Comparison of Support Vector Machine, Bayesian Logistic Regression, and Alternating Decision Tree Algorithms for Shallow Landslide Susceptibility Mapping along a Mountainous Road in the West of Iran

• This paper aims to apply and compare the performance of the three machine learningalgorithms–support vector machine (SVM), bayesian logistic regression (BLR), and alternatingdecision tree (ADTree)–to map landslide susceptibility along the mountainous road of the SalavatAbad saddle, Kurdistan province, Iran. We identified 66 shallow landslide locations, based on fieldsurveys, by recording the locations of the landslides by a global position System (GPS), Google Earthimagery and black-and-white aerial photographs (scale 1: 20,000) and 19 landslide conditioningfactors, then tested these factors using the information gain ratio (IGR) technique. We checked thevalidity of the models using statistical metrics, including sensitivity, specificity, accuracy, kappa,root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC).We found that, although all three machine learning algorithms yielded excellent performance, theSVM algorithm (AUC=0.984) slightly outperformed the BLR (AUC=0.980), and ADTree (AUC=0.977) algorithms. We observed that not only all three algorithms are useful and effective tools foridentifying shallow landslide-prone areas but also the BLR algorithm can be used such as the SVMalgorithm as a soft computing benchmark algorithm to check the performance of the models in future.

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Samhällsbyggnadsteknik -- Geoteknik (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Civil Engineering -- Geotechnical Engineering (hsv//eng)

Nyckelord

shallow landslides

machine learning

goodness-of-fit

support vector machine

bayesian logistic regression

Kurdistan

Iran

Geoteknik

Soil Mechanics

Publikations- och innehållstyp

ref (ämneskategori)

art (ämneskategori)