Improving Estimation of Winter Wheat Biophysical Traits Using Solar-Induced Fluorescence Indices and a Multi-Task Gaussian Process Model

Abstract

Accurate estimation of crop biophysical traits is essential for optimizing crop management. Solarinduced chlorophyll fluorescence (SIF), as a direct indicator of photosynthesis, has large potential in monitoring plant growth status. This study aimed to enhance the estimation of wheat key biophysical traits, including aboveground biomass (AGB), canopy relative chlorophyll content (RCC), and nitrogen balance index (NBI), by integrating reflectance-based SIF-sensitive indices with a multi-task sparse variational Gaussian process (SVGP) model. The results showed that the model utilizing the indices as the exclusive predictors demonstrated superior performance compared to other models. This study confirmed the efficacy of the indices in the estimation of winter wheat biophysical traits, offering a precise method for monitoring the growth status of winter wheat.