<p>Landslide Susceptibility Zonation (LSZ) is essential for comprehending and predicting landslide events, especially in areas prone to natural hazards. This study assesses and contrasts the efficacy of two machine learning (ML) algorithm, Random Forest (RF) and Support Vector Machine (SVM), in producing high resolution LSZ maps for the Wayanad area in Kerala, India. The region is significantly susceptible to landslides, as evident by a disastrous occurrence on July 30, 2024, which led to more than 300 deaths and impacted almost 5,000 individuals. LSZ map was created using twelve landslide conditioning factors (LCFs) at a spatial resolution of 12.5 × 12.5&#xa0;m. The evaluation of multicollinearity confirmed the independence of the explanatory factors. The model training utilized a balanced dataset consisting of 314 landslide and 314 non-landslide sites. The RF model revealed high susceptibility zones including 23.8% of the study region, while the SVM model recognized 19.5%. These zones are primarily located along the southwestern, western, and northwestern boundaries of Wayanad. The predictive capacities of the models, assessed using Receiver Operating Characteristic (ROC) analysis, demonstrated accuracies of 95.8% for RF and 93.5% for SVM, reflecting the strong performance of both techniques. The findings highlight the efficacy of ML algorithm, particularly RF, in LSZ, offering critical insights for hazard mitigation and land-use planning in comparable geologically vulnerable areas.</p> Graphical Abstract <p>This research offers a machine learning-driven evaluation of landslide vulnerability in the Wayanad District of Kerala, India. The graphical abstract depicts the cohesive workflow employed for model generation and spatial analysis. The approach commences with a comprehensive assessment of the study area, encompassing the delineated landslide inventory and the methodological framework employed during the analysis. Essential factors influencing landslides namely altitude, slope, aspect, curvature, topographic wetness index (TWI), stream power index (SPI), lithology, land use/land cover, geomorphon, and proximity to drainage, roads, and faults were identified through an extensive literature review and multicollinearity analysis. These variables were essential inputs for model training. Two prevalent and resilient machine learning methods, Random Forest (RF) and Support Vector Machine (SVM), were utilized to produce landslide susceptibility maps. The resultant spatial classifications were examined to ascertain the percentage of land area within each susceptibility category. The research indicated that high-susceptibility zones include 19.5% of the district according to RF and 23.8% according to SVM, predominantly situated in the southwestern and northern parts. Validation measures indicated exceptional precision, with the RF and SVM models attaining accuracies of 95.8% and 93.5%, respectively. Mananthavady Tehsil is identified as the area most susceptible to landslides. Furthermore, three previously unidentified high-risk areas were detected, which may have downstream effects. These findings underscore the efficacy of machine learning methodologies in enhancing early warning systems, regional risk mitigation measures, and policy-driven land-use planning in intricate mountainous landscapes.</p>