Landslides occur when soil, rock, and debris break apart and move downhill due to gravity. These events are commonly observed in steep-slope regions and are mainly triggered by heavy and prolonged rainfall that saturates the soil. Factors such as population growth, urban expansion, and the presence of economically vulnerable communities contribute to the occupation of high-risk areas, increasing both the likelihood and destructive impact of landslides. This study aims to assess landslide susceptibility in Coonoor taluk, using a GIS-based approach and the Random Forest machine learning algorithm. In this study area is covers an area of around 230.44 sq.km and the research integrates historical landslide data with nine geo-environmental factors such as elevation, slope, aspect, precipitation, land use/land cover, drainage density, lineament density, and soil texture. These factors were compiled and analysed using Google Earth Engine to develop a Landslide Susceptibility Map consisting five classes of susceptible zones. The moderate class has the largest area, covering 53.45 units or 23.21% of the total area. The high class covers 41.45 units, making up 18.23% of the area, while the very high class covers the smallest area of 36.03 units or 15.43%. Villages with minimal landslide risk include Kolakombai and parts of Mellur Hosatty (green). Low-risk zones (light green) cover areas like Athigaratty and Bellada. Moderate-risk areas (yellow) include Nadhuhatty and Wellington. High-risk zones (orange) are seen in Ketti Palada and Bedford, while very highrisk areas (red) are around Yellanalli, Marapalam, and Burliyar. The landslide inventory dataset was split into training (70%) and testing (30%) sets, analyzed using the Random Forest algorithm for prediction. The model’s performance, assessed via the ROC curve, achieved an AUC of 0.859, indicating high accuracy. Results show landslides are linked to steep slopes, high drainage density, and specific land use patterns. These insights aid in identifying high-risk zones, improving disaster prevention and resource allocation.