A comparison among fuzzy multi-criteria decision making, bivariate, multivariate and machine learning models in landslide susceptibility mapping

Abstract

Landslides are dangerous events which threaten both human life and property. The study aims to analyze the landslide susceptibility (LS) in the Kysuca river basin, Slovakia. For this reason, previous landslide events were analyzed with 16 landslide conditioning factors. Landslide inventory was divided into training (70% of landslide locations) and validating dataset (30% of landslide locations). The heuristic approach of Fuzzy Decision Making Trial and Evaluation Laboratory (FDEMATEL)-Analytic Network Process (ANP) was applied first, followed by bivariate Frequency Ratio (FR), multivariate Logistic Regression (LR), Random Forest Classifier (RFC), Naïve Bayes Classifier (NBC) and Extreme Gradient Boosting (XGBoost), respectively. The results showed that 52.2%, 36.5%, 40.7%, 50.6%, 43.6% and 40.3% of the total basin area had very high to high LS corresponding to FDEMATEL-ANP, FR, LR, RFC, NBC and XGBoost model, respectively. The analysis revealed that RFC was the most accurate model (overall accuracy of 98.3% and AUC of 97.0%). Besides, the heuristic approach of FDEMATEL-ANP model (overall accuracy of 93.8% and AUC of 92.4%) had better prediction capability than bivariate FR (overall accuracy of 86.9% and AUC of 86.1%), multivariate LR (overall accuracy of 90.5% and AUC of 91.2%), machine learning NBC (overall accuracy of 76.3% and AUC of 90.9%) and even deep learning XGBoost (overall accuracy of 92.3% and AUC of 87.1%) models. The study revealed that the FDEMATEL-ANP outweighed the NBC and XGBoost ARTICLE HISTORY

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

“…Another study [91] used an RF classification model defined in Equation ( 12), trained on 700 landslide pixels.…”

Análise de Decisão Multicritério como Subsídio a Determinação de Áreas de Aptidão para Alcance de Objetivos em Parques Nacionais

“…Com o avanço tecnológico nas áreas de aquisição e processamento de dados, a avaliação desses impactos se torna cada vez mais complexa e integrada a múltiplos fatores e variáveis. O uso de modelos como o de decisão multicritério, multivariado e Machine Learning, se tornam cada vez mais comuns na avaliação da qualidade ambiental (Pham et al, 2021).…”

“…As ações e atividades geradoras de impacto se apresentam, na verdade, como critérios que podem ser manipulados, dimensionados e avaliados de forma individualizada ou coletiva, com o intuito de verificar a qualidade socioambiental dos ambientes ou a identificação de áreas prioritárias (Fanelli et al, 2021). Quando são realizados mapeamento e identificação de elementos como ameaças, características culturais e climáticas, fragmentação da vegetação, ou ainda a ausência de modelos de organização social, reunidos em um sistema de informação espacial, pode-se agrupar e estabelecer relações entre esses elementos (Saura et al, 2018;Pham et al, 2021;Fanelli et al, 2021). É possível determinar também quais elementos podem ter um peso maior ou menor para o alcance do objetivo.…”

Regional Landslide Hazard Assessment Using Extreme Value Analysis and a Probabilistic Physically Based Approach

“…Landslide susceptibility analyses are generally either statistically or physically based [3][4][5][6]. Statistical approaches acquire knowledge of susceptibility obtained through the statistical analysis of the relationship between landslide occurrences and various conditioning factors [5,[7][8][9][10][11][12][13]. However, when applied to a wide area, statistical analysis requires considerable data on both landslide distribution and conditioning factors.…”