Leveraging artificial intelligence to quantify slope rainfall sensitivity for refining regional landslide rainfall thresholds

IF 8.4 1区工程技术 Q1 ENGINEERING, GEOLOGICAL

Engineering Geology Pub Date : 2025-07-23 DOI:10.1016/j.enggeo.2025.108260

Yuhang Zhu , Kunlong Yin , Ye Li , Haoran Yang , Hong Chen , Chao Zhou , Samuele Segoni

{"title":"Leveraging artificial intelligence to quantify slope rainfall sensitivity for refining regional landslide rainfall thresholds","authors":"Yuhang Zhu , Kunlong Yin , Ye Li , Haoran Yang , Hong Chen , Chao Zhou , Samuele Segoni","doi":"10.1016/j.enggeo.2025.108260","DOIUrl":null,"url":null,"abstract":"<div><div>Regional-scale landslide early warning systems are commonly developed based on empirical rainfall thresholds. However, current rainfall threshold models overlook the significant spatial variations in slopes response to rainfall, thus undermining the accuracy of warnings. In this study, we improved a regional-scale landslide early warning method based on rainfall thresholds by accounting for the varying rainfall sensitivity of individual slope units. First, the Rainfall Sensitivity Index (RSI) for both dry and wet seasons are computed using a Graph Attention Network (GAN) model, incorporating ten influencing factors. Subsequently, an initial regional critical rainfall threshold was obtained based on the Effective cumulative rainfall – rainfall Duration (<em>E</em>-D). Finally, the improved rainfall thresholds for each slope units are derived by coupling the initial critical rainfall threshold and RSI. Using Pingyang County, Zhejiang Province, China as test site, the reliability and reasonableness of the proposed method was validated by statistical analysis, in-situ tests and historical rainfall events. The results reveal that the GAN demonstrates robust predictive capability in RSI assessment, achieving a precision of 0.88. Notably, slopes exhibit higher rainfall sensitivity during dry season compared to wet season. The early warning system employing improved critical thresholds shows significant improvement, with 11.9 % higher accuracy and 14.3 % fewer missed alarms relative to conventional methods. Overall, this study proposes a novel method for downscaling of regional-scale thresholds to slope-unit levels in landslide early warning systems, which informs risk mitigation strategies and governmental decision-making, thereby effectively reducing the risk of landslides.</div></div>","PeriodicalId":11567,"journal":{"name":"Engineering Geology","volume":"355 ","pages":"Article 108260"},"PeriodicalIF":8.4000,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Geology","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0013795225003564","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Regional-scale landslide early warning systems are commonly developed based on empirical rainfall thresholds. However, current rainfall threshold models overlook the significant spatial variations in slopes response to rainfall, thus undermining the accuracy of warnings. In this study, we improved a regional-scale landslide early warning method based on rainfall thresholds by accounting for the varying rainfall sensitivity of individual slope units. First, the Rainfall Sensitivity Index (RSI) for both dry and wet seasons are computed using a Graph Attention Network (GAN) model, incorporating ten influencing factors. Subsequently, an initial regional critical rainfall threshold was obtained based on the Effective cumulative rainfall – rainfall Duration (E-D). Finally, the improved rainfall thresholds for each slope units are derived by coupling the initial critical rainfall threshold and RSI. Using Pingyang County, Zhejiang Province, China as test site, the reliability and reasonableness of the proposed method was validated by statistical analysis, in-situ tests and historical rainfall events. The results reveal that the GAN demonstrates robust predictive capability in RSI assessment, achieving a precision of 0.88. Notably, slopes exhibit higher rainfall sensitivity during dry season compared to wet season. The early warning system employing improved critical thresholds shows significant improvement, with 11.9 % higher accuracy and 14.3 % fewer missed alarms relative to conventional methods. Overall, this study proposes a novel method for downscaling of regional-scale thresholds to slope-unit levels in landslide early warning systems, which informs risk mitigation strategies and governmental decision-making, thereby effectively reducing the risk of landslides.

查看原文本刊更多论文

利用人工智能量化坡面降雨敏感性，以细化区域滑坡降雨阈值

区域滑坡预警系统通常是基于经验降雨阈值来开发的。然而，目前的降雨阈值模型忽略了斜坡对降雨响应的显著空间变化，从而削弱了预警的准确性。在本研究中，我们改进了一种基于降雨阈值的区域尺度滑坡预警方法，该方法考虑了单个边坡单元降雨敏感性的变化。首先，利用图注意力网络（GAN）模型计算了旱季和雨季的降雨敏感性指数（RSI），并纳入了10个影响因素。随后，基于有效累积雨量-降雨持续时间（E-D），得到了初始区域临界降雨阈值。最后，将初始临界降雨阈值与RSI相结合，推导出各坡面单元的改进降雨阈值。以浙江省平阳县为试验点，通过统计分析、现场试验和历史降水事件验证了所提方法的可靠性和合理性。结果表明，GAN在RSI评估中表现出强大的预测能力，达到0.88的精度。值得注意的是，与雨季相比，旱季斜坡表现出更高的降雨敏感性。采用改进的临界阈值的预警系统显示出显著的改进，与传统方法相比，准确率提高11.9%，漏报率减少14.3%。总体而言，本研究提出了一种新的方法，将滑坡预警系统中的区域尺度阈值降至坡单元水平，从而为风险缓解策略和政府决策提供信息，从而有效降低滑坡风险。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Engineering Geology 地学-地球科学综合

CiteScore

13.70

自引率

12.20%

发文量

327

审稿时长

5.6 months

期刊介绍： Engineering Geology, an international interdisciplinary journal, serves as a bridge between earth sciences and engineering, focusing on geological and geotechnical engineering. It welcomes studies with relevance to engineering, environmental concerns, and safety, catering to engineering geologists with backgrounds in geology or civil/mining engineering. Topics include applied geomorphology, structural geology, geophysics, geochemistry, environmental geology, hydrogeology, land use planning, natural hazards, remote sensing, soil and rock mechanics, and applied geotechnical engineering. The journal provides a platform for research at the intersection of geology and engineering disciplines.