Evaluating Landslide Susceptibility Using Sampling Methodology and Multiple Machine Learning Models

Song, Yongyan; Yang, Degang; Wu, Weicheng; Zhang, Xin; Zhou, Jie; Tian, Zhaoxu; Wang, C; Song, Yingxu

doi:10.3390/ijgi12050197

Cited by 16 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, the aim was not to control all variables but to maximize the available resources; therefore, the uncertainty regarding the number and type of variables was minimized by conducting a comprehensive analysis of the topographic variables in the models, including correlation, multicollinearity, and dimensional reduction using PCA. This approach allowed us to exclude variable correlations, reduce noise, and mitigate the risk of overfitting, thus improving the accuracy of the models [45,81]. Additionally, the WoE analysis was employed to identify causal relationships between instability factors and the distribution of MM.…”

Section: Discussionmentioning

confidence: 99%

A Comparative Study of Susceptibility and Hazard for Mass Movements Applying Quantitative Machine Learning Techniques—Case Study: Northern Lima Commonwealth, Peru

Badillo-Rivera,

Olcese,

Santiago

et al. 2024

Geosciences

View full text Add to dashboard Cite

This study addresses the importance of conducting mass movement susceptibility mapping and hazard assessment using quantitative techniques, including machine learning, in the Northern Lima Commonwealth (NLC). A previous exploration of the topographic variables revealed a high correlation and multicollinearity among some of them, which led to dimensionality reduction through a principal component analysis (PCA). Six susceptibility models were generated using weights of evidence, logistic regression, multilayer perceptron, support vector machine, random forest, and naive Bayes methods to produce quantitative susceptibility maps and assess the hazard associated with two scenarios: the first being El Niño phenomenon and the second being an earthquake exceeding 8.8 Mw. The main findings indicate that machine learning models exhibit excellent predictive performance for the presence and absence of mass movement events, as all models surpassed an AUC value of >0.9, with the random forest model standing out. In terms of hazard levels, in the event of an El Niño phenomenon or an earthquake exceeding 8.8 Mw, approximately 40% and 35% respectively, of the NLC area would be exposed to the highest hazard levels. The importance of integrating methodologies in mass movement susceptibility models is also emphasized; these methodologies include the correlation analysis, multicollinearity assessment, dimensionality reduction of variables, and coupling statistical models with machine learning models to improve the predictive accuracy of machine learning models. The findings of this research are expected to serve as a supportive tool for land managers in formulating effective disaster prevention and risk reduction strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparative Study of Susceptibility and Hazard for Mass Movements Applying Quantitative Machine Learning Techniques—Case Study: Northern Lima Commonwealth, Peru

Badillo-Rivera,

Olcese,

Santiago

et al. 2024

Geosciences

View full text Add to dashboard Cite

show abstract

“…Comparing the variables selected by the PCA with those in SET-3 shows substantial agreement. However, when comparing with those selected in [68], it is found that both algorithms use similar variables in their predictions as follows: lithology, earthquake intensity parameters, and curvature. These matches in variable selection highlight the importance of these factors in predicting co-seismic landslides.…”

Section: Validation and Comparison With Physical Methodologiesmentioning

confidence: 99%

“…Its objective is to obtain a new set of uncorrelated variables called "principal components", which capture the most information in terms of the variance of the original data. This technique is widely used in various fields [68] to perform tasks such as dimensionality reduction, data visualization, pattern detection, and exploration of the underlying structure in a set of variables.…”

Section: Model Evaluationmentioning

confidence: 99%

Comparison between Machine Learning and Physical Models Applied to the Evaluation of Co-Seismic Landslide Hazard

2023

View full text Add to dashboard Cite

A comparative methodology between advanced statistical tools and physical-based methods is carried out to ensure their reliability and objectivity for the evaluation of co-seismic landslide hazard maps. To do this, an inventory of landslides induced by the 2011 Lorca earthquake is used to highlight the usefulness of these methods to improve earthquake-induced landslide hazard analyses. Various statistical models, such as logistic regression, random forest, artificial neural network, and support vector machine, have been employed for co-seismic landslide susceptibility mapping. The results demonstrate that machine learning techniques using principal components (especially, artificial neural network and support vector machine) yield better results compared to other models. In particular, random forest shows poor results. Artificial neural network and support vector machine approaches are compared to the results of physical-based methods in the same area, suggesting that machine learning methods can provide better results for developing co-seismic landslide susceptibility maps. The application of different advanced statistical models shows the need for validation with an actual inventory of co-seismic landslides to ensure reliability and objectivity. In addition, statistical methods require a great amount of data. The results establish effective land planning and hazard management strategies in seismic areas to minimize the damage of future co-seismic landslides.

show abstract

“…Looking at the previous studies using ML algorithms, it is seen that some studies produced LSMs with a single ML algorithm [14][15][16][17], while some studies produced LSMs using multiple ML algorithms together [18][19][20] and compared their performances. In these studies, algorithms such as Support Vector Machines (SVM) [21,22], K-Nearest Neighbor (KNN) [23,24], Naïve Bayes (NB) [25,26], Artificial Neural Network (ANN) [27,28], Multilayer Perceptron (MLP) [7,29], Classification and Regression Tree (CART) [30,31], Random Forest (RF) [16,32], Adaptive Boosting (AdaBoost) [33,34], Gradient Boosting Machine (GBM) [28,35], Light Gradient Boosting Machine (LightGBM) [36,37], Natural Gradient Boosting (NGBoost) [3], Extreme Gradient Boosting (XGBoost) [17] and categorical boosting (CatBoost) [36,38] are frequently used. Algorithms such as RF, GBM, LightGBM, AdaBoost, NGBoost, CatBoost, and XGBoost that use ensemble methods such as bagging, stacking, or boosting are called tree-based ensemble learning algorithms [36,39].…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping: A Case Study in Rize, Turkey

Özalp

Akıncı

Zeybek

2023

Water

View full text Add to dashboard Cite

The Eastern Black Sea Region is regarded as the most prone to landslides in Turkey due to its geological, geographical, and climatic characteristics. Landslides in this region inflict both fatalities and significant economic damage. The main objective of this study was to create landslide susceptibility maps (LSMs) using tree-based ensemble learning algorithms for the Ardeşen and Fındıklı districts of Rize Province, which is the second-most-prone province in terms of landslides within the Eastern Black Sea Region, after Trabzon. In the study, Random Forest (RF), Gradient Boosting Machine (GBM), CatBoost, and Extreme Gradient Boosting (XGBoost) were used as tree-based machine learning algorithms. Thus, comparing the prediction performances of these algorithms was established as the second aim of the study. For this purpose, 14 conditioning factors were used to create LMSs. The conditioning factors are: lithology, altitude, land cover, aspect, slope, slope length and steepness factor (LS-factor), plan and profile curvatures, tree cover density, topographic position index, topographic wetness index, distance to drainage, distance to roads, and distance to faults. The total data set, which includes landslide and non-landslide pixels, was split into two parts: training data set (70%) and validation data set (30%). The area under the receiver operating characteristic curve (AUC-ROC) method was used to evaluate the prediction performances of the models. The AUC values showed that the CatBoost (AUC = 0.988) had the highest prediction performance, followed by XGBoost (AUC = 0.987), RF (AUC = 0.985), and GBM (ACU = 0.975) algorithms. Although the AUC values of the models were close to each other, the CatBoost performed slightly better than the other models. These results showed that especially CatBoost and XGBoost models can be used to reduce landslide damages in the study area.

show abstract

Evaluating Landslide Susceptibility Using Sampling Methodology and Multiple Machine Learning Models

Cited by 16 publications

References 53 publications

A Comparative Study of Susceptibility and Hazard for Mass Movements Applying Quantitative Machine Learning Techniques—Case Study: Northern Lima Commonwealth, Peru

A Comparative Study of Susceptibility and Hazard for Mass Movements Applying Quantitative Machine Learning Techniques—Case Study: Northern Lima Commonwealth, Peru

Comparison between Machine Learning and Physical Models Applied to the Evaluation of Co-Seismic Landslide Hazard

Comparative Analysis of Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping: A Case Study in Rize, Turkey

Contact Info

Product

Resources

About