|
Title
|
Application of a Novel Hybrid Machine Learning Algorithm in Shallow Landslide Susceptibility Mapping in a Mountainous Area
|
|
Type
|
JournalPaper
|
|
Keywords
|
landslide susceptibility, spatial modeling, rotation forest, random forest, decision tree, GIS, Iran
|
|
Abstract
|
Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose a hybrid machine learningmodel based on a rotation forest (RoF) meta classifier and a random forest (RF) decision tree classifier called RoFRF for landslide prediction in a mountainous area near Kamyaran city, Kurdistan Province, Iran. We used 118 landslide locations and 25 conditioning factors from which their predictive usefulness was measured using the chi-square technique in a 10-fold cross-validation analysis. We used the sensitivity, specificity, accuracy, F1-measure, Kappa, and area under the receiver operating characteristic curve (AUC) to validate the performance of the proposed model compared to the Artificial Neural Network (ANN), Logistic Model Tree (LMT), Best First Tree (BFT), and RF models. The validation results demonstrated that the landslide susceptibility map produced by the hybrid model had the highest goodness-of-fit (AUC = 0.953) and higher prediction accuracy (AUC = 0.919) compared to the benchmark models. The hybrid RoFRF model proposed in this study can be used as a robust predictive model for landslide susceptibility mapping in the mountainous regions around the world
|
|
Researchers
|
Anuar Ahmad (Not In First Six Researchers), Sushant K. Singh (Not In First Six Researchers), Assefa M.Melesse (Not In First Six Researchers), Marten Geertsema (Not In First Six Researchers), Abolfazl Jaafari (Fifth Researcher), Nadhir Al-Ansari (Fourth Researcher), Ataollah Shirzadi (Third Researcher), Himan Shahabi (Second Researcher), Bahare Qasemyan (First Researcher)
|