Performance Comparison of Landslide Susceptibility Maps Derived from Logistic Regression and Random Forest Models in the Bolaman Basin, Türkiye

Abstract

Landslides often cause significant economic and human losses, and therefore landslide susceptibility mapping (LSM) has become increasingly important. Accurate assessment of LSM is important for appropriate land use management and risk assessment. The aim of this study is to define and compare the results of applying the random forest (RF) and logistic regression (LR) models for estimating landslide susceptibility, and also to confirm the accuracy of the resulting susceptibility maps in the Ordu-Bolaman River micro-basin. The study area was selected because it is one of the most landslide-prone areas in Türkiye. First, a total of 231 landslide locations were identified. Then 12 landslide-influencing factors were selected to generate landslide susceptibility maps. These maps were produced using the landslide influencing factors based on the RF and LR models in a geographical information system (GIS) environment. Finally, area under the curve (AUC) analysis, sensitivity, specificity, and accuracy were considered to assess and compare the performance of the two models. In addition, the maps were retested with large landslides not included in the training and test data sets, using general accuracy criteria. The results of the present study will be helpful for future landslide risk mitigation efforts in the research area. Landslide susceptibility mapping is crucial in adequately mitigating hazards and provides guidelines for landslide-prone areas to avoid hazards in the future. Therefore, landslide susceptibility assessment is of the utmost significance to ensure the safety of human life, mitigate the negative impacts on the economy, and prevent landslide hazards. Government agencies, policymakers, local authorities, and urban planners can use landslide susceptibility maps to plan effective management strategies for landslide prevention and mitigation and to make informed decisions regarding land use zoning and development. By identifying areas with very high and high landslide susceptibility, constructing critical infrastructure and buildings in hazardous zones can be avoided, reducing the risk of damage and loss during potential landslide events. Furthermore, landslide susceptibility maps play a crucial role in disaster risk management and emergency response planning. Authorities can use these maps to prioritize areas for early warning systems, evacuation routes, and disaster response teams. Farmers and landowners can benefit from the maps by being made aware of landslide-prone areas on their property. In addition, insurance companies can use landslide susceptibility maps to assess the risk of landslides in certain regions and adjust their insurance policies accordingly. By implementing these practical applications, landslide susceptibility maps can have a significant impact on reducing the vulnerability of communities and infrastructure to landslides, ultimately contributing to safer and more resilient environments. Consequently, this study is an example of landslide susceptibility mapping efforts for an agriculturally important area.