Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China DOI Creative Commons

Yong Song,

Yingxu Song,

Chengnan Wang

et al.

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 20, 2024

This study aims to evaluate the effectiveness of various individual machine learning and their ensemble techniques such as Stacking, Voting Meta-learning in landslide susceptibility assessment taking Poyang, Jiangxi, China an example. Multi-source geo-environmental data including field surveys, Sentinel-2A/B satellite images, Digital Elevation Models (DEM), geological hydrological were utilized construct validate models. Results show that Stacking Classifier outperformed other models, achieving highest F1 Score 0.846 AUC (Area Under ROC Curve) 0.923, demonstrating its strong predictivity, followed by with 0.829 0.922. Among Multi-Layer Perceptron (MLP) performed best 0.828 0.904. Furthermore, explainable Artificial Intelligence (XAI) technique was applied better understand mechanism classifiers predicting it suggests a significant correlation between land use, distance fault, occurrences. In conclusion, hybrid models clear advantages over ones for risk zoning. The results may provide technical support disaster mitigation efforts future urban planning areas prone landslides Poyang.

Language: Английский

Assessment of the effects of characterization methods selection on the landslide susceptibility: a comparison between logistic regression (LR), naive bayes (NB) and radial basis function network (RBF Network) DOI
Hui Shang,

Lixiang Su,

Yang Liu

et al.

Bulletin of Engineering Geology and the Environment, Journal Year: 2025, Volume and Issue: 84(3)

Published: Feb. 15, 2025

Language: Английский

Citations

0
An improved information quantity method for non-landslide selection to enhance landslide susceptibility evaluation: a case study in Yongfeng, South China DOI
Shuhua Zhai, Yue Sun,

Jiantao Lei

et al.

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

Language: Английский

Citations

0
Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China DOI Creative Commons

Yong Song,

Yingxu Song,

Chengnan Wang

et al.

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 20, 2024

This study aims to evaluate the effectiveness of various individual machine learning and their ensemble techniques such as Stacking, Voting Meta-learning in landslide susceptibility assessment taking Poyang, Jiangxi, China an example. Multi-source geo-environmental data including field surveys, Sentinel-2A/B satellite images, Digital Elevation Models (DEM), geological hydrological were utilized construct validate models. Results show that Stacking Classifier outperformed other models, achieving highest F1 Score 0.846 AUC (Area Under ROC Curve) 0.923, demonstrating its strong predictivity, followed by with 0.829 0.922. Among Multi-Layer Perceptron (MLP) performed best 0.828 0.904. Furthermore, explainable Artificial Intelligence (XAI) technique was applied better understand mechanism classifiers predicting it suggests a significant correlation between land use, distance fault, occurrences. In conclusion, hybrid models clear advantages over ones for risk zoning. The results may provide technical support disaster mitigation efforts future urban planning areas prone landslides Poyang.

Language: Английский

Citations

2