Investigating the potential of Sentinel-2 configuration to predict the quality of Mediterranean permanent grasslands in open woodlands

Abstract

The assessment of pasture quality in permanent grasslands is essential for their conservation and management, as it can contribute to making real-time decisions for livestock management. In this study, we assessed the potential of Sentinel-2 configuration to predict forage quality in high diverse Mediterranean permanent grasslands of open woodlands. We evaluated the performance of Partial Least Squares Regression (PLS) models to predict crude protein (CP), neutral detergent fibre (NDF), acid detergent fibre (ADF) and enzyme digestibility of organic matter (EDOM) by using three different reflectance datasets: (i) laboratory measurements of reflectance of dry and ground pasture samples re-sampled to Sentinel-2 configuration (Spec-lab) (ii) field in-situ measurements of grasslands canopy reflectance resampled to Sentinel-2 configuration (Spec-field); (iii) and Bottom Of Atmosphere Sentinel-2 imagery. For the three reflectance datasets, the models to predict CP content showed moderate performance and predictive ability. Mean R2test = 0.68 were obtained using Spec-lab data, mean R2test decreased by 0.11 with Spec-field and by 0.18 when Sentinel-2 reflectance was used. Statistics for NDF showed worse predictions than those obtained for CP: predictions produced with Spec-lab showed mean R2test = 0.64 and mean RPDtest = 1.73. The mean values of R2test = 0.50 and RPDtest = 1.54 using Sentinel-2 BOA reflectance were marginally better than the values obtained with Spec-field (mean R2test = 0.48, mean RPDtest = 1.43). For ADF and EDOM, only predictions made with Spec-lab produced acceptable results. Bands from the red-edge region, especially band 5, and the SWIR regions showed the highest contribution to estimating CP and NDF. Bands 2, blue and 4, red also seem to be important. The implementation of field spectroscopy in combination with Sentinel-2 imagery proved to be feasible to produce forage quality maps and to develop larger datasets. This study contributes to increasing knowledge of the potential and applicability of Sentinel-2 to predict the quality of Mediterranean permanent grasslands in open woodlands.