Explaining the Mechanism of Multiscale Groundwater Drought Events: A New Perspective From Interpretable Deep Learning Model

Cai, Hejiang1,2,3; Shi, Haiyun2,3; Zhou, Zhaoqiang4; Liu, Suning3; Babovic, Vladan1

2024-07-01

10.1029/2023WR035139

WATER RESOURCES RESEARCH   影响因子和分区

0043-1397

1944-7973

["This study presents a new approach to understand the causes of groundwater drought events with interpretable deep learning (DL) models. As prerequisites, accurate long short-term memory (LSTM) models for simulating groundwater are built for 16 regions representing three types of spatial scales in the southeastern United States, and standardized groundwater index is applied to identify 233 groundwater drought events. Two interpretation methods, expected gradients (EG) and additive decomposition (AD), are adopted to decipher the DL-captured patterns and inner workings of LSTM networks. The EG results show that: (a) temperature-related features were the primary drivers of large-scale groundwater droughts, with their importance increasing from 56.1% to 63.1% as the drought events approached from 6 months to 15 days. Conversely, precipitation-related features were found to be the dominant factors in the formation of groundwater drought in small-scale catchments, with the overall importance ranging from 59.8% to 53.3%; (b) Seasonal variations in the importance of temperature-related factors are inversely related between large and small spatial scales, being more significant in summer for larger regions and in winter for catchments; and (c) temperature-related factors exhibited an overall \"trigger effect\" on causing groundwater drought events in the studying areas. The AD method unveiled how the LSTM network behaved differently in retaining and discarding information when emulating different groundwater droughts. In summary, this study provides a new perspective for the causes of groundwater drought events and highlights the potential and prospect of interpretable DL in enhancing our understanding of hydrological processes.","An interpretable deep learning model was proposed to explain the mechanisms of groundwater droughts at different scales The interpretation analysis of 233 groundwater droughts revealed spatial-temporal variations in their dominant factors and trigger effects The proposed model could successfully capture the confluence effect of precipitation and long-term memory characteristics of groundwater"]

groundwater drought explainable AI LSTM network temporal analysis model interpretation

SCI ; EI

英语

通讯

National Key Research and Development Program of China[2022YFC3201802] ; Shenzhen Key Laboratory of Precision Measurement and Early Warning Technology for Urban Environmental Health Risks[ZDSYS20220606100604008] ; Natural Science Foundation of Shenzhen[JCYJ20210324105014039]

Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources

Environmental Sciences ; Limnology ; Water Resources

WOS:001255537400001

AMER GEOPHYSICAL UNION

20242716598020

Catchments ; Groundwater ; Learning systems ; Long short-term memory ; Runoff

Flood Control:442.1 ; Precipitation:443.3 ; Water Resources:444 ; Surface Water:444.1 ; Groundwater:444.2

ENVIRONMENT/ECOLOGY

Web of Science

1.Natl Univ Singapore, Dept Civil & Environm Engn, Singapore, Singapore
2.Southern Univ Sci & Technol, Sch Environm Sci & Engn, Shenzhen Key Lab Precis Measurement & Early Warnin, Shenzhen, Peoples R China
3.Southern Univ Sci & Technol, Sch Environm Sci & Engn, State Environm Protect Key Lab Integrated Surface, Shenzhen, Peoples R China
4.Northeast Agr Univ, Sch Water Conservancy & Civil Engn, Harbin, Peoples R China

Cai, Hejiang,Shi, Haiyun,Zhou, Zhaoqiang,et al. Explaining the Mechanism of Multiscale Groundwater Drought Events: A New Perspective From Interpretable Deep Learning Model[J]. WATER RESOURCES RESEARCH,2024,60(7).

Cai, Hejiang,Shi, Haiyun,Zhou, Zhaoqiang,Liu, Suning,&Babovic, Vladan.(2024).Explaining the Mechanism of Multiscale Groundwater Drought Events: A New Perspective From Interpretable Deep Learning Model.WATER RESOURCES RESEARCH,60(7).

Cai, Hejiang,et al."Explaining the Mechanism of Multiscale Groundwater Drought Events: A New Perspective From Interpretable Deep Learning Model".WATER RESOURCES RESEARCH 60.7(2024).