Enhancing seasonal leaf area index estimation using PLSR with Sentinel-2 spectral and texture features: the importance of feature engineering and feature selection

Overcomes spectral-band limits of multisensory PLSR. Feature engineering integrates Sentinel-2 spectra, VIs, and textures for seasonal LAI. LASSO-VIF-PLSR boosts accuracy, notably spring and autumn. Universal PLSR model captures cross-seasonal LAI dynamics. The empirical retrieval of leaf area index (LAI) through multispectral remote sensing typically relies more on vegetation indices (VIs) than on partial least squares regression (PLSR). This is primarily because the limited number of bands in