Assessment of Vegetation Dynamics in Xinjiang Using NDVI Data and Machine Learning Models from 2000 to 2023

被引:0
|
作者
Ma, Nan [1 ,2 ,3 ,4 ]
Cao, Shanshan [2 ]
Bai, Tao [1 ,3 ,4 ]
Yang, Zhihao [5 ]
Cai, Zhaozhao [1 ,3 ,4 ]
Sun, Wei [2 ]
机构
[1] Xinjiang Agr Univ, Coll Comp & Informat Engn, Urumqi 830052, Peoples R China
[2] Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100081, Peoples R China
[3] Minist Educ, Engn Res Ctr Intelligent Agr, Urumqi 830052, Peoples R China
[4] Xinjiang Agr Informatizat Engn Technol Res Ctr, Urumqi 830052, Peoples R China
[5] Xinjiang Agr Univ, Coll Hydraul & Civil Engn, Urumqi 830052, Peoples R China
基金
中国国家自然科学基金;
关键词
NDVI; machine learning; soil moisture; runoff; potential evaporation; spatio-temporal change; RANDOM FOREST; REGRESSION; CLIMATE; GROWTH; TREND;
D O I
10.3390/su17010306
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study utilizes NASA's Normalized Difference Vegetation Index (NDVI) data from the Google Earth Engine (GEE) platform and employs methods such as mean analysis, trend analysis, and the Hurst index to assess NDVI dynamics in Xinjiang, with a particular focus on desert, meadow, and grassland vegetation. Furthermore, multiple linear regression, random forest, support vector machines, and XGBoost models are applied to construct and evaluate the NDVI prediction models. The key driving forces are identified and ranked based on the results of the optimal model. Changes in the vegetation cover in response to these driving forces are analyzed using the Mann-Kendall test and partial correlation analysis. The results indicate the following: (1) From 2000 to 2023, the annual variation in NDVI in Xinjian fluctuates at a rate of 0.0012 per year. The intra-annual trend follows an inverted U shape, with meadow vegetation exhibiting the highest monthly NDVI fluctuations. (2) During this period, the annual average NDVI in Xinjiang ranges from 0 to 0.3, covering 74.74% of the region. Spatially, higher NDVI values are observed in the north and northwest, while lower values are concentrated in the south and southeast. (3) The overall slope of the variation in NDVI in Xinjiang between 2000 and 2023 ranges between -0.034 and 0.047, indicating no significant upward trend. According to the Hurst index, future projections suggest a shift from vegetation improvement to potential degradation. (4) Machine learning models are developed to predict NDVI, with random forest and XGBoost showing the highest precision. Soil moisture, runoff, and potential evaporation are identified as key drivers. In the last 24 years, the temperatures in Xinjiang have generally increased, while precipitation, soil moisture, and runoff have declined. There is a significant negative correlation between NDVI and both temperature and potential evaporation, while the correlation between NDVI and precipitation, soil moisture, and runoff is positive and significant, with distinct spatial variations throughout the region. The overall trend of vegetation cover in Xinjiang has been increasing, but the future outlook is less promising. Enhanced environmental monitoring and protective measures are essential moving forward.
引用
收藏
页数:24
相关论文
共 50 条
  • [21] Trends in Vegetation Seasonality in the Iberian Peninsula: Spatiotemporal Analysis Using AVHRR-NDVI Data (1982-2023)
    Gutierrez-Hernandez, Oliver
    Garcia, Luis V.
    SUSTAINABILITY, 2024, 16 (21)
  • [22] Comparative evaluation of machine learning models for assessment of seabed liquefaction using finite element data
    Du, Xing
    Song, Yupeng
    Wang, Dong
    He, Kunpeng
    Chi, Wanqing
    Xiu, Zongxiang
    Zhao, Xiaolong
    FRONTIERS IN MARINE SCIENCE, 2024, 11
  • [23] Deriving vegetation dynamics of natural terrestrial ecosystems from MODIS NDVI/EVI data over Turkey
    Evrendilek, Fatih
    Gulbeyaz, Onder
    SENSORS, 2008, 8 (09): : 5270 - 5302
  • [24] NDVI-BASED VEGETATION DYNAMICS AND ITS RESPONSE TO PRECIPITATION CHANGES IN THE HEXI CORRIDOR OF CHINA FROM 2000 TO 2019
    E, M. X.
    Zhao, B.
    Chong, S. L.
    APPLIED ECOLOGY AND ENVIRONMENTAL RESEARCH, 2024, 22 (02): : 1903 - 1916
  • [25] Approximate Data Deletion from Machine Learning Models
    Izzo, Zachary
    Smart, Mary Anne
    Chaudhuri, Kamalika
    Zou, James
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [26] Certified Data Removal from Machine Learning Models
    Guo, Chuan
    Goldstein, Tom
    Hannun, Awni
    van der Maaten, Laurens
    25TH AMERICAS CONFERENCE ON INFORMATION SYSTEMS (AMCIS 2019), 2019,
  • [27] Certified Data Removal from Machine Learning Models
    Guo, Chuan
    Goldstein, Tom
    Hannun, Awni
    van der Maaten, Laurens
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [28] Accurate Wheat Yield Prediction Using Machine Learning and Climate-NDVI Data Fusion
    Ashfaq, Muhammad
    Khan, Imran
    Alzahrani, Abdulrahman
    Tariq, Muhammad Usman
    Khan, Humera
    Ghani, Anwar
    IEEE ACCESS, 2024, 12 : 40947 - 40961
  • [29] Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data
    Yongbing Zhao
    Jinfeng Shao
    Yan W.Asmann
    Genomics,Proteomics & Bioinformatics, 2022, (05) : 899 - 911
  • [30] Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data
    Zhao, Yongbing
    Shao, Jinfeng
    Asmann, Yan W.
    GENOMICS PROTEOMICS & BIOINFORMATICS, 2022, 20 (05) : 899 - 911