The yeastLachancea thermotolerans(previouslyKluyveromyces thermotolerans) is a species of large, yet underexplored, oenological potential. This study delivers comprehensive oenological phenomes of 94 L. thermotoleransstrains obtained from diverse ecological niches worldwide, classified in nine genetic groups based on their pre-determined microsatellite genotypes. The strains and the genetic groups were compared for their alcoholic fermentation performance, production of primary and secondary metabolites and pH modulation in Chardonnay grape juice fermentations. The common oenological features ofL. thermotoleransstrains were their glucophilic character, relatively extensive fermentation ability, low production of acetic acid and the formation of lactic acid, which significantly affected the pH of the wines. An untargeted analysis of volatile compounds, used for the first time in a population-scale phenotyping of a non-Saccharomycesyeast, revealed that 58 out of 90 volatiles were affected at anL. thermotoleransstrain level. Besides the remarkable extent of intra-specific diversity, our results confirmed the distinct phenotypic performance ofL. thermotoleransgenetic groups. Together, these observations provide further support for the occurrence of domestication events and allopatric differentiation inL. thermotoleranspopulation.

This paper gives two contributions to the state-of-the-art for viticulture technology research. First we present a comprehensive review of computer vision, image processing, and machine learning techniques in viticulture. We summarise the latest developments in vision systems and techniques with examples from various representative studies including harvest yield estimation, vineyard management and monitoring, grape disease detection, quality evaluation, and grape phenology. We focus on how computer vision and machine learning techniques can be integrated into current vineyard management and vinification processes to achieve industry relevant outcomes. The second component of the paper presents the new GrapeCS-ML Database which consists of images of grape varieties at different stages of development together with the corresponding ground truth data (e.g. pH, Brix, etc.) obtained from chemical analysis. One of the objectives of this database is to motivate computer vision and machine learning researchers to develop practical solutions for deployment in smart vineyards. We illustrate the usefulness of the database for a color-based berry detection application for white and red cultivars and give baseline comparisons using various machine learning approaches and color spaces. The paper concludes by highlighting future challenges that need to be addressed prior to successful implementation of this technology in the viticulture industry.