Debris flows dynamic risk assessment and interpretable Shapley method-based driving mechanisms exploring – A case study of the upper reach of the Min River

• Mapped the variation pattern of debris flow risk in the upper reach of the Min River between the 2000 and 2020. • Explored the Shapley method’s feasibility for assessing debris flow risk. • Uncovered the driving mechanism of debris flow risk variation due to the indicators. • Revealed the changes in debris flow risk and causes from the perspective of elevation zones. Debris flow is one of the most devastating natural hazards. Identifying the dynamic changes and driving factors of debris flow risk can enhance hazard mitigation and prevention. It is not clear what factors can mostly lead to debris flow risk change in mountainous areas, particularly some of these areas in the context of intense earthquakes, rapid urbanization, and climate change. To address these questions, an ensemble learning model was constructed to estimate the debris flow risk of the baseline period (2000) and the current period (2020) in the upper reach of the Min River. The study found that the areas with extremely high debris flow risk decreased by 18.57%, while the areas with moderate and high risk levels increased by 8% and 14% respectively. With this trend of overall risk increasing, the population and buildings affected by extremely high debris flow risk have increased by 20% and 30% respectively. Based on the interpretable learning model of SHAP (The Shapley Additive Explanations value), the mechanisms by driven factors that lead to changes in risk were explored. Population, elevation and NDVI are the most influential factors leading to changes in risk. Specifically, the increase in risk in the low elevation area is due to the rapid urbanization caused by the increase of population and GDP. While the risk change in higher elevation areas contributes to the variation of vegetation and precipitation. These findings have implications for debris flow mitigation and contribute to the understanding of the multiple factors that impact debris flow risk.

Authors

Institutions

Publication Details

Journal
Ecological Indicators
Published
2025-03-31
DOI
https://doi.org/10.1016/j.ecolind.2025.113400
Citations
6
Primary Topic
Landslides and related hazards
Type
article
Field-Weighted Citation Impact
14.53
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Debris flows dynamic risk assessment and interpretable Shapley method-based driving mechanisms exploring – A case study of the upper reach of the Min River

Yufeng He, Jun Liu, Yu Duan, Hao Zheng et al.
6 citations
Ecological Indicators
Landslides and related hazards
14.53
article

Debris flows dynamic risk assessment and interpretable Shapley method-based driving mechanisms exploring – A case study of the upper reach of the Min River

Yufeng He, Jun Liu, Yu Duan, Hao Zheng, Wen He, Mingtao Ding
article en
6 citations

Abstract

• Mapped the variation pattern of debris flow risk in the upper reach of the Min River between the 2000 and 2020. • Explored the Shapley method’s feasibility for assessing debris flow risk. • Uncovered the driving mechanism of debris flow risk variation due to the indicators. • Revealed the changes in debris flow risk and causes from the perspective of elevation zones. Debris flow is one of the most devastating natural hazards. Identifying the dynamic changes and driving factors of debris flow risk can enhance hazard mitigation and prevention. It is not clear what factors can mostly lead to debris flow risk change in mountainous areas, particularly some of these areas in the context of intense earthquakes, rapid urbanization, and climate change. To address these questions, an ensemble learning model was constructed to estimate the debris flow risk of the baseline period (2000) and the current period (2020) in the upper reach of the Min River. The study found that the areas with extremely high debris flow risk decreased by 18.57%, while the areas with moderate and high risk levels increased by 8% and 14% respectively. With this trend of overall risk increasing, the population and buildings affected by extremely high debris flow risk have increased by 20% and 30% respectively. Based on the interpretable learning model of SHAP (The Shapley Additive Explanations value), the mechanisms by driven factors that lead to changes in risk were explored. Population, elevation and NDVI are the most influential factors leading to changes in risk. Specifically, the increase in risk in the low elevation area is due to the rapid urbanization caused by the increase of population and GDP. While the risk change in higher elevation areas contributes to the variation of vegetation and precipitation. These findings have implications for debris flow mitigation and contribute to the understanding of the multiple factors that impact debris flow risk.

Ecological IndicatorsVol. 173
Sun Yat-sen University (CN), Sichuan University (CN), Southwest Jiaotong University (CN)
Climate action
Openalex Percentile: Top 1%
Landslides and related hazards
14.53
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.