**Kaige Chi 1,2, Bo Pang 1,2,\*, Lizhuang Cui 1,2, Dingzhi Peng 1,2, Zhongfan Zhu 1,2, Gang Zhao 1,3 and Shulan Shi 1,2**


Received: 31 March 2020; Accepted: 13 May 2020; Published: 18 May 2020

**Abstract:** Vegetation coverage variation may influence watershed water balance and water resource availability. Yarlung Zangbo River, the longest river on the Tibetan Plateau, has high spatial heterogeneity in vegetation coverage and is the main freshwater resource of local residents and downstream countries. In this study, we proposed a model based on random forest (RF) to predict the Normalized Difference Vegetation Index (NDVI) of the Yarlung Zangbo River Basin and explore its relationship with climatic factors. High-resolution datasets of NDVI and monthly meteorological observation data from 2000 to 2015 were used to calibrate and validate the proposed model. The proposed model was then compared with artificial neural network and support vector machine models, and principal component analysis and partial correlation analysis were also used for predictor selection of artificial neural network and support vector machine models for comparative study. The results show that RF had the highest model efficiency among the compared models. The Nash–Sutcliffe coefficients of the proposed model in the calibration period and verification period were all higher than 0.8 for the five subzones; this indicated that the proposed model can successfully simulate the relationship between the NDVI and climatic factors. By using built-in variable importance evaluation, RF chose appropriate predictor combinations without principle component analysis or partial correlation analysis. Our research is valuable because it can be integrated into water resource management and elucidates ecological processes in Yarlung Zangbo River Basin.

**Keywords:** NDVI; Yarlung Zangbo River; machine learning model; random forest
