Cover Image

A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area

Landslide susceptibility maps (LSMs) are very crucial for planning policies in hazardous areas. However, the accuracy and reliability of LSMs depend on available data and the selection of suitable methods. This study is conducted to produce LSMs by combinations of machine learning methods and weight...

Full description

Saved in:
Bibliographic Details
Main Authors: Thanh, Trinh, Binh Thanh, Luu, Trang Ha Thi, Le
Format: Bài trích
Language:English
Published: Taylor & Francis Group 2022
Subjects:
Landslide
Logistic regression
Online Access:https://www.tandfonline.com/doi/full/10.1080/20964471.2022.2043520
https://dlib.phenikaa-uni.edu.vn/handle/PNK/5901
https://doi.org/10.1080/20964471.2022.2043520
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-5901
record_format dspace
spelling oai:localhost:PNK-59012022-08-17T05:54:55Z A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area Thanh, Trinh Binh Thanh, Luu Trang Ha Thi, Le Landslide Logistic regression Landslide susceptibility maps (LSMs) are very crucial for planning policies in hazardous areas. However, the accuracy and reliability of LSMs depend on available data and the selection of suitable methods. This study is conducted to produce LSMs by combinations of machine learning methods and weighting techniques for Ha Giang province, Vietnam, where has limited data. In study area, we gather 11 landslide conditioning factors and establish a landslide inventory map. Computing the weights of classes (or factors) is very important to prepare data for machine learning methods to generate LSMs. We first use frequency ratio (FR) and analytic hierarchy process (AHP) techniques to generate the weights. Then, random forest (RF), support vector machine (SVM), logistic regression (LR), and AHP methods are combined with FR and AHP weights to yield accurate and reliable LSMs. Finally, the performance of these methods is evaluated by five statistical metrics, ROC and R-index. The empirical results have shown that RF is the best method in terms of R-index and the five metrics, i.e. TP rate (0.9661), FP rate (0.0), ACC (0.9835), MAE (0.0046), and RMSE (0.0350) for this study area. This study opens the perspective of weight-based machine learning methods for landslide susceptibility mapping 2022-07-13T01:59:51Z 2022-07-13T01:59:51Z 2022 Bài trích https://www.tandfonline.com/doi/full/10.1080/20964471.2022.2043520 https://dlib.phenikaa-uni.edu.vn/handle/PNK/5901 https://doi.org/10.1080/20964471.2022.2043520 en Taylor & Francis Group
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic Landslide
Logistic regression
spellingShingle Landslide
Logistic regression
Thanh, Trinh
Binh Thanh, Luu
Trang Ha Thi, Le
A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
description Landslide susceptibility maps (LSMs) are very crucial for planning policies in hazardous areas. However, the accuracy and reliability of LSMs depend on available data and the selection of suitable methods. This study is conducted to produce LSMs by combinations of machine learning methods and weighting techniques for Ha Giang province, Vietnam, where has limited data. In study area, we gather 11 landslide conditioning factors and establish a landslide inventory map. Computing the weights of classes (or factors) is very important to prepare data for machine learning methods to generate LSMs. We first use frequency ratio (FR) and analytic hierarchy process (AHP) techniques to generate the weights. Then, random forest (RF), support vector machine (SVM), logistic regression (LR), and AHP methods are combined with FR and AHP weights to yield accurate and reliable LSMs. Finally, the performance of these methods is evaluated by five statistical metrics, ROC and R-index. The empirical results have shown that RF is the best method in terms of R-index and the five metrics, i.e. TP rate (0.9661), FP rate (0.0), ACC (0.9835), MAE (0.0046), and RMSE (0.0350) for this study area. This study opens the perspective of weight-based machine learning methods for landslide susceptibility mapping
format Bài trích
author Thanh, Trinh
Binh Thanh, Luu
Trang Ha Thi, Le
author_facet Thanh, Trinh
Binh Thanh, Luu
Trang Ha Thi, Le
author_sort Thanh, Trinh
title A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
title_short A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
title_full A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
title_fullStr A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
title_full_unstemmed A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area
title_sort comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in ha giang area
publisher Taylor & Francis Group
publishDate 2022
url https://www.tandfonline.com/doi/full/10.1080/20964471.2022.2043520
https://dlib.phenikaa-uni.edu.vn/handle/PNK/5901
https://doi.org/10.1080/20964471.2022.2043520
_version_ 1751856287110397952
score 8.891145

Similar Items