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

doi:10.17521/cjpe.2020.0111

Abstract

Abstract:

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

ZHANG Wen-Qiang, LUO Ge-Ping, ZHENG Hong-Wei, WANG Hao, HAMDI Rafiq, HE Hui-Li, CAI Peng, CHEN Chun-Bo. 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[J]. Chin J Plant Ecol, 2020, 44(11): 1113-1126.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.plant-ecology.com/EN/10.17521/cjpe.2020.0111

https://www.plant-ecology.com/EN/Y2020/V44/I11/1113

Figures/Tables 16

References 32

[1]	Belgiu M, Drăguţ L (2016). Random Forest in Remote Sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31.
[2]	Breiman L (2001). Random forests. Machine Learning, 45, 5-32.
[3]	Cai P, Hamdi R, Luo GP, He HL, Zhang M, Termonia P, de Maeyer P (2019). Agriculture intensification increases summer precipitation in Tianshan Mountains, China. Atmospheric Research, 227, 140-146.
[4]	Chen X, Luo GP, Xia J, Zhou KF, Lou SP, Ye MQ (2004). Ecological response of climate change on the northern slope of Tianshan Mountains in Xinjiang. Science in China Series D, 34, 1166-1175.
	[ 陈曦, 罗格平, 夏军, 周可法, 娄少平, 叶民权 (2004). 新疆天山北坡气候变化的生态响应研究. 中国科学D辑, 34, 1166-1175.]
[5]	Fang XR, Wen ZF, Chen JL, Wu SJ, Huang YY, Ma MH (2019). Remote sensing estimation of suspended sediment concentration based on Random Forest Regression Model. Journal of Remote Sensing, 23, 756-772.
	[ 方馨蕊, 温兆飞, 陈吉龙, 吴胜军, 黄远洋, 马茂华 (2019). 随机森林回归模型的悬浮泥沙浓度遥感估算. 遥感学报, 23, 756-772.]
[6]	Gang C, Zhou W, Wang Z, Chen Y, Li J, Chen J, Qi J, Odeh I, Groisman PY (2015). Comparative assessment of grassland NPP dynamics in response to climate change in China, North America, Europe and Australia from 1981 to 2010. Journal of Agronomy and Crop Science, 201, 57-68. DOI URL
[7]	Gao JB, Jiao KW, Wu SH (2019). Revealing the climatic impacts on spatial heterogeneity of NDVI in China during 1982-2013. Acta Geographica Sinica, 74, 534-543. DOI URL
	[ 高江波, 焦珂伟, 吴绍洪 (2019). 1982-2013年中国植被NDVI空间异质性的气候影响分析. 地理学报, 74, 534-543.]
[8]	Gilbert M, Nicolas G, Cinardi G, van Boeckel TP, Vanwambeke SO, Wint GRW, Robinson TP (2018). Global distribution data for cattle, buffaloes, horses, sheep, goats, pigs, chickens and ducks in 2010. Scientific Data, 5, 180227. DOI: 10.1038/sdata.2018.227. DOI URL PMID
[9]	Gu ZJ, Duan XW, Shi YD, Li Y, Pan X (2018). Spatiotemporal variation in vegetation coverage and its response to climatic factors in the Red River Basin, China. Ecological Indicators, 93, 54-64.
[10]	Han QF, Luo GP, Li CF, Shakir A, Wu M, Saidov A (2016). Simulated grazing effects on carbon emission in Central Asia. Agricultural and Forest Meteorology, 216, 203-214.
[11]	He K, Wu SX, Yang Y, Wang D, Zhang SY, Yin N (2018). Dynamic changes of land use and oasis in Xinjiang in the last 40 years. Arid Land Geography, 41, 1333-1340.
	[ 贺可, 吴世新, 杨怡, 王丹, 张寿雨, 尹楠 (2018). 近40 a新疆土地利用及其绿洲动态变化. 干旱区地理, 41, 1333-1340.]
[12]	Hu S, Wang FY, Zhan CS, Zhao RX, Mo XG, Liu LMZ (2019). Detecting and attributing vegetation changes in Taihang Mountain, China. Journal of Mountain Science, 16, 337-350.
[13]	Huang XT, Luo GP, He HL, Wang XX, Amuti T (2017). Ecological effects of grazing in the northern Tianshan Mountains. Water, 9, 932. DOI: 10.3390/w9120932.
[14]	Huang XT, Luo GP, Ye FP, Han QF (2018). Effects of grazing on net primary productivity, evapotranspiration and water use efficiency in the grasslands of Xinjiang, China. Journal of Arid Land, 10, 588-600.
[15]	Kasza J, Wolfe R (2014). Interpretation of commonly used statistical regression models. Respirology, 19(1), 14-21. URL PMID
[16]	Krishnaswamy J, John R, Joseph S (2014). Consistent response of vegetation dynamics to recent climate change in tropical mountain regions. Global Change Biology, 20, 203-215. URL PMID
[17]	Li JJ, Peng SZ, Li Z (2017). Detecting and attributing vegetation changes on China’s Loess Plateau. Agricultural and Forest Meteorology, 247, 260-270.
[18]	Liu Q, Yang ZP, Han F, Wang ZG, Wang CR (2016). NDVI-based vegetation dynamics and their response to recent climate change: a case study in the Tianshan Mountains, China. Environmental Earth Sciences, 75, 1189. DOI: 10.1007/s12665-016-5987-5.
[19]	Liu Y, Nie L, Yang Y (2018). Spatio-temporal evolution and climatic driving characteristics of grassland in Tianshan Mountain area in 2001-2015. Ecology and Environmental Sciences, 27, 802-810.
	[ 刘艳, 聂磊, 杨耘 (2018). 2001-2015年天山地区草地NDVI时空演变和气候驱动特征分析. 生态环境学报, 27, 802-810.]
[20]	Liu ZJ, Liu YS, Li YR (2018). Anthropogenic contributions dominate trends of vegetation cover change over the farming-pastoral ecotone of northern China. Ecological Indicators, 95, 370-378.
[21]	Lujan-Moreno GA, Howard PR, Rojas OG, Montgomery DC (2018). Design of experiments and response surface methodology to tune machine learning hyperparameters, with a random forest case-study. Expert Systems with Applications, 109, 195-205.
[22]	Ma QM, Jia XP, Wang HB, Li YS, Li SN (2019). Recent advances in driving mechanisms of climate and anthropogenic factors on vegetation change. Journal of Desert Research, 39(6), 48-55.
	[ 马启民, 贾晓鹏, 王海兵, 李永山, 李劭宁 (2019). 气候和人为因素对植被变化影响的评价方法综述. 中国沙漠, 39(6), 48-55.]
[23]	Seddon AWR, Macias-Fauria M, Long PR, Benz D, Willis KJ (2016). Sensitivity of global terrestrial ecosystems to climate variability. Nature, 531, 229-232. URL PMID
[24]	Sung S, Nicklas F, Georg K, Lee DK (2016). Estimating net primary productivity under climate change by application of Global Forest Model (G4M). Journal of the Korean Society People, Plants, and Environment, 19, 549-558.
[25]	Wang H, Zhou SL, Li XB, Liu HH, Chi DK, Xu KK (2016). The influence of climate change and human activities on ecosystem service value. Ecological Engineering, 87, 224-239.
[26]	Wang JB, Zhao J, Li CH, Zhu Y, Kang CY, Gao C (2019). The spatial-temporal patterns of the impact of human activities on vegetation coverage in China from 2001 to 2015. Acta Geographica Sinica, 74, 504-519.
	[ 王建邦, 赵军, 李传华, 朱钰, 康重阳, 高超 (2019). 2001-2015年中国植被覆盖人为影响的时空格局. 地理学报, 74, 504-519.]
[27]	Wang ZY, Xu DY, Yang H, Ding X, Li DJ (2017). Impacts of climate change and human activities on vegetation dynamics in Inner Mongolia, 1981-2010. Progress in Geography, 36, 1025-1032.
	[ 王子玉, 许端阳, 杨华, 丁雪, 李达净 (2017). 1981-2010年气候变化和人类活动对内蒙古地区植被动态影响的定量研究. 地理科学进展, 36, 1025-1032.]
[28]	Yang HF, Yao L, Wang YB, Li JL (2017). Relative contribution of climate change and human activities to vegetation degradation and restoration in north Xinjiang, China. The Rangeland Journal, 39, 289-302.
[29]	Zhang M, Luo GP, Cao XS, Hamdi R, Li T, Cai P, Ye H, He HL (2019). Numerical simulation of the irrigation effects on surface fluxes and local climate in typical mountain-oasis-desert systems in the central Asia arid area. Journal of Geophysical Research: Atmospheres, 124, 12485-12506.
[30]	Zhang Q, Yuan XL, Chen X, Luo GP, Li LH (2016). Vegetation change and its response to climate change in Central Asia from 1982 to 2012. Chinese Journal of Plant Ecology, 40, 13-23.
	[ 张琪, 袁秀亮, 陈曦, 罗格平, 李龙辉 (2016). 1982-2012年中亚植被变化及其对气候变化的响应. 植物生态学报, 40, 13-23.]
[31]	Zhang RP, Zhang YL, Guo J, Feng QS, Liang TG (2018). Comparison of spatial interpolation methods for precipitation distribution in Xinjiang region. Pratacultural Science, 35, 521-529.
	[ 张仁平, 张云玲, 郭靖, 冯琦胜, 梁天刚 (2018). 新疆地区降水分布的空间插值方法比较. 草业科学, 35, 521-529.]
[32]	Zheng K, Wei JZ, Pei JY, Cheng H, Zhang XL, Huang FQ, Li FM, Ye JS (2019). Impacts of climate change and human activities on grassland vegetation variation in the Chinese Loess Plateau. Science of the Total Environment, 660, 236-244.

数据 Data	数据类型 Data type	空间分辨率 Spatial resolution	数据时段 Acquisition time	数据来源 Data source
MODIS-NDVI	栅格 Raster	1 km	2000-2015	https://code.earthengine.google.com
Landsat TM/ETM/OLI	栅格 Raster	30 m	2000, 2005, 2010, 2015	https://earthexplorer.usgs.gov
气象数据 Meteorological data	站点 Station	-	2000-2015	中国气象科学数据共享服务网(http://data.cma.cn/)、当地气象局 China meteorological data sharing service system (http://data.cma.cn/), local weather bureau
土地利用类型 Land use type	矢量 Vector	-	2000, 2005, 2010, 2015	中国科学院新疆生态与地理研究所对地观测与系统模拟实验室 Earth observation and systems simulation laboratory, Xinjiang institute of ecology and geography, Chinese Academy of Sciences
放牧数据 Grazing data	栅格、站点 Raster, station	0.083 33°	2000, 2005, 2010, 2015	世界粮农组织(FAO)(http://www.fao.org/livestock-systems/en/)、2015年野外实测数据、新疆统计年鉴 Food and Agriculture Organization (http://www.fao.org/livestock-systems/en/), field data in 2015, Xinjiang statistical yearbook

数据 Data	数据类型 Data type	空间分辨率 Spatial resolution	数据时段 Acquisition time	数据来源 Data source
MODIS-NDVI	栅格 Raster	1 km	2000-2015	https://code.earthengine.google.com
Landsat TM/ETM/OLI	栅格 Raster	30 m	2000, 2005, 2010, 2015	https://earthexplorer.usgs.gov
气象数据 Meteorological data	站点 Station	-	2000-2015	中国气象科学数据共享服务网(http://data.cma.cn/)、当地气象局 China meteorological data sharing service system (http://data.cma.cn/), local weather bureau
土地利用类型 Land use type	矢量 Vector	-	2000, 2005, 2010, 2015	中国科学院新疆生态与地理研究所对地观测与系统模拟实验室 Earth observation and systems simulation laboratory, Xinjiang institute of ecology and geography, Chinese Academy of Sciences
放牧数据 Grazing data	栅格、站点 Raster, station	0.083 33°	2000, 2005, 2010, 2015	世界粮农组织(FAO)(http://www.fao.org/livestock-systems/en/)、2015年野外实测数据、新疆统计年鉴 Food and Agriculture Organization (http://www.fao.org/livestock-systems/en/), field data in 2015, Xinjiang statistical yearbook

自变量 Independent variable	回归系数 Regression coefficient
自变量 Independent variable	2000	2005	2010	2015
年最低气温 Annual minimum temperature	0.134	0.156	0.127	0.162
年平均气温 Annual average temperature	-0.160	-0.139	-0.122	-0.245
年最高气温 Annual maximum temperature	0.026	-0.014	-0.013	0.072
年累计降水量 Annual cumulative precipitation	0.000 2	0.000 3	0.000 03	0.000 001
耕地比例 Arable proportion	0.005	0.005	0.005	0.005
林地比例 Forest proportion	0.005	0.005	0.007	0.007
草地比例 Grassland proportion	0.002	0.001	0.001	0.001
水体比例 Water body proportion	-0.001	-0.001	-0.001	-0.002
城市比例 Urban proportion	0.003	0.002	0.002	0.002
荒漠比例 Desert proportion	0.001	0.000 1	-0.000 4	-0.000 3
放牧强度 Grazing intensity	0.054	0.038	0.053	0.044
常数项 Constant	0.617	0.983	0.981	0.634

自变量 Independent variable	回归系数 Regression coefficient
自变量 Independent variable	2000	2005	2010	2015
年最低气温 Annual minimum temperature	0.134	0.156	0.127	0.162
年平均气温 Annual average temperature	-0.160	-0.139	-0.122	-0.245
年最高气温 Annual maximum temperature	0.026	-0.014	-0.013	0.072
年累计降水量 Annual cumulative precipitation	0.000 2	0.000 3	0.000 03	0.000 001
耕地比例 Arable proportion	0.005	0.005	0.005	0.005
林地比例 Forest proportion	0.005	0.005	0.007	0.007
草地比例 Grassland proportion	0.002	0.001	0.001	0.001
水体比例 Water body proportion	-0.001	-0.001	-0.001	-0.002
城市比例 Urban proportion	0.003	0.002	0.002	0.002
荒漠比例 Desert proportion	0.001	0.000 1	-0.000 4	-0.000 3
放牧强度 Grazing intensity	0.054	0.038	0.053	0.044
常数项 Constant	0.617	0.983	0.981	0.634

2000	2005						总计 Total
2000	耕地 Arable	林地 Forest	草地 Grassland	水体 Water body	城市 Urban	荒漠 Desert	总计 Total
耕地 Arable	1.568 8	0.003 8	0.040 9	0.001 1	0.010 1	0.021 6	1.646 3
林地 Forest	0.017 9	0.592 0	0.017 3	0.000 5	0.001 7	0.001 9	0.631 3
草地 Grassland	0.140 3	0.004 9	5.606 3	0.005 5	0.006 8	0.534 3	6.298 1
水体 Water body	0.001 3	0.000 1	0.003 8	0.489 3	0.000 4	0.005 0	0.499 9
城市 Urban	0.006 2	0.000 1	0.002 3	0.000 2	0.147 9	0.000 9	0.157 6
荒漠 Desert	0.056 6	0.001 5	0.027 6	0.017 7	0.011 6	5.558 6	5.673 6
总计 Total	1.791 1	0.602 4	5.698 2	0.514 3	0.178 5	6.122 3	14.906 8