文献类型：期刊文献

英文题名：Comparison of Machine Learning Methods to Up-Scale Gross Primary Production

作者：Yu, Tao[1,2,3,4] Zhang, Qiang[3,4,5] Sun, Rui[3,4,5]

第一作者：Yu, Tao;余涛

通信作者：Sun, R[1];Sun, R[2];Sun, R[3]

机构：[1]Chinese Acad Forestry, Res Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]Natl Forestry & Grassland Adm, Key Lab Forestry Remote Sensing & Informat Syst, Beijing 100091, Peoples R China;[3]Beijing Normal Univ, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China;[4]Chinese Acad Sci, State Key Lab Remote Sensing Sci, Inst Remote Sensing & Digital Earth, Beijing 100875, Peoples R China;[5]Beijing Normal Univ, Beijing Engn Res Ctr Global Land Remote Sensing P, Inst Remote Sensing Sci & Engn, Fac Geog Sci, Beijing 100875, Peoples R China

年份：2021

卷号：13

期号：13

外文期刊名：REMOTE SENSING

收录：;EI(收录号：20212810614800);Scopus(收录号：2-s2.0-85109215361);WOS:【SCI-EXPANDED(收录号:WOS:000670911600001)】；

基金：This research was funded by the National Key R&D Program of China (2016YFB0501502, 2017YFA0603002) and the National Natural Science Foundation of China (41531174), and the Fundamental Research Funds of CAF (CAFYBB2021SY009).

语种：英文

外文关键词：GPP; up-scaling; machine learning; validation

摘要：Eddy covariance observation is an applicable way to obtain accurate and continuous carbon flux at flux tower sites, while remote sensing technology could estimate carbon exchange and carbon storage at regional and global scales effectively. However, it is still challenging to up-scale the field-observed carbon flux to a regional scale, due to the heterogeneity and the unstable air conditions at the land surface. In this paper, gross primary production (GPP) from ground eddy covariance systems were up-scaled to a regional scale by using five machine learning methods (Cubist regression tree, random forest, support vector machine, artificial neural network, and deep belief network). Then, the up-scaled GPP were validated using GPP at flux tower sites, weighted GPP in the footprint, and MODIS GPP products. At last, the sensitivity of the input data (normalized difference vegetation index, fractional vegetation cover, shortwave radiation, relative humidity and air temperature) to the precision of up-scaled GPP was analyzed, and the uncertainty of the machine learning methods was discussed. The results of this paper indicated that machine learning methods had a great potential in up-scaling GPP at flux tower sites. The validation of up-scaled GPP, using five machine learning methods, demonstrated that up-scaled GPP using random forest obtained the highest accuracy.