Understanding of the influence of factors on vegetation changes in different is still largely unknown. We have applied the Geographic Detector, a new spatial statistical method to study the interactive effects of factors on the spatial patterns of normalized vegetation index (NDVI) changes and determine the optimal characteristics of key impact factors that are beneficial to vegetation growth. Our results show that the vegetation cover from 2000 to 2015 for the upper reaches of the Minjiang River, western China was in good condition, the areas of 0.6<NDVI>0.8 and NDVI>0.8 accounted for more than 80%, and the spatial-temporal changes of vegetation cover were significant. The changes of vegetation cover were showed a significant transformation in the regions of NDVI>0.6. Our study uniquely illustrated that the elevation, annual average temperature and soil type can relatively well explain the vegetation changes. We propose that there are interactive effects between impact factors on vegetation NDVI, and the synergistic effects of the impact factors show mutual enhancement and nonlinear enhancement. The interactions between impact factors significantly enhance the impact of a single factor on vegetation changes. The most suitable characteristics of the main impact factors that promote the vegetation growth revealed help a better understanding of the impact of factors on NDVI and its driving mechanisms. Our findings suggest that the determined a favourable value range or the most suitable characteristics of impact factors help to intervene and promote vegetation change for vegetation restoration and alleviate environmental degradation.