermmemorymodelsofwaterqualityininlandwaterenvironments AT kyunghwacho longshorttermmemorymodelsofwaterqualityininlandwaterenvironments |