Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia

Landslides are a natural hazard which cause great losses of lives and properties. Landslide susceptibility analysis (LSA) is of great importance for landslide management and mitigation. This study mainly aims to improve the spatial prediction performance of LSA using machine learning techniques. Sin...

Full description

Saved in:

Bibliographic Details
Main Author:	Gao, Han
Format:	Thesis
Language:	English
Published:	2021
Subjects:	QA1 Mathematics (General)
Online Access:	http://eprints.usm.my/52694/1/GAO%20HAN%20-%20TESIS24.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.52694
record_format	uketd_dc
spelling	my-usm-ep.526942022-05-31T17:42:45Z Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia 2021-10 Gao, Han QA1 Mathematics (General) Landslides are a natural hazard which cause great losses of lives and properties. Landslide susceptibility analysis (LSA) is of great importance for landslide management and mitigation. This study mainly aims to improve the spatial prediction performance of LSA using machine learning techniques. Since landslide samples account for a small percentage in the raw data, selecting an optimal sample ratio before training machine learning models and increasing the landslide samples in an efficient way are the main research problems. On the one hand, three types of sample ratios are designed to increase the spatial prediction performance through comparative analysis. The equal ratio for datasets is found as the optimal ratio in LSA. Additionally, three oversampling methods, random oversampling technique (ROTE), synthetic minority oversampling technique (SMOTE) and self-creating oversampling technique (SCOTE), are applied to augment the landslide samples. A comparable result is obtained which indicates the efficiency of the augmented landslide samples. Finally, gradient boosting models are developed to integrate with SMOTE and SCOTE in LSA. The area under the curve (AUC) values are considered as the key metric for evaluating the models’ performance. The results show an enhancement in the performance with the highest AUC value of 0.9525. To summarise, the maps produced in this study can provide useful information for the local landslide management and mitigation. 2021-10 Thesis http://eprints.usm.my/52694/ http://eprints.usm.my/52694/1/GAO%20HAN%20-%20TESIS24.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Matematik
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QA1 Mathematics (General)
spellingShingle	QA1 Mathematics (General) Gao, Han Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
description	Landslides are a natural hazard which cause great losses of lives and properties. Landslide susceptibility analysis (LSA) is of great importance for landslide management and mitigation. This study mainly aims to improve the spatial prediction performance of LSA using machine learning techniques. Since landslide samples account for a small percentage in the raw data, selecting an optimal sample ratio before training machine learning models and increasing the landslide samples in an efficient way are the main research problems. On the one hand, three types of sample ratios are designed to increase the spatial prediction performance through comparative analysis. The equal ratio for datasets is found as the optimal ratio in LSA. Additionally, three oversampling methods, random oversampling technique (ROTE), synthetic minority oversampling technique (SMOTE) and self-creating oversampling technique (SCOTE), are applied to augment the landslide samples. A comparable result is obtained which indicates the efficiency of the augmented landslide samples. Finally, gradient boosting models are developed to integrate with SMOTE and SCOTE in LSA. The area under the curve (AUC) values are considered as the key metric for evaluating the models’ performance. The results show an enhancement in the performance with the highest AUC value of 0.9525. To summarise, the maps produced in this study can provide useful information for the local landslide management and mitigation.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Gao, Han
author_facet	Gao, Han
author_sort	Gao, Han
title	Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
title_short	Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
title_full	Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
title_fullStr	Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
title_full_unstemmed	Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia
title_sort	landslide susceptibility analysis using machine learning techniques in penang island, malaysia
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Sains Matematik
publishDate	2021
url	http://eprints.usm.my/52694/1/GAO%20HAN%20-%20TESIS24.pdf
_version_	1747822205209673728

Landslide Susceptibility Analysis Using Machine Learning Techniques In Penang Island, Malaysia

Similar Items