Landslide Prediction Validation in Western North Carolina After Hurricane Helene DOI Creative Commons
Sophia Lin, Shen-En Chen, Ryan A. Rasanen

и другие.

Geotechnics, Год журнала: 2024, Номер 4(4), С. 1259 - 1281

Опубликована: Дек. 14, 2024

Hurricane Helene triggered 1792 landslides across western North Carolina and has caused damage to 79 bridges date. hit days after a low-pressure system dropped up 254 mm of rain in some locations (e.g., Asheville Regional Airport). The already waterlogged region experienced devastation as significant additional rainfall occurred during Helene, where areas, like Asheville, received an 356 (National Weather Service, 2024). In this study, machine learning (ML)-generated multi-hazard landslide susceptibility maps are compared the documented from Helene. models use database, soil survey, rainfall, USGS digital elevation model (DEM), distance rivers create variables. From DEM, aspect factors slope computed. Because recent research suggests fault movement is destabilizing slopes, was also incorporated predictor variable. Finally, types were used wildfire total, 4794 for training. Random Forest logistic regression algorithms develop map. Furthermore, examined with without consideration wildfires. Ultimately, study indicates heavy debris-laden floodwaters critical triggering both scour, posing dual threat bridge stability. Field investigations revealed that concentrated at abutments, scour sediment deposition exacerbating structural vulnerability. We evaluated assumed flooding potential (AFP) damaged area, finding lower AFP values particularly vulnerable submersion flood events. Differentiating between landslide-induced scour-induced essential accurately assessing risks infrastructure. findings emphasize importance comprehensive hazard mapping guide infrastructure resilience planning mountainous regions.

Язык: Английский

Landslide susceptibility assessment using information quantity and machine learning integrated models: a case study of Sichuan province, southwestern China DOI

Pengtao Zhao,

Ying Wang, Yi Xie

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Янв. 18, 2025

Язык: Английский

Процитировано

4
Hybrid catboost models optimized with metaheuristics for predicting shear strength in rock joints DOI
Xiaohua Ding, Mahdi Hasanipanah, Mohammad Matin Rouhani

и другие.

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(3)

Опубликована: Фев. 25, 2025

Язык: Английский

Процитировано

2
Optimizing landslide susceptibility mapping using integrated forest by penalizing attributes model with ensemble algorithms DOI
Wei Chen, Chao Wang, Xia Zhao

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
High-precision landslide susceptibility assessment based on the coupling of IHAOAVOA algorithm and BP neural network DOI

Siyu Liang,

Li Li, Yue Qiang

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Evolution of landslide susceptibility in the Three Gorges Reservoir area over the three decades from 1991 to 2020 DOI Creative Commons
Jiahui Dong,

Jinrong Duan,

Runqing Ye

и другие.

Geomatics Natural Hazards and Risk, Год журнала: 2025, Номер 16(1)

Опубликована: Фев. 25, 2025

Язык: Английский

Процитировано

0
Rainfall-Induced Geological Hazard Susceptibility Assessment in the Henan Section of the Yellow River Basin: Multi-Model Approaches Supporting Disaster Mitigation and Sustainable Development DOI Open Access

Y. Zhang,

Hui Ci, Hui Yang

и другие.

Sustainability, Год журнала: 2025, Номер 17(10), С. 4348 - 4348

Опубликована: Май 11, 2025

The Henan section of the Yellow River Basin (3.62 × 104 km2, 21.7% Province), a vital agro-industrial and politico-economic hub, faces frequent rainfall-induced geohazards. 2021 “7·20” Zhengzhou disaster, causing 398 fatalities CNY 120.06 billion loss, highlights its vulnerability to extreme weather. While machine learning (ML) aids geohazard assessment, geological hazard susceptibility assessment (RGHSA) remains understudied, with single ML models lacking interpretability precision for complex disaster data. This study presents hybrid framework (IVM-ML) that integrates Information Value Model (IVM) ML. uses historical data 11 factors (e.g., rainfall erosivity, relief amplitude) calculate information values construct prediction model these quantitative results. By combining IVM’s spatial analysis ML’s predictive power, it addresses limitations conventional models. ROC curve validation shows Random Forest (RF) in IVM-ML achieves highest accuracy (AUC = 0.9599), outperforming standalone IVM 0.7624). All exhibit AUC exceeding 0.75, demonstrating strong capability capturing rainfall–hazard relationships reliable performance. Findings support RGHSA practices mid-Yellow urban cluster, offering insights sustainable risk management, land-use planning, climate resilience. Bridging geoscience data-driven methods, this advances global sustainability goals reduction environmental security vulnerable riverine regions.

Язык: Английский

Процитировано

0
Optimizing the Application of Machine Learning Models in Predicting Landslide Susceptibility Using the Information Value Model in Junlian County of Sichuan Basin DOI
Lijun Qian,

Lihua Ou,

Guoxin Li

и другие.

Advances in Space Research, Год журнала: 2025, Номер unknown

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Landslide Prediction Validation in Western North Carolina After Hurricane Helene DOI Creative Commons
Sophia Lin, Shen-En Chen, Ryan A. Rasanen

и другие.

Geotechnics, Год журнала: 2024, Номер 4(4), С. 1259 - 1281

Опубликована: Дек. 14, 2024

Hurricane Helene triggered 1792 landslides across western North Carolina and has caused damage to 79 bridges date. hit days after a low-pressure system dropped up 254 mm of rain in some locations (e.g., Asheville Regional Airport). The already waterlogged region experienced devastation as significant additional rainfall occurred during Helene, where areas, like Asheville, received an 356 (National Weather Service, 2024). In this study, machine learning (ML)-generated multi-hazard landslide susceptibility maps are compared the documented from Helene. models use database, soil survey, rainfall, USGS digital elevation model (DEM), distance rivers create variables. From DEM, aspect factors slope computed. Because recent research suggests fault movement is destabilizing slopes, was also incorporated predictor variable. Finally, types were used wildfire total, 4794 for training. Random Forest logistic regression algorithms develop map. Furthermore, examined with without consideration wildfires. Ultimately, study indicates heavy debris-laden floodwaters critical triggering both scour, posing dual threat bridge stability. Field investigations revealed that concentrated at abutments, scour sediment deposition exacerbating structural vulnerability. We evaluated assumed flooding potential (AFP) damaged area, finding lower AFP values particularly vulnerable submersion flood events. Differentiating between landslide-induced scour-induced essential accurately assessing risks infrastructure. findings emphasize importance comprehensive hazard mapping guide infrastructure resilience planning mountainous regions.

Язык: Английский

Процитировано

1