湖北农业科学 ›› 2024, Vol. 63 ›› Issue (8): 216-222.doi: 10.14088/j.cnki.issn0439-8114.2024.08.036

• 遥感技术 • 上一篇    下一篇

基于机器学习的新疆植被覆盖变化及其影响因子之间的关系

马楠1, 蔡朝朝1,2, 白涛1,2   

  1. 1.新疆农业大学计算机与信息工程学院,乌鲁木齐 830052;
    2.新疆农业信息化工程技术研究中心,乌鲁木齐 830052
  • 收稿日期:2022-09-22 出版日期:2024-08-25 发布日期:2024-09-05
  • 通讯作者: 蔡朝朝(1978-),女,副教授,博士,主要从事林业信息化、大数据技术研究,(电子信箱)czz@xjau.edu.cn。
  • 作者简介:马 楠(1994-),女,新疆昌吉人,在读硕士研究生,研究方向为农业信息化,(电话)13619906124(电子信箱)1457883572@qq.com。
  • 基金资助:
    新疆维吾尔自治区自然科学基金面上项目(2022D01A81); 新疆维吾尔自治区高校基本科研业务费科研项目(XJEDU2022J009); 科学技术部科技创新2030重大项目(2022ZD0115800)

The relationship between vegetation cover change and its influencing factors in Xinjiang based on machine learning

MA Nan1, CAI Zhao-zhao1,2, BAI Tao1,2   

  1. 1. College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China;
    2. Xinjiang Agricultural Informatization Engineering Technology Research Center, Urumqi 830052, China
  • Received:2022-09-22 Published:2024-08-25 Online:2024-09-05

摘要: 以新疆植被覆盖变化及其影响因子之间的关系作为研究对象,通过比较多元线性回归、随机森林回归、XGBoost、支持向量机回归,优选出精度最高的模型,依据最优模型计算出的属性重要程度,对15个影响因子进行重组并分析,探索了气温、降水量、辐射量、潜在蒸发、经度、纬度、高程、地貌类型、坡度、坡向、人类影响指数、径流、土壤类型、土壤湿度、植被类型15个影响因子对植被覆盖变化的影响。结果表明,XGBoost模型对归一化植被指数(NDVI)预测准确率最高,随机森林回归次之。在研究区内对NDVI影响程度最大的影响因子是土壤湿度、径流、植被类型、经度、潜在蒸发、气温、辐射量、地貌类型、降水量。在影响因素类型方面,气候条件因素对NDVI影响程度最大,土壤特征因素影响程度次之,地形地貌因素比前两者低。

关键词: 机器学习, 植被覆盖, XGBoost, 预测模型, 影响因子, 归一化植被指数(NDVI), 新疆

Abstract: Taking the relationship between vegetation cover change and its influencing factors in Xinjiang as the research object, by comparing multiple linear regression, random forest regression, XGBoost and support vector machine regression, the model with the highest accuracy was selected, and 15 influencing factors were reorganized and analyzed according to the attribute importance degree calculated by the optimal model. The effects of 15 factors including air temperature, precipitation, radiation amount, potential evaporation, longitude, dimension, elevation, landform type, slope, slope orientation, human impact index, runoff, soil type, soil moisture, and vegetation type on vegetation cover change were explored. The results showed that XGBoost model had the highest prediction accuracy for normalized vegetation index (NDVI), followed by random forest regression. In the study area, the most influential factors on NDVI were soil moisture, runoff, vegetation type, longitude, potential evaporation, air temperature, radiation amount, landform type and precipitation. In terms of the types of influencing factors, climatic conditions had the greatest influence on NDVI, followed by soil characteristics, and the topographic and geomorphic factors were the lowest compared with the first two.

Key words: machine learning, vegetation cover, XGBoost, prediction model, influence factor, normalized vegetation index (NDVI), Xinjiang

中图分类号: