Evaluation and machine learning improvement of global hydrological model-based flood simulations
A warmer climate is expected to accelerate global hydrological cycle, causing more intense precipitation and floods. Despite recent progress in global flood risk assessment, the accuracy and improvement of global hydrological models (GHMs)-based flood simulation is insufficient for most applications...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IOP Publishing
2019-01-01
|
Series: | Environmental Research Letters |
Subjects: | |
Online Access: | https://doi.org/10.1088/1748-9326/ab4d5e |
_version_ | 1797747854142341120 |
---|---|
author | Tao Yang Fubao Sun Pierre Gentine Wenbin Liu Hong Wang Jiabo Yin Muye Du Changming Liu |
author_facet | Tao Yang Fubao Sun Pierre Gentine Wenbin Liu Hong Wang Jiabo Yin Muye Du Changming Liu |
author_sort | Tao Yang |
collection | DOAJ |
description | A warmer climate is expected to accelerate global hydrological cycle, causing more intense precipitation and floods. Despite recent progress in global flood risk assessment, the accuracy and improvement of global hydrological models (GHMs)-based flood simulation is insufficient for most applications. Here we compared flood simulations from five GHMs under the Inter-Sectoral Impact Model Intercomparison Project 2a (ISIMIP2a) protocol, against those calculated from 1032 gauging stations in the Global Streamflow Indices and Metadata Archive for the historical period 1971–2010. A machine learning approach, namely the long short-term memory units (LSTM) was adopted to improve the GHMs-based flood simulations within a hybrid physics- machine learning approach (using basin-averaged daily mean air temperature, precipitation, wind speed and the simulated daily discharge from GHMs-CaMa-Flood model chain as the inputs of LSTM, and observed daily discharge as the output value). We found that the GHMs perform reasonably well in terms of amplitude of peak discharge but are relatively poor in terms of their timing. The performance indicated great discrepancy under different climate zones. The large difference in performance between GHMs and observations reflected that those simulations require improvements. The LSTM used in combination with those GHMs was then shown to drastically improve the performance of global flood simulations (especially in terms of amplitude of peak discharge), suggesting that the combination of classical flood simulation and machine learning techniques might be a way forward for more robust and confident flood risk assessment. |
first_indexed | 2024-03-12T15:57:33Z |
format | Article |
id | doaj.art-48d4788484294f63be09eec9fe9c4bd3 |
institution | Directory Open Access Journal |
issn | 1748-9326 |
language | English |
last_indexed | 2024-03-12T15:57:33Z |
publishDate | 2019-01-01 |
publisher | IOP Publishing |
record_format | Article |
series | Environmental Research Letters |
spelling | doaj.art-48d4788484294f63be09eec9fe9c4bd32023-08-09T14:48:05ZengIOP PublishingEnvironmental Research Letters1748-93262019-01-01141111402710.1088/1748-9326/ab4d5eEvaluation and machine learning improvement of global hydrological model-based flood simulationsTao Yang0https://orcid.org/0000-0002-7662-4798Fubao Sun1Pierre Gentine2https://orcid.org/0000-0002-0845-8345Wenbin Liu3https://orcid.org/0000-0002-9569-6762Hong Wang4Jiabo Yin5Muye Du6Changming Liu7Key Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of China; Department of Earth and Environmental Engineering, Columbia University , New York, United States of America; University of Chinese Academy of Sciences , Beijing, People’s Republic of ChinaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of China; University of Chinese Academy of Sciences , Beijing, People’s Republic of China; State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, People’s Republic of China; Akesu National Station of Observation and Research for Oasis Agro-ecosystem, Akesu, Xinjiang, People’s Republic of ChinaDepartment of Earth and Environmental Engineering, Columbia University , New York, United States of America; Earth Institute, Columbia University , New York, United States of AmericaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaDepartment of Earth and Environmental Engineering, Columbia University , New York, United States of America; State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University , Wuhan, People’s Republic of ChinaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of China; University of Chinese Academy of Sciences , Beijing, People’s Republic of ChinaKey Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaA warmer climate is expected to accelerate global hydrological cycle, causing more intense precipitation and floods. Despite recent progress in global flood risk assessment, the accuracy and improvement of global hydrological models (GHMs)-based flood simulation is insufficient for most applications. Here we compared flood simulations from five GHMs under the Inter-Sectoral Impact Model Intercomparison Project 2a (ISIMIP2a) protocol, against those calculated from 1032 gauging stations in the Global Streamflow Indices and Metadata Archive for the historical period 1971–2010. A machine learning approach, namely the long short-term memory units (LSTM) was adopted to improve the GHMs-based flood simulations within a hybrid physics- machine learning approach (using basin-averaged daily mean air temperature, precipitation, wind speed and the simulated daily discharge from GHMs-CaMa-Flood model chain as the inputs of LSTM, and observed daily discharge as the output value). We found that the GHMs perform reasonably well in terms of amplitude of peak discharge but are relatively poor in terms of their timing. The performance indicated great discrepancy under different climate zones. The large difference in performance between GHMs and observations reflected that those simulations require improvements. The LSTM used in combination with those GHMs was then shown to drastically improve the performance of global flood simulations (especially in terms of amplitude of peak discharge), suggesting that the combination of classical flood simulation and machine learning techniques might be a way forward for more robust and confident flood risk assessment.https://doi.org/10.1088/1748-9326/ab4d5eflood simulationmachine learningglobal hydrological modellong short-term memory |
spellingShingle | Tao Yang Fubao Sun Pierre Gentine Wenbin Liu Hong Wang Jiabo Yin Muye Du Changming Liu Evaluation and machine learning improvement of global hydrological model-based flood simulations Environmental Research Letters flood simulation machine learning global hydrological model long short-term memory |
title | Evaluation and machine learning improvement of global hydrological model-based flood simulations |
title_full | Evaluation and machine learning improvement of global hydrological model-based flood simulations |
title_fullStr | Evaluation and machine learning improvement of global hydrological model-based flood simulations |
title_full_unstemmed | Evaluation and machine learning improvement of global hydrological model-based flood simulations |
title_short | Evaluation and machine learning improvement of global hydrological model-based flood simulations |
title_sort | evaluation and machine learning improvement of global hydrological model based flood simulations |
topic | flood simulation machine learning global hydrological model long short-term memory |
url | https://doi.org/10.1088/1748-9326/ab4d5e |
work_keys_str_mv | AT taoyang evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT fubaosun evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT pierregentine evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT wenbinliu evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT hongwang evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT jiaboyin evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT muyedu evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations AT changmingliu evaluationandmachinelearningimprovementofglobalhydrologicalmodelbasedfloodsimulations |