Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features.
Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features.
复制标题
利用优化算法和多维特征改进高寒草原植被覆盖率的估计
DOI：
10.1186/s13007-021-00796-5
复制
发表时间：
2021-09-17
期刊：
影响因子：
5.1
通讯作者：
Han X
中科院分区：
文献类型：
--
作者：
Lin X;Chen J;Lou P;Yi S;Qin Y;You H;Han X
植被覆盖度是青藏高原高寒草地生态系统定量监测的重要基础参数。基于无人机（UAV）采集的测量数据，并将其与卫星遥感图像在像素尺度上匹配，可以确定适当的驱动数据和反演算法的选择，是生成高精度的高寒草原FVC products.MethodsThis研究提出了估计高寒草原FVC使用优化算法和多维特征。该方法首先利用原始光谱波段、22个植被指数和地形因子构建多维特征集，然后基于不同的特征选择算法确定最优特征子集，作为优化机器学习算法的驱动数据。结果（1）随机森林（RF）算法（R2：0.861，RMSE：9.5%）在4种典型植被指数驱动的4种机器学习算法中反演FVC的效果最好。(2)与4种典型植被指数相比，采用多维特征集作为驱动数据明显提高了4种机器学习算法的FVC反演精度（RF算法的R2提高到0.890）。(3)在Boruta、序贯前向选择（SFS）和排列重要性-递归特征消除（PI-RFE）三种变量选择算法中，所构造的PI-RFE特征选择算法对多维特征集的降维效果最好。(4)机器学习算法的超参数优化和多维特征集的特征选择进一步提高了FVC反演精度（R2：0.917，RMSE：结论本研究为FVC反演提供了一种具有最佳多维特征集的高精度优化算法，这对高寒草地生态环境的定量监测至关重要。
BackgroundFractional vegetation cover (FVC) is an important basic parameter for the quantitative monitoring of the alpine grassland ecosystem on the Qinghai-Tibetan Plateau. Based on unmanned aerial vehicle (UAV) acquisition of measured data and matching it with satellite remote sensing images at the pixel scale, the proper selection of driving data and inversion algorithms can be determined and is crucial for generating high-precision alpine grassland FVC products.MethodsThis study presents estimations of alpine grassland FVC using optimized algorithms and multi-dimensional features. The multi-dimensional feature set (using original spectral bands, 22 vegetation indices, and topographical factors) was constructed from many sources of information, then the optimal feature subset was determined based on different feature selection algorithms as the driving data for optimized machine learning algorithms. Finally, the inversion accuracy, sensitivity to sample size, and computational efficiency of the four machine learning algorithms were evaluated.Results(1) The random forest (RF) algorithm (R2: 0.861, RMSE: 9.5%) performed the best for FVC inversion among the four machine learning algorithms driven by the four typical vegetation indices. (2) Compared with the four typical vegetation indices, using multi-dimensional feature sets as driving data obviously improved the FVC inversion accuracy of the four machine learning algorithms (R2of the RF algorithm increased to 0.890). (3) Among the three variable selection algorithms (Boruta, sequential forward selection [SFS], and permutation importance-recursive feature elimination [PI-RFE]), the constructed PI-RFE feature selection algorithm had the best dimensionality reduction effect on the multi-dimensional feature set. (4) The hyper-parameter optimization of the machine learning algorithms and feature selection of the multi-dimensional feature set further improved FVC inversion accuracy (R2: 0.917 and RMSE: 7.9% in the optimized RF algorithm).ConclusionThis study provides a highly precise, optimized algorithm with an optimal multi-dimensional feature set for FVC inversion, which is vital for the quantitative monitoring of the ecological environment of alpine grassland.
登录
查看更多内容
影响因子：
6.1
作者：
Chen, Jianjun;Yi, Shuhua;Qin, Yu
通讯作者：
Qin, Yu
基于无人机改进青藏高原高寒草原植被覆盖度估算
影响因子：
3.4
作者：
Chen, Jianjun;Yi, Shuhua;Wang, Xiaoyun
通讯作者：
Wang, Xiaoyun
DOI：
10.1016/s0273-1177(97)01133-2
发表时间：
1998-01-01
期刊：
SYNERGISTIC USE OF MULTISENSOR DATA FOR LAND PROCESSES
影响因子：
--
作者：
Gitelson, AA;Merzlyak, MN
通讯作者：
Merzlyak, MN
影响因子：
13.5
作者：
Bunting, Erin L.;Munson, Seth M.;Bradford, John B.
通讯作者：
Bradford, John B.
影响因子：
2.4
作者：
Chen, Wei;Sakai, Tetsuro;Cao, Chunxiang
通讯作者：
Cao, Chunxiang