Retrieval of crop traits using PROSAIL-based hybrid radiative transfer model and EnMAP hyperspectral data

• EnMAP hyperspectral data facilitated the accurate retrieval of key wheat traits. • Leaf Chlorophyll Content, Carotenoids, and Leaf Area Index were estimated using PROSAIL and Machine/Active Learning. • All the models were validated using ground measurements, showcasing EnMAP’s potential for precision agriculture. Implementing high spectral resolution imaging from the Environmental Mapping and Analysis Program (EnMAP) paved the way for detailed retrieval of agricultural traits for accurate crop monitoring and management. The proposed methodology involves the integration and detailed analysis of Radiative Transfer Modelling (RTM) with an integrated approach of machine learning (ML) and Active Learning (AL) algorithms for the retrieval of the Leaf Chlorophyll Content (LCC), Carotenoids (Car) and Leaf Area index (LAI) of wheat cropland from the continuous three years of the dataset. Reflectance values of leaf were collected using Analytical Spectral Device (ASD) − Spectroradiometer data ranging from 350-2500 nm and EnMAP satellite hyperspectral data extends spectral data range varies between 420 nm to 1000 nm in the visible and near-infrared (VNIR) of EMR region, and from 900 nm to 2450 nm in the shortwave infrared (SWIR) region for crop parameters mapping for a larger spatial area of Varanasi district, Uttar Pradesh, India. The PROSPECT + SAIL (PROSAIL) RTM was employed to simulate spectral (reflectance) data, and fourteen ML algorithms were assessed for implementation into a hybrid model. Kernel Ridge regression (KRR) was combined with Euclidean-based Diversity (EBD) algorithms to retrieve crop characteristics due to their exceptional accuracy and reduced uncertainty. Spectral profiles were further used to train hybrid models using PCA (Principal Component Analysis) feature selection, and combined techniques (ML + AL) were applied to retrieve LCC, Car, and LAI. Afterwards, biophysical and biochemical spatial large-scale estimation were provided through atmospherically corrected, and noise-removed EnMAP hyperspectral data with the help of a trained and tested hybrid (ML + AL) model and validated with the ground-measured datasets. The performance indicators showed significantly very high values of correlation during calibration (LCC = 0.99, Car = 0.74, and LAI = 0.99) and validation (LCC = 0.66, Car = 0.57, and LAI= 0.88). The work showed that the optimized hybrid (KRR + AL) models customized for EnMAP hyperspectral data can efficiently estimate the wheat biophysical and biochemical parameters in near-real time therefore, expanding this workflow to agricultural fields may enable more effective monitoring and management of wheat crops.