Chin J Plant Ecol ›› 2020, Vol. 44 ›› Issue (11): 1113-1126.DOI: 10.17521/cjpe.2020.0111

• Research Articles • Previous Articles     Next Articles

Analysis of vegetation index changes and driving forces in inland arid areas based on random forest model: a case study of the middle part of northern slope of the north Tianshan Mountains

ZHANG Wen-Qiang1,2, LUO Ge-Ping1,2,3,*(), ZHENG Hong-Wei1,2, WANG Hao4, HAMDI Rafiq1,5,6, HE Hui-Li1,2, CAI Peng1,2, CHEN Chun-Bo1,2   

  1. 1State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, ürümqi 830011, China
    2University of Chinese Academy of Sciences, Beijing 100049, China
    3Central Asian Center for Ecology and Environmental Research, Chinese Academy of Sciences, ürümqi 830011, China
    4School of Environment, Beijing Normal University, Beijing 100875, China
    5Royal Meteorological Institute, Brussels 1180, Belgium
    6Department of Physics and Astronomy, Ghent University, Ghent 9000, Belgium
  • Received:2020-04-20 Accepted:2020-06-02 Online:2020-11-20 Published:2020-07-07
  • Contact: LUO Ge-Ping
  • Supported by:
    National Natural Science Foundation of China(41671108);International Partnership Program of Chinese Academy of Sciences(131965KYSB20160004)


Aims In the context of global change, vegetation changes in arid areas in the context of global change are both affected by climate change and human activities. Quantifying the vegetation dynamics and their driving mechanism are essential for monitoring the ecological environment change in arid areas and for promoting the sustainable development. Because of the complexity of human activities, most researches are limited to the response of normalized differential vegetation index (NDVI) to climate change, while the impacts of human activities have not yet been comprehensively considered.
Methods Firstly, we proposed a quantification method to quantify the main human activities related to land use. Then, the contribution of climate change and human activities to the NDVI in the middle part of the northern slope of the north Tianshan Mountains was analyzed using the multiple linear regression model and random forest model.
Important findings We found that an overall upward trend was evident in NDVI variations from 2000 to 2015. The fitting accuracy of NDVI based on the random forest model was significantly better than the multiple linear regression model with an improved R2 of about 24%. The contribution of human activities related to arable land to NDVI change in the study area showed an increasing trend which was greater than climatic factors from 2000 to 2015. This study provides new insight into the effects of climate change and human activities on vegetation and a scientific basis for the protection and restoration of the ecological environment in the arid areas.

Key words: NDVI, climate change, human activities, random forest model, the middle part of northern slope of the north Tianshan Mountains