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

Abstract

Landslides are natural disasters deliberated as the most destructive among the others considered. Using the Muzaffarabad as a case study, this work compares the performance of three conventional Machine Learning (ML) techniques, namely Logistic Regression (LGR), Linear Regression (LR), Support Vector Machine (SVM), and two Multi-Criteria Decision Making (MCDM) techniques, namely Analytical Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for the susceptibility mapping of landslides. Most of these techniques have been used in the region of Northern Pakistan before for the same purpose. However, this study for landslide susceptibility assessment compares the performance of various techniques and provides additional insights into the factors used by adopting multicollinearity analysis. 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 SVM performs better than LGR and LR among ML models. 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 80% accuracy in Landslide Susceptibility Maps (LSMs) from ML techniques. The accuracy of the produced map from the AHP model is 80%, but for TOPSIS, it is less (78%). In disaster planning, the produced LSMs can significantly help the decision-makers, town planners, and local management take necessary measures to decrease the loss of life and assets.

Effects of riparian buffer and stream channel widths on ecological indicators in the upper and lower Indus River basins in Pakistan

“…The results of this study indicate that stream channel management by administrators should not comply with the same sustainable rules (Guo et al, 2021). It is also likely that some discrepancies in buffer activities are due to differences in land use and stream structure between the two jurisdictions (Khalil et al, 2022;Majeed et al, 2022;Monteiro et al, 2022). The UIB and LIB responses in the IRB differ considerably.…”

Rainfall in the Urban Area and Its Impact on Climatology and Population Growth

“…During the analyzed period, Aracaju had some rainy (dry) years, mainly between 1964 and 1968 (1961 to 1963 and 2004 to 2014). Among the years analyzed, 1983 (El Niño Strong) and 2016 (El Niño Very Strong) stand out with the lowest rainfall records [2,6,38], which recently have been called Mega-El Niño in the literature [42,43].…”

“…Northeastern Brazil (NEB) has a high spatiotemporal variability of rainfall, with a direct influence on various human activities, mainly in the agricultural sector, tourism, and industry, as well as on the dynamics and phytophysiognomy of existing biomes [1][2][3]. Due to its geographic location, several multiscale meteorological systems, from local to large scale, contribute to rainfall dynamics in the NEB [4][5][6].…”

Land subsidence analysis using synthetic aperture radar data

“…Some earlier methods [ [5] , [6] , [7] , [8] ] of measuring subsidence included a global positioning system (GPS), ground-based field observation data, repeated Geodetic Leveling Surveys, and ground and water sensors. However, these surveys are now considered costly and limited and present-day research relies on remote sending based Synthetic Aperture Radar (SAR) surveys for measuring subsidence [ 9 , 10 ]. Land subsidence was previously monitored through techniques such as point-based leveling, GPS, ground-based field observation data, repeated Geodetic Leveling Surveys (GLS), and ground and water sensors [ 9 , 11 , 12 ].…”

“…However, these surveys are now considered costly and limited and present-day research relies on remote sending based Synthetic Aperture Radar (SAR) surveys for measuring subsidence [ 9 , 10 ]. Land subsidence was previously monitored through techniques such as point-based leveling, GPS, ground-based field observation data, repeated Geodetic Leveling Surveys (GLS), and ground and water sensors [ 9 , 11 , 12 ]. However, these techniques are costly and outdated, and their data is not easily available in Pakistan.…”