基于Landsat 8和机器学习的塔城地区草地地上生物量估测模型
Estimation model of above-ground biomass of grassland in Tarbagatay Prefecture based on Landsat 8 and machine learning
杨延晓 1曹姗姗 2李全胜 1张鲜花 3孙伟2
作者信息
- 1. 新疆农业大学,计算机与信息工程学院,乌鲁木齐 830052
- 2. 中国农业科学院农业信息研究所,北京 100081
- 3. 新疆农业大学,草业学院,乌鲁木齐 830052
- 折叠
摘要
以新疆塔城地区为研究区,利用植被指数、气象数据、地形数据作为自变量,结合研究区样地实测生物量数据,分析并比较K近邻回归(KNN)、多元线性回归(MLR)、梯度提升决策树(GBDT)和随机森林回归(RF)和极端梯度提升(XGBoost)5种机器学习模型,进而分析并比较采用投票回归器(Voting regressor)和堆叠(Stacking)方法构建的2种集成学习模型的估测精度.结果表明,基于Stacking集成学习模型性能最优,R2达0.764,RMSE和MAE分别为23.29 g/m2和16.8 g/m2,进而利用最优模型进行草地地上生物量(Above ground biomass,AGB)反演制图.
Abstract
Taking Tarbagatay Prefecture of Xinjiang as the study area,using vegetation index,meteorological data and terrain data as independent variables,combined with the measured biomass data of sample plots in the study area,five machine learning models in-cluding k-nearest neighbors regression(KNN),multiple linear regression(MLR),gradient boosting decision tree(GBDT),random forest regression(RF)and Gradient Boosting Decision Tree(GBDT)were analyzed and compared,as well as two ensemble learning models constructed using voting regressor and stacking methods.The results showed that the stacking ensemble learning model had the best performance,with R2 of 0.764,RMSE and MAE of 23.29 g/m2 and 16.8 g/m2,respectively.The optimal model was then used to in-vert and map above-ground biomass(AGB)of grassland.
关键词
草地地上生物量/Landsat/8/遥感影像/机器学习/估测模型/新疆塔城地区Key words
above-ground biomass(AGB)of grassland/Landsat 8/remote sensing image/machine learning/estimation model/Tarbagatay Prefecture,Xinjiang引用本文复制引用
基金项目
国家自然科学基金项目(32271880)
国家自然科学基金项目(31860180)
新疆农业大学2023年度研究生科研创新项目(XJAUGRI2023030)
出版年
2024
NETL
NSTL
万方数据