MACHINE LEARNING ALGORITHM USED FOR DEVELOPMENT OF FORECASTING LANDSLIDE SUSCEPTIBILITY

The machine learning algorithms commonly used in the development of landslide susceptibility models. The study begins by highlighting the significance of landslide susceptibility forecasting and the challenges associated with traditional methods. Various algorithms, including logistic regression, decision trees, random forest, support vector machines, artificial neural networks, and gradient boosting algorithms, are discussed in detail. It highlights the significance of evaluating the performance of the models using appropriate metrics and discusses the need for validation and uncertainty analysis. Case studies and research findings from the literature are presented to demonstrate the application of these algorithms in real-world landslide susceptibility mapping. This paper provides a comprehensive overview of machine learning algorithms used for developing landslide susceptibility management, highlighting the potential of machine learning techniques in enhancing our understanding and prediction of landslide susceptibility