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: Trinh, Thanh, Luu, Thanh Binh, Le, Thi Trang Ha, Nguyen, Huy Duong, Tran, Van Trong, Nguyen, Thi Hai Van, Nguyen, Khanh Quoc, Nguyen Thi Lien
Format: Bài trích
Language:English
Published: Taylor & Francis 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/5758
https://doi.org/10.1080/20964471.2022.2043520
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-5758
record_format dspace
spelling oai:localhost:PNK-57582022-08-17T05:54:53Z A comparative analysis of weight-based machine learning methods for landslide susceptibility mapping in Ha Giang area Trinh, Thanh Luu, Thanh Binh Le, Thi Trang Ha Nguyen, Huy Duong Tran, Van Trong Nguyen, Thi Hai Van Nguyen, Khanh Quoc Nguyen Thi Lien 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. 2022-05-05T07:26:19Z 2022-05-05T07:26:19Z 2022 Bài trích https://www.tandfonline.com/doi/full/10.1080/20964471.2022.2043520 https://dlib.phenikaa-uni.edu.vn/handle/PNK/5758 https://doi.org/10.1080/20964471.2022.2043520 en Taylor & Francis
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic Landslide
Logistic regression
spellingShingle Landslide
Logistic regression
Trinh, Thanh
Luu, Thanh Binh
Le, Thi Trang Ha
Nguyen, Huy Duong
Tran, Van Trong
Nguyen, Thi Hai Van
Nguyen, Khanh Quoc
Nguyen Thi Lien
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 Trinh, Thanh
Luu, Thanh Binh
Le, Thi Trang Ha
Nguyen, Huy Duong
Tran, Van Trong
Nguyen, Thi Hai Van
Nguyen, Khanh Quoc
Nguyen Thi Lien
author_facet Trinh, Thanh
Luu, Thanh Binh
Le, Thi Trang Ha
Nguyen, Huy Duong
Tran, Van Trong
Nguyen, Thi Hai Van
Nguyen, Khanh Quoc
Nguyen Thi Lien
author_sort Trinh, Thanh
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
publishDate 2022
url https://www.tandfonline.com/doi/full/10.1080/20964471.2022.2043520
https://dlib.phenikaa-uni.edu.vn/handle/PNK/5758
https://doi.org/10.1080/20964471.2022.2043520
_version_ 1751856281620054016
score 8.891787

Similar Items