Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

Abstract

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

Investigating causative factors and selecting optimal machine learning algorithms for landslide susceptibility assessment in Lom Kao area, northern Thailand

“…In addition, landslide susceptibility mapping techniques have been developed, including several methods: statistical, index-based, machine learning, or neural network. The machine learning technique is outstanding and accurate [9,10]. Therefore, it is important to (1) investigate the correlation between each of causative factors and detect the collinearity among the factors and (2) choose the appropriate machine learning algorithm in order to be used for landslide susceptibility modelling [7].…”

“…There are various mathematical techniques for establishing landslide susceptibility maps that could be classified into classical statistics, index-based, machine learning, multi-criteria, and neural network [8]. In recent years, the rapidly growing and outstanding machine learning techniques in landslide evaluation have assisted in determining landslide occurrence and assessing the susceptibility of landslides [9,10]. The supervised machine learning algorithms are extensively used in landslide susceptibility research [11].…”

A comprehensive review of machine learning‐based methods in landslide susceptibility mapping

“…Some of them also took deep learning models into consideration. Ado et al (2022) comprehensively discussed the recently developed hybrid, ensemble, and deep learning methods applied in landslide susceptibility assessment, and concluded that generally hybrid, ensemble, or deep learning models could overcome the limitations of conventional machine learning models, thus producing more accurate landslide susceptibility maps. Ma et al (2021) critically reviewed current machine learning models for landslide susceptibility investigation, and also suggested to explore the application of deep learning methods in future works.…”

Landslide susceptibility modeling and mapping at Dien Bien province, Vietnam using Bagging based MLP neural network

“…Popular ML models used for landslide susceptibility modeling are Support Vector Machines [7,8], Artificial Neural Networks -ANN [9,10], Decision Trees [11,12], and Random Forests -RF [13,14]. More recently, hybrid/ensemble models which are combinations of single ML models and different optimization techniques are considered as better tools compared with single ML models for landslide susceptibility modeling [15]. Lucchese, De Oliveira [16] developed and applied hybrid models of ANN and RF and Bagging ensemble for landslide susceptibility modeling at the Itajaí-Açu river valley, Brazil.…”