Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin
A warming climate will intensify the water cycle, resulting in an exacerbation of water resources crises and flooding risks in the Lancang–Mekong River Basin (LMRB). The mitigation of these risks requires accurate streamflow and flood simulations. Process-based and data-driven hydrological models ar...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/14/9/1429 |
| _version_ | 1797502430468898816 |
|---|---|
| author | Binxiao Liu Qiuhong Tang Gang Zhao Liang Gao Chaopeng Shen Baoxiang Pan |
| author_facet | Binxiao Liu Qiuhong Tang Gang Zhao Liang Gao Chaopeng Shen Baoxiang Pan |
| author_sort | Binxiao Liu |
| collection | DOAJ |
| description | A warming climate will intensify the water cycle, resulting in an exacerbation of water resources crises and flooding risks in the Lancang–Mekong River Basin (LMRB). The mitigation of these risks requires accurate streamflow and flood simulations. Process-based and data-driven hydrological models are the two major approaches for streamflow simulations, while a hybrid of these two methods promises advantageous prediction accuracy. In this study, we developed a hybrid physics-data (HPD) methodology for streamflow and flood prediction under the physics-guided neural network modeling framework. The HPD methodology leveraged simulation information from a process-based model (i.e., VIC-CaMa-Flood) along with the meteorological forcing information (precipitation, maximum temperature, minimum temperature, and wind speed) to simulate the daily streamflow series and flood events, using a long short-term memory (LSTM) neural network. This HPD methodology outperformed the pure process-based VIC-CaMa-Flood model or the pure observational data driven LSTM model by a large margin, suggesting the usefulness of introducing physical regularization in data-driven modeling, and the necessity of observation-informed bias correction for process-based models. We further developed a gradient boosting tree method to measure the information contribution from the process-based model simulation and the meteorological forcing data in our HPD methodology. The results show that the process-based model simulation contributes about 30% to the HPD outcome, outweighing the information contribution from each of the meteorological forcing variables (<20%). Our HPD methodology inherited the physical mechanisms of the process-based model, and the high predictability capability of the LSTM model, offering a novel way for making use of incomplete physical understanding, and insufficient data, to enhance streamflow and flood predictions. |
| first_indexed | 2024-03-10T03:32:59Z |
| format | Article |
| id | doaj.art-263f32d09b6547ab9a7c0dd90725216d |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T03:32:59Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-263f32d09b6547ab9a7c0dd90725216d2023-11-23T09:35:37ZengMDPI AGWater2073-44412022-04-01149142910.3390/w14091429Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River BasinBinxiao Liu0Qiuhong Tang1Gang Zhao2Liang Gao3Chaopeng Shen4Baoxiang Pan5Key Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaDepartment of Global Ecology, Carnegie Institution for Science, Stanford, CA 94305, USAState Key Laboratory of Internet of Things for Smart City and Department of Civil and Environmental Engineering, University of Macau, Macao SAR 999078, ChinaCivil and Environmental Engineering, Pennsylvania State University, State College, PA 16801, USALawrence Livermore National Lab, Atmospheric, Earth and Energy Division, Livermore, CA 94550, USAA warming climate will intensify the water cycle, resulting in an exacerbation of water resources crises and flooding risks in the Lancang–Mekong River Basin (LMRB). The mitigation of these risks requires accurate streamflow and flood simulations. Process-based and data-driven hydrological models are the two major approaches for streamflow simulations, while a hybrid of these two methods promises advantageous prediction accuracy. In this study, we developed a hybrid physics-data (HPD) methodology for streamflow and flood prediction under the physics-guided neural network modeling framework. The HPD methodology leveraged simulation information from a process-based model (i.e., VIC-CaMa-Flood) along with the meteorological forcing information (precipitation, maximum temperature, minimum temperature, and wind speed) to simulate the daily streamflow series and flood events, using a long short-term memory (LSTM) neural network. This HPD methodology outperformed the pure process-based VIC-CaMa-Flood model or the pure observational data driven LSTM model by a large margin, suggesting the usefulness of introducing physical regularization in data-driven modeling, and the necessity of observation-informed bias correction for process-based models. We further developed a gradient boosting tree method to measure the information contribution from the process-based model simulation and the meteorological forcing data in our HPD methodology. The results show that the process-based model simulation contributes about 30% to the HPD outcome, outweighing the information contribution from each of the meteorological forcing variables (<20%). Our HPD methodology inherited the physical mechanisms of the process-based model, and the high predictability capability of the LSTM model, offering a novel way for making use of incomplete physical understanding, and insufficient data, to enhance streamflow and flood predictions.https://www.mdpi.com/2073-4441/14/9/1429hydrological modelingdata-driven modelingphysics-guided neural network (PGNN) |
| spellingShingle | Binxiao Liu Qiuhong Tang Gang Zhao Liang Gao Chaopeng Shen Baoxiang Pan Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin Water hydrological modeling data-driven modeling physics-guided neural network (PGNN) |
| title | Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin |
| title_full | Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin |
| title_fullStr | Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin |
| title_full_unstemmed | Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin |
| title_short | Physics-Guided Long Short-Term Memory Network for Streamflow and Flood Simulations in the Lancang–Mekong River Basin |
| title_sort | physics guided long short term memory network for streamflow and flood simulations in the lancang mekong river basin |
| topic | hydrological modeling data-driven modeling physics-guided neural network (PGNN) |
| url | https://www.mdpi.com/2073-4441/14/9/1429 |
| work_keys_str_mv | AT binxiaoliu physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin AT qiuhongtang physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin AT gangzhao physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin AT lianggao physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin AT chaopengshen physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin AT baoxiangpan physicsguidedlongshorttermmemorynetworkforstreamflowandfloodsimulationsinthelancangmekongriverbasin |