Gully erosion is a significant form of soil erosion and a major source of sediment in arid and semi-arid regions. Mining activities have severely exacerbated vegetation degradation and ground deformation in coalfields, potentially accelerating gully expansion. However, few studies have explored gully erosion susceptibility (GES) in coalfield areas. This study aims to investigate GES and its influencing environmental factors in the Wanli coalfield, China. Three hybrid models were established using Multi-Attributive Border Approximation area Comparison (MABAC), frequency ratio (FR), AdaBoost (AB), Extremely-Randomized Trees (ET), and Light Gradient Boosting Machine (LG). During the 2023 field survey, an Unmanned Aerial Vehicle (UAV) was used to create a digital ortho map (DOM) and a digital elevation model (DEM), from which 2,128 gullies were visually identified. A total of 14 environmental factors were utilized to generate the gully erosion susceptibility mapping (GESM), including six topographical factors, four hydrological factors, and four other factors. Three hybrid models-MABAC-FR-AB, MABAC-FR-ET, and MABAC-FR-LG-were selected to predict GES. Among these models, MABAC-FR-LG exhibited the best performance with an AUC of 0.996, followed by MABAC-FR-ET (AUC = 0.987) and MABAC-FR-AB (AUC = 0.976). Additionally, gully headcuts advancement rates (GHR) were calculated based on satellite imagery from 2012 and 2021 in 5 different GES areas to validate the accuracy of GESM. The GHR in very high GES area was 0.247 m yr-1, greater than those in high GES area (0.167 m yr-1), moderate GES area (0.141 m yr-1), low GES area (0.076 m yr-1), and very low GES area (0.036 m yr-1). Gullies with ground fissures exhibited higher GHR (0.213 m yr-1) than those without ground fissures (0.167 m yr-1). This study offers a novel perspective on preventing and controlling gully erosion in coalfields.