*Article* **Applying RGB- and Thermal-Based Vegetation Indices from UAVs for High-Throughput Field Phenotyping of Drought Tolerance in Forage Grasses**

**Tom De Swaef 1,\* ,†, Wouter H. Maes 2,†, Jonas Aper <sup>1</sup> , Joost Baert <sup>1</sup> , Mathias Cougnon <sup>3</sup> , Dirk Reheul <sup>3</sup> , Kathy Steppe <sup>4</sup> , Isabel Roldán-Ruiz 1,5 and Peter Lootens <sup>1</sup>**


**Abstract:** The persistence and productivity of forage grasses, important sources for feed production, are threatened by climate change-induced drought. Breeding programs are in search of new drought tolerant forage grass varieties, but those programs still rely on time-consuming and less consistent visual scoring by breeders. In this study, we evaluate whether Unmanned Aerial Vehicle (UAV) based remote sensing can complement or replace this visual breeder score. A field experiment was set up to test the drought tolerance of genotypes from three common forage types of two different species: *Festuca arundinacea*, diploid *Lolium perenne* and tetraploid *Lolium perenne*. Drought stress was imposed by using mobile rainout shelters. UAV flights with RGB and thermal sensors were conducted at five time points during the experiment. Visual-based indices from different colour spaces were selected that were closely correlated to the breeder score. Furthermore, several indices, in particular *H* and *NDLab*, from the HSV (Hue Saturation Value) and CIELab (Commission Internationale de l'éclairage) colour space, respectively, displayed a broad-sense heritability that was as high or higher than the visual breeder score, making these indices highly suited for high-throughput field phenotyping applications that can complement or even replace the breeder score. The thermal-based Crop Water Stress Index *CWSI* provided complementary information to visual-based indices, enabling the analysis of differences in ecophysiological mechanisms for coping with reduced water availability between species and ploidy levels. All species/types displayed variation in drought stress tolerance, which confirms that there is sufficient variation for selection within these groups of grasses. Our results confirmed the better drought tolerance potential of *Festuca arundinacea*, but also showed which *Lolium perenne* genotypes are more tolerant.

**Keywords:** UAV; RGB camera; thermal camera; drought tolerance; forage grass; HSV; CIELab; broad-sense heritability; phenotyping gap; high throughput field phenotyping
