Karst regions in southwest China are characterized by vulnerable ecological environ
ment. Knowledge on the driving factors of vegetation cover change could provide valuable infor
mation for ecological restoration
manage
ment. However, quantitative identifification of the key drivers for the vegetation restoration re
mains challenging in karst trough valleys. In this study, we used nor
malized difffference vegetation index (NDVI) ti
me 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 perfor
mance of
multiple linear regression (MLR), generalized additive
models (GAM), support vector
machine (SVM), and rando
m forest (RF) in accounting for vegetation cover change were co
mpared. 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 te
mporal change and future sustainability in NDVI (p < .01). RF perfor
med
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 i
mpacts 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 li
mestone and above- 900
m elevation do
minate, 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.