This research uses Machine Learning (ML) algorithms applied to various conditioning factors, including curvature, lithology, aspect, river density, soil, lineament density, river distance, elevation, Slope Length (LS), Land Use Land Cover (LULC), Standardized Precipitation Index (SPI), valley depth, profile curvature, slope, solar radiation, road density, road distance, lineament distance, precipitation, Topographic Wetness Index (TWI), plan curvature, and Normalized Difference Vegetation Index (NDVI), for modeling LD in Shaqlawa district, of Kurdistan Region of Iraq (KRI). The Information Gain Ratio (IGR) factor selection technique shows that each of the TWI, NDVI, lithology, slope, and LS has a value of 0.031, 0.029, 0.027, 0.023, and 0.02, respectively; they are shown as the most critical factor in the prediction of LD within Shaqlawa district. Some other important factors are LULC, aspect, solar radiation, river density, profile curvature, curvature, plan curvature, elevation, and valley depth; others like road distance, lineament distance, precipitation, road density, river distance, SPI, and lineament density have weak predictive ability and soil with IGR value 0.000 is not considered for training. It is crucial to understand how all these elements play together in managing LD effectively.
