Sentinel-2 estimation of CNC and LAI in rice cropping system through hybrid approach modelling

Earth observation techniques represent a reliable and faster alternative to in-situ measurements by providing spatio-temporal information on crop status. In this framework, a study was conducted to assess the performance of hybrid approaches, either standard (HYB) or exploiting an active learning optimisation strategy (HYB-AL), to estimate leaf area index (LAI) and canopy nitrogen content (CNC) from Sentinel-2 (S2) data, in rice crops. To achieve this, the PROSAIL-PRO Radiative Transfer Model (RTM) was tested. Results demonstrate that a wide range of rice spectra, simulated according to realistic crop parameters, are reliable when appropriate field background conditions are considered. Simulations were used to train a Gaussian Process Regression (GPR) algorithm. Both cross-validation and validation results showed that HYB-AL approach resulted the best performing retrieval schema. LAI estimation achieved good performance (R-2=0.86; RMSE=0.54) and resulted very promising for model application in operational monitoring systems. CNC estimations showed moderate performance (R-2=0.63; RMSE=0.89) due to a saturation behaviour limiting the retrieval accuracy for moderate/high CNC values, approximately above 4 [g m(-2)]. S2 maps of LAI and CNC provided spatio-temporal information in agreement with crop growth, nutritional status and agro-practices applied to the study area, resulting in an important contribution to precision farming applications.

Automated summary

This study evaluated the performance of hybrid approaches in estimating leaf area index (LAI) and canopy nitrogen content (CNC) in rice crops using Earth observation techniques. The results showed that the hybrid approach with active learning optimization strategy had the best retrieval performance, providing valuable information for precision farming applications.