Karst regions in southwest China are characterized by vulnerable ecological environment. Knowledge on the driving factors of vegetation cover change could provide valuable information for ecological restoration management. However, quantitative identifification of the key drivers for the vegetation restoration remains challenging in karst trough valleys. In this study, we used normalized difffference vegetation index (NDVI) time series (2000–2016), Theil-Sen median analysis, Mann-Kendall trend test, and Hurst exponent to analyze the vegetation cover trends in a karst trough valley. The performance of multiple linear regression (MLR), generalized additive models (GAM), support vector machine (SVM), and random forest (RF) in accounting for vegetation cover change were compared. The results showed that vegetation cover trends for increasing, stable and decreasing accounted for 71.44%, 28.16% and 0.40% of the study area, respectively. Lithology had a signifificant effffect on spatial patterns of temporal change and future sustainability in NDVI (p < .01). RF performed much better than MLR, GAM and SVM in accounting for vegetation cover change. The RF model had much lower fifitting error indices (MAE = 1.46*10−3 , RMSE = 1.92*10−3 ) and higher R2 (0.65) than MLR, GAM and SVM models. Thus, RF model was applied to identify impacts of driving factors on vegetation cover change quantitatively. Precipitation change, lithology and elevation were key factors for vegetation cover change. The vegetation restoration and reconstruction projects should pay more attention to the region where
limestone and above- 900 m elevation dominate, due to relatively slow vegetation growth in these regions. The new understandings obtained in this study enrich our knowledge of the effffects of lithology and topography on the vegetation cover
change and are necessary to guide sustainable projects of ecological recovery in karst trough valleys.