Grassland Productivity and Ewes’ Forage Intake Monitoring by Combined Multispectral Vegetation Indices and Machine Learning Approaches for Precision Grazing Management

Grassland productivity and precise monitoring of animal herbage intake are key requirements for sustainable grazing management in Mediterranean upland systems. This study aimed to evaluate the potential of uncrewed aerial vehicle (UAV)-based multispectral vegetation indices (VIs) combined with machine learning (ML) algorithms to estimate forage biomass, quality parameters and daily herbage dry matter intake (HDMI) of grazing ewes at the paddock scale. The experiment was conducted in a managed ryegrass-white clover meadow-pasture in southern Italy, where four plots were grazed sequentially by lactating Sarda ewes during spring-summer 2025. Ground measurements included pre- and post-grazing biomass inside and outside exclusion cages, botanical composition and forage quality. Concurrently, UAV multispectral imagery has been acquired, from which several VIs were computed. Pearson's correlations were used to explore relationships between VIs and forage variables, and five ML algorithms. Indices such as MCARI2, MTVI2, MTVI, MSAVI and OSAVI showed the strongest associations with biomass and quality traits, while support vector machine and neural networks provided the best prediction accuracies, particularly for HDMI (R2 up to 0.91). The integrated UAV-ML approach proved effective in simultaneously capturing spatial variability of pasture productivity and animal intake, supporting the development of operational precision grazing tools for heterogeneous Mediterranean grasslands.