Quantitative contribution of climate change and human activities to vegetation cover variations based on GA-SVM model

Vegetation cover is a frequently used indicator for assessing terrestrial ecosystem conditions. It is important to investigate the spatial and temporal change patterns of vegetation cover, and quantify the effects of climate change and human activities on vegetation cover dynamics. In this study, the cross wavelet analysis was first applied to reveal the detailed associations between the Normalized Difference Vegetation Index (NDVI) and precipitation/air temperature, as well as their evolution characteristics. Then, a Support Vector Machine (SVM)based simulation model was introduced to quantify the effects of climate change and human activities on vegetation cover dynamics. Results indicated that: (1) the proposed GA-SVM model is reliable in reproducing the observed NDVI series; (2) the increasing trend of annual NDVI was primarily contributed by the increase in spring and autumn, during which precipitation and air temperature changes lead to the lengthening of vegetation growing season; (3) for the Wei River Basin as a whole, climate change effects (about 59.3%) on NDVI are stronger than those by human activities (nearly 40.7%), whereas human activities including the large-scale "Grain for Green" Program are exerting the dominant influences in the Beiluo River Basin. The findings of this study are helpful for guiding the ecological restoration practices in the Loess Plateau under the backdrop of changing environment.