AUTHOR=Khalil Umer , Imtiaz Iqra , Aslam Bilal , Ullah Israr , Tariq Aqil , Qin Shujing 

TITLE=Comparative analysis of machine learning and multi-criteria decision making techniques for landslide susceptibility mapping of Muzaffarabad district

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.1028373

DOI=10.3389/fenvs.2022.1028373

ISSN=2296-665X

ABSTRACT=Landslide, a natural disaster that is deliberated as most destructive among the others considered. In disaster planning, landslide susceptibility maps (LSMs) can significantly help the decision-makers, town planners, and local management to take necessary measures for decreasing the fatalities of life and assets. Using the Muzaffarabad as a case study, this paper describes the new weight determining method based on Machine Learning (ML) techniques, namely Logistic Regression (LGR), Multiple Linear Regression (LR), Support Vector Machine (SVM), and as a comparison to Multi-Criteria Decision Making (MCDM) techniques, which are Analytical Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for the mapping of landslides. Landslide inducing factors considered in this research are lithology, slope, flow direction, fault lines, aspect, elevation, curvature, earthquakes, plan curvature, precipitation, profile curvature, Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), roads, and waterways. Results show that among ML models, SVM performs better than LGR and LR. On the other hand, the performance of AHP was better than TOPSIS. All the models rank slope, precipitation, elevation, lithology, NDWI, and flow direction as the top three most imperative landslide inducing factors. Results show an overall 80% accuracy in LSMs from ML techniques. The accuracy of the produced map from the AHP model is 80%, but for TOPSIS, it is less (78%). For landslide susceptibility assessment, this paper also provides a new weight determining method.