Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area
Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose a hybrid machine learning model based on a rotation forest (RoF) meta classifier and a random forest (RF) decision tree classifier called RoFRF for landslide predi...
Saved in:
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022
|
Subjects: | |
Online Access: | http://eprints.utm.my/104043/1/AnuarAhmad2022_ApplicationofaNovelHybridMachineLearning.pdf http://eprints.utm.my/104043/ http://dx.doi.org/10.3389/fenvs.2022.897254 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.104043 |
---|---|
record_format |
eprints |
spelling |
my.utm.1040432024-01-14T00:51:49Z http://eprints.utm.my/104043/ Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area Ghasemian, Bahareh Shahabi, Himan Shirzadi, Ataollah Al-Ansari, Nadhir Jaafari, Abolfazl Geertsema, Marten M. Melesse, Assefa K. Singh, Sushant Ahmad, Anuar G70.39-70.6 Remote sensing Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose a hybrid machine learning model based on a rotation forest (RoF) meta classifier and a random forest (RF) decision tree classifier called RoFRF for landslide prediction in a mountainous area near Kamyaran city, Kurdistan Province, Iran. We used 118 landslide locations and 25 conditioning factors from which their predictive usefulness was measured using the chi-square technique in a 10-fold cross-validation analysis. We used the sensitivity, specificity, accuracy, F1-measure, Kappa, and area under the receiver operating characteristic curve (AUC) to validate the performance of the proposed model compared to the Artificial Neural Network (ANN), Logistic Model Tree (LMT), Best First Tree (BFT), and RF models. The validation results demonstrated that the landslide susceptibility map produced by the hybrid model had the highest goodness-of-fit (AUC = 0.953) and higher prediction accuracy (AUC = 0.919) compared to the benchmark models. The hybrid RoFRF model proposed in this study can be used as a robust predictive model for landslide susceptibility mapping in the mountainous regions around the world. Frontiers Media S.A. 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/104043/1/AnuarAhmad2022_ApplicationofaNovelHybridMachineLearning.pdf Ghasemian, Bahareh and Shahabi, Himan and Shirzadi, Ataollah and Al-Ansari, Nadhir and Jaafari, Abolfazl and Geertsema, Marten and M. Melesse, Assefa and K. Singh, Sushant and Ahmad, Anuar (2022) Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area. Frontiers in Environmental Science, 10 (NA). pp. 1-14. ISSN 2296-665X http://dx.doi.org/10.3389/fenvs.2022.897254 DOI : 10.3389/fenvs.2022.897254 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
G70.39-70.6 Remote sensing |
spellingShingle |
G70.39-70.6 Remote sensing Ghasemian, Bahareh Shahabi, Himan Shirzadi, Ataollah Al-Ansari, Nadhir Jaafari, Abolfazl Geertsema, Marten M. Melesse, Assefa K. Singh, Sushant Ahmad, Anuar Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
description |
Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose a hybrid machine learning model based on a rotation forest (RoF) meta classifier and a random forest (RF) decision tree classifier called RoFRF for landslide prediction in a mountainous area near Kamyaran city, Kurdistan Province, Iran. We used 118 landslide locations and 25 conditioning factors from which their predictive usefulness was measured using the chi-square technique in a 10-fold cross-validation analysis. We used the sensitivity, specificity, accuracy, F1-measure, Kappa, and area under the receiver operating characteristic curve (AUC) to validate the performance of the proposed model compared to the Artificial Neural Network (ANN), Logistic Model Tree (LMT), Best First Tree (BFT), and RF models. The validation results demonstrated that the landslide susceptibility map produced by the hybrid model had the highest goodness-of-fit (AUC = 0.953) and higher prediction accuracy (AUC = 0.919) compared to the benchmark models. The hybrid RoFRF model proposed in this study can be used as a robust predictive model for landslide susceptibility mapping in the mountainous regions around the world. |
format |
Article |
author |
Ghasemian, Bahareh Shahabi, Himan Shirzadi, Ataollah Al-Ansari, Nadhir Jaafari, Abolfazl Geertsema, Marten M. Melesse, Assefa K. Singh, Sushant Ahmad, Anuar |
author_facet |
Ghasemian, Bahareh Shahabi, Himan Shirzadi, Ataollah Al-Ansari, Nadhir Jaafari, Abolfazl Geertsema, Marten M. Melesse, Assefa K. Singh, Sushant Ahmad, Anuar |
author_sort |
Ghasemian, Bahareh |
title |
Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
title_short |
Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
title_full |
Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
title_fullStr |
Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
title_full_unstemmed |
Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
title_sort |
application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area |
publisher |
Frontiers Media S.A. |
publishDate |
2022 |
url |
http://eprints.utm.my/104043/1/AnuarAhmad2022_ApplicationofaNovelHybridMachineLearning.pdf http://eprints.utm.my/104043/ http://dx.doi.org/10.3389/fenvs.2022.897254 |
_version_ |
1789424369958649856 |
score |
13.18916 |