Inversion of the hybrid machine learning model to estimate leaf area index of winter wheat from GaoFen-6 WFV imagery

Abstract

The leaf area index (LAI) is an important agroecological physiological parameter affecting vegetation growth and is an essential indicator for estimating crop growth. To apply the hybrid machine learning model to the remote sensing inversion of winter wheat LAI at three growth stages based on the wide field of view (WFV) of the GaoFen-6 (GF-6 WFV) images, the Xiangfu District in the east of Kaifeng City, Henan Province, was selected as the testing region. The LAI values, which were simulated using the CERES-wheat model, were an input for the PROSAIL model to simulate spectral reflectance. Different machine learning regression algorithms (MLRA) were trained with simulated spectra reflectance by PROSAIL and subsequently applied to the GF-6 WFV reflectance spectra. The random forest regression (RFR) model achieved reliable LAI estimates at the three growth stages. CERES-wheat and PROSAIL preserved the most informative spectra reflectance for LAI estimation so that each RFR could achieve satisfactory estimation results. The hybrid machine learning model could accurately reverse the growth state of winter wheat in three growth stages.