<p>Landslides are common geological hazards that not only&#160;affect the normal road traffic but also pose a great threat and damage to human&#160;lives&#160;and properties. This study aims to&#160;conduct such&#160;a hazard risk&#160;mapping&#160;using&#160;Random&#160;Forest Classification&#160;(RFC)&#160;approach taking Ruijin County in Jiangxi, China&#160;as an example. Multi-source data&#160;namely terrain&#160;(DEM, slope and aspect),&#160;precipitation, the normalized difference vegetation index (NDVI)&#160;representing vegetation condition and abundance, strata and their lithology, distance to roads, distance to rivers, distance to faults,&#160;thickness of weathering crust, soil type and&#160;texture, etc., were employed for this study. The non-numeric data such as geological strata, soil units, faults, were spatialized and assigned values in terms of their susceptibility to landslide. Similarly, linear features such as roads, rivers and faults were buffered with distances of 0-30, 30-60, 60-90 and 90-120 m and each buffer zone was assigned a susceptibility value of landslide, e.g., zones&#160;0-30,&#160;30-60, 60-90 and 90-120 of road buffers were assigned respectively 10, 7, 4, and 1, meaning that the closer to the road, the higher risk of landslide. In total, 16&#160;hazard&#160;factor&#160;layers were derived and converted into raster. 156 landslide&#160;hazards&#160;that have truly taken places (points) and been verified in field were used to create&#160;a&#160;training set (TS, 70% of total landslides)&#160;and a&#160;validation set (VS, 30%)&#160;by buffering-based rasterization&#160;procedure. A number of polygons were defined in places where landslide is unlikely to occur, e.g., water bodies, zero-slope plain, and urban areas. These polygons were added to the TS as non-risk area. Then, RFC&#160;was conducted to model&#160;the probability of landslide risk using these 16&#160;factor layers as predictors and TS for training. The obtained RF model was applied&#160;back to the 16 factor layers to predict&#160;the&#160;probability of landslide&#160;risk at each pixel&#160;in the&#160;whole county. The prediction map was checked against the VS and found that the Overall Accuracy&#160;and&#160;Kappa Coefficient are respectively 92.18% and 0.8432, and the landslide-prone areas are mainly distributed on two&#160;sides of the roads. The results reveal that extremely high-risk zones&#160;with a probability&#160;of&#160;more&#160;than 0.9&#160;take up 76.70&#160;km<sup>2</sup>&#160;in the county, and the distance to roads&#160;is the most important factor followed by precipitation among all factors causing&#160;landslides as road construction and housing development cut off slopes leading to instability of the weathered crust; and heavy rainfalls trigger the instability. Our study shows that the RFC prediction&#160;has high accuracy and in good consistency with field observation.</p>