Implementation of hyperspectral image analysis for evaluating table grape quality on bunch and berry level

The concept of ‘terroir’ describes the interplay of the environmental factors that affect the grapevine. This includes but is not limited to climate, soil composition, vineyard management, topography, and geology.

Climate change will require the adaptation of agricultural systems and among the different means of adaptation, changing plant material is a promising strategy. In viticulture, different levels of diversity are currently exploited: clonal and varietal diversity for rootstocks and scions. A huge quantity of research aims to evaluate different genotypes in different environmental conditions to identify which ones are the best adapted and the most tolerant to future environmental conditions.

vine plant material is one of the major factors of terroir. The vine numbers over 1,000 species, of which the main cultivated species, Vitis vinifera, includes some 6,000 varieties. For the last forty years, selection has been carried out on these, mainly through clonal selection. However, today, only 300 varieties present one or more clones. A dozen varieties are considered as international. The extreme requirements of selection, in terms of diseases, provoke the elimination of the majority of selected plants. This approach to selection is not thorough because it focuses mainly on elimination of virosis and phytoplasma diseases.

Regenerative agriculture (RA) practices aim to minimize soil disturbance, keep soil covered, maintain living roots underground, and integrate livestock to improve soil health and sustainability.

Knowledge on the reflectance spectrum of soil is potentially useful since it carries information on soil chemical composition that can be used to the planning of agricultural practices. If compared with analytical methods such as conventional chemical analysis, reflectance measurement provides non-destructive, economic, near real-time data. This paper reports results from reflectance measurements performed by spectroradiometry on soils from two vineyards in south Brazil. The vineyards are close to each other, are on different geological formations, but were subjected to the same management. The objective was to detect spectral differences between the two areas, correlating these differences to variations in their chemical composition, to assess the technique’s potential to predict soil attributes from reflectance data.To that end, soil samples were collected from ten selected vine parcels. Chemical analysis yield data on concentration of twenty-one soil attributes, and spectroradiometry was performed on samples. Chemical differences significant to a 95% confidence level between the two studied areas were found for six soil attributes, and the average reflectance spectra were separated by this same level along most of the observed spectral domain. Correlations between soil reflectance and concentrations of soil attributes were looked for, and for ten soil traits it was possible to define wavelength domains were reflectance and concentrations are correlated to confidence levels from 95% to 99%. Partial Least Squares Regression (PLSR) analyses were performed comparing measured and predicted concentrations, and for fifteen out of 21 soil traits we found Pearson correlation coefficients r > 0.8. These preliminary results, which have to be validated, suggest that variations of concentration in the investigated soil attributes induce differences in reflectance that can be detected by spectroradiometry. Applications of these observations include the assessment of the chemical content of soils by spectroradiometry as a fast, low-cost alternative to chemical analytical methods.