Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment
We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 landslides compiled using Synthetic Aperture Radar Interferometry, Goog...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2020
|
Subjects: | |
Online Access: | http://eprints.utm.my/93344/1/BaharinAhmad2020_LandslideSusceptibilityMappingUsingMachine.pdf |
_version_ | 1796865603138486272 |
---|---|
author | Nhu, Viet Ha Mohammadi, Ayub Shahabi, Himan Ahmad, Baharin Al-Ansari, Nadhir Shirzadi, Ataollah Clague, John J. Jaafari, Abolfazl Chen, Wei Nguyen, Hoang |
author_facet | Nhu, Viet Ha Mohammadi, Ayub Shahabi, Himan Ahmad, Baharin Al-Ansari, Nadhir Shirzadi, Ataollah Clague, John J. Jaafari, Abolfazl Chen, Wei Nguyen, Hoang |
author_sort | Nhu, Viet Ha |
collection | ePrints |
description | We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 landslides compiled using Synthetic Aperture Radar Interferometry, Google Earth images, and field surveys, and 17 conditioning factors (slope, aspect, elevation, distance to road, distance to river, proximity to fault, road density, river density, normalized difference vegetation index, rainfall, land cover, lithology, soil types, curvature, profile curvature, stream power index, and topographic wetness index). We carried out the validation process using the area under the receiver operating characteristic curve (AUC) and several parametric and non-parametric performance metrics, including positive predictive value, negative predictive value, sensitivity, specificity, accuracy, root mean square error, and the Friedman and Wilcoxon sign rank tests. The AB model (AUC = 0.96) performed better than the ensemble ABADTree model (AUC = 0.94) and successfully outperformed the ADTree model (AUC = 0.59) in predicting landslide susceptibility. Our findings provide insights into the development of more efficient and accurate landslide predictive models that can be used by decision makers and landuse managers to mitigate landslide hazards. |
first_indexed | 2024-03-05T20:59:31Z |
format | Article |
id | utm.eprints-93344 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T20:59:31Z |
publishDate | 2020 |
publisher | MDPI |
record_format | dspace |
spelling | utm.eprints-933442021-11-19T03:30:12Z http://eprints.utm.my/93344/ Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment Nhu, Viet Ha Mohammadi, Ayub Shahabi, Himan Ahmad, Baharin Al-Ansari, Nadhir Shirzadi, Ataollah Clague, John J. Jaafari, Abolfazl Chen, Wei Nguyen, Hoang NA Architecture We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 landslides compiled using Synthetic Aperture Radar Interferometry, Google Earth images, and field surveys, and 17 conditioning factors (slope, aspect, elevation, distance to road, distance to river, proximity to fault, road density, river density, normalized difference vegetation index, rainfall, land cover, lithology, soil types, curvature, profile curvature, stream power index, and topographic wetness index). We carried out the validation process using the area under the receiver operating characteristic curve (AUC) and several parametric and non-parametric performance metrics, including positive predictive value, negative predictive value, sensitivity, specificity, accuracy, root mean square error, and the Friedman and Wilcoxon sign rank tests. The AB model (AUC = 0.96) performed better than the ensemble ABADTree model (AUC = 0.94) and successfully outperformed the ADTree model (AUC = 0.59) in predicting landslide susceptibility. Our findings provide insights into the development of more efficient and accurate landslide predictive models that can be used by decision makers and landuse managers to mitigate landslide hazards. MDPI 2020-07-02 Article PeerReviewed application/pdf en http://eprints.utm.my/93344/1/BaharinAhmad2020_LandslideSusceptibilityMappingUsingMachine.pdf Nhu, Viet Ha and Mohammadi, Ayub and Shahabi, Himan and Ahmad, Baharin and Al-Ansari, Nadhir and Shirzadi, Ataollah and Clague, John J. and Jaafari, Abolfazl and Chen, Wei and Nguyen, Hoang (2020) Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment. International Journal of Environmental Research and Public Health, 17 (14). pp. 1-23. ISSN 1661-7827 http://dx.doi.org/10.3390/ijerph17144933 DOI:10.3390/ijerph17144933 |
spellingShingle | NA Architecture Nhu, Viet Ha Mohammadi, Ayub Shahabi, Himan Ahmad, Baharin Al-Ansari, Nadhir Shirzadi, Ataollah Clague, John J. Jaafari, Abolfazl Chen, Wei Nguyen, Hoang Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title | Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title_full | Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title_fullStr | Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title_full_unstemmed | Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title_short | Landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
title_sort | landslide susceptibility mapping using machine learning algorithms and remote sensing data in a tropical environment |
topic | NA Architecture |
url | http://eprints.utm.my/93344/1/BaharinAhmad2020_LandslideSusceptibilityMappingUsingMachine.pdf |
work_keys_str_mv | AT nhuvietha landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT mohammadiayub landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT shahabihiman landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT ahmadbaharin landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT alansarinadhir landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT shirzadiataollah landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT claguejohnj landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT jaafariabolfazl landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT chenwei landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment AT nguyenhoang landslidesusceptibilitymappingusingmachinelearningalgorithmsandremotesensingdatainatropicalenvironment |