TY - JOUR
T1 - Viewing Soil Moisture Flash Drought Onset Mechanism and Their Changes Through XAI Lens
T2 - A Case Study in Eastern China
AU - Feng, Jiajin
AU - Li, Jun
AU - Xu, Chong Yu
AU - Wang, Zhaoli
AU - Zhang, Zhenxing
AU - Wu, Xushu
AU - Lai, Chengguang
AU - Zeng, Zhaoyang
AU - Tong, Hongfu
AU - Jiang, Shijie
N1 - We would like to thank the editors and anonymous reviewers for their detailed and constructive comments, which helped to significantly improve the manuscript. This research was financially supported by the National Natural Science Foundation of China (52109019), the Guangdong Basic and Applied Basic Research Foundation (2023B1515020087, 2023A1515030191, 2021A1515010935), and the cooperation research project between South China University of Technology and Qingyuan Hydrology Sub-bureau of Guangdong Province (QYSWFK-2022-85). J.L. acknowledges the National Natural Science Foundation of China (42301106). S.J. acknowledges support by the Carl Zeiss Stiftung. Z.Z. acknowledges the National Natural Science Foundation of China (52209019) and the Guangzhou Basic and Applied Basic Research Scheme (2023A04J1595).
We would like to thank the editors and anonymous reviewers for their detailed and constructive comments, which helped to significantly improve the manuscript. This research was financially supported by the National Natural Science Foundation of China (52109019), the Guangdong Basic and Applied Basic Research Foundation (2023B1515020087, 2023A1515030191, 2021A1515010935), and the cooperation research project between South China University of Technology and Qingyuan Hydrology Sub\u2010bureau of Guangdong Province (QYSWFK\u20102022\u201085). J.L. acknowledges the National Natural Science Foundation of China (42301106). S.J. acknowledges support by the Carl Zeiss Stiftung. Z.Z. acknowledges the National Natural Science Foundation of China (52209019) and the Guangzhou Basic and Applied Basic Research Scheme (2023A04J1595).
PY - 2024/6
Y1 - 2024/6
N2 - Soil moisture flash droughts often pose significant challenges to humans and ecosystems, with wide-ranging socioeconomic consequences. However, the underlying mechanisms of flash droughts and their changes remain unquantified. Taking China as a case study, we present a novel framework that combines machine learning with interpretable and cluster techniques to investigate flash drought mechanisms from 1980 to 2018. We first quantified the temporal contribution of drivers and further identified different mechanisms during drought onsets. We subsequently investigated the temporal changes in different mechanisms and classified drought event types. We identified four driving mechanism types triggering drought: Concurrent precipitation, Antecedent-concurrent precipitation, Antecedent temperature-concurrent precipitation, and Antecedent transpiration-concurrent precipitation. The total effects from vegetation transpiration contributed to around 50% of the impacts for mechanisms involving antecedent transpiration and concurrent precipitation, highlighting the non-neglectable role of vegetation water consumption in drought occurrences. Remarkably, about 60% of flash drought onsets exhibited close association with the antecedent anomalies, which contribute approximately 50% of overall effects, emphasizing the importance of the cumulative effects of drivers. Moreover, driving mechanisms associated with temperature and transpiration increased significantly over time, implying an elevated influence of these factors on droughts. Our classification of drought events reveals that nearly 70% of events were driven by at least two mechanisms, underscoring a complex time-varying pattern of driving factors during drought events. The proposed holistic framework not only sheds insight into the multifaceted mechanisms driving flash droughts within China but also extends its potential applicability to broader geographical contexts.
AB - Soil moisture flash droughts often pose significant challenges to humans and ecosystems, with wide-ranging socioeconomic consequences. However, the underlying mechanisms of flash droughts and their changes remain unquantified. Taking China as a case study, we present a novel framework that combines machine learning with interpretable and cluster techniques to investigate flash drought mechanisms from 1980 to 2018. We first quantified the temporal contribution of drivers and further identified different mechanisms during drought onsets. We subsequently investigated the temporal changes in different mechanisms and classified drought event types. We identified four driving mechanism types triggering drought: Concurrent precipitation, Antecedent-concurrent precipitation, Antecedent temperature-concurrent precipitation, and Antecedent transpiration-concurrent precipitation. The total effects from vegetation transpiration contributed to around 50% of the impacts for mechanisms involving antecedent transpiration and concurrent precipitation, highlighting the non-neglectable role of vegetation water consumption in drought occurrences. Remarkably, about 60% of flash drought onsets exhibited close association with the antecedent anomalies, which contribute approximately 50% of overall effects, emphasizing the importance of the cumulative effects of drivers. Moreover, driving mechanisms associated with temperature and transpiration increased significantly over time, implying an elevated influence of these factors on droughts. Our classification of drought events reveals that nearly 70% of events were driven by at least two mechanisms, underscoring a complex time-varying pattern of driving factors during drought events. The proposed holistic framework not only sheds insight into the multifaceted mechanisms driving flash droughts within China but also extends its potential applicability to broader geographical contexts.
KW - event classification
KW - flash drought
KW - interpretable machine learning
KW - mechanism quantification
KW - type changes
UR - http://www.scopus.com/inward/record.url?scp=85195886184&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85195886184&partnerID=8YFLogxK
U2 - 10.1029/2023WR036297
DO - 10.1029/2023WR036297
M3 - Article
AN - SCOPUS:85195886184
SN - 0043-1397
VL - 60
JO - Water Resources Research
JF - Water Resources Research
IS - 6
M1 - e2023WR036297
ER -