A Comparison of Hybrid Machine Learning Algorithms for the Retrieval of Wheat Biophysical Variables from Sentinel-2

Remote Sensing

Xianfeng Zhou¹  Stefano Pignatti²  Simone Pascucci²  Deepak Upreti³  Raffaele Casa³  Weiping Kong⁴  Wenjiang Huang⁴  Huichun Ye⁴ 

[1] College of Life Information Science and Instrument Engineering, Hangzhou Dianzi University, Hangzhou 310018, China;Consiglio Nazionale delle Ricerche, Institute of Methodologies for Environmental Analysis (CNR, IMAA), Via del Fosso del Cavaliere, 100, 00133 Rome, Italy;DAFNE, Università della Tuscia, Via San Camillo de Lellis, 01100 Viterbo, Italy;Key laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China;

关键词: LAI;    LCC;    FAPAR;    FVC;    CCC;    PROSAIL;    GPR;    machine learning;    active learning;   

DOI  :  10.3390/rs11050481

来源: DOAJ

【 摘 要 】

This study focuses on the comparison of hybrid methods of estimation of biophysical variables such as leaf area index (LAI), leaf chlorophyll content (LCC), fraction of absorbed photosynthetically active radiation (FAPAR), fraction of vegetation cover (FVC), and canopy chlorophyll content (CCC) from Sentinel-2 satellite data. Different machine learning algorithms were trained with simulated spectra generated by the physically-based radiative transfer model PROSAIL and subsequently applied to Sentinel-2 reflectance spectra. The algorithms were assessed against a standard operational approach, i.e., the European Space Agency (ESA) Sentinel Application Platform (SNAP) toolbox, based on neural networks. Since kernel-based algorithms have a heavy computational cost when trained with large datasets, an active learning (AL) strategy was explored to try to alleviate this issue. Validation was carried out using ground data from two study sites: one in Shunyi (China) and the other in Maccarese (Italy). In general, the performance of the algorithms was consistent for the two study sites, though a different level of accuracy was found between the two sites, possibly due to slightly different ground sampling protocols and the range and variability of the values of the biophysical variables in the two ground datasets. For LAI estimation, the best ground validation results were obtained for both sites using least squares linear regression (LSLR) and partial least squares regression, with the best performances values of R² of 0.78, rott mean squared error (RMSE) of 0.68 m² m⁻² and a relative RMSE (RRMSE) of 19.48% obtained in the Maccarese site with LSLR. The best results for LCC were obtained using Random Forest Tree Bagger (RFTB) and Bagging Trees (BagT) with the best performances obtained in Maccarese using RFTB (R² = 0.26, RMSE = 8.88 μg cm⁻², RRMSE = 17.43%). Gaussian Process Regression (GPR) was the best algorithm for all variables only in the cross-validation phase, but not in the ground validation, where it ranked as the best only for FVC in Maccarese (R² = 0.90, RMSE = 0.08, RRMSE = 9.86%). It was found that the AL strategy was more efficient than the random selection of samples for training the GPR algorithm.

【 授权许可】

Unknown