Physiological variable predictions using VIS–NIR spectroscopy for water stress detection on grapevine: Interest in combining climate data using multiblock method

Abstract

In recent years, climate fluctuations have been increasingly extreme, affecting agricultural production. The development of digital agriculture driven by new intelligent sensors is one of the privileged paths to improve farm management. Assessing transpiration E and stomatal conductance gs in real time with optical instruments is a real challenge to detect water stress. In this study, the objective is to evaluate VIS–NIR spectroscopy to predict transpiration E and stomatal conductance gs of grapevine plants (Vitis vinifiera L.). For this purpose, a water stress gradient was obtained using vine pots of three varieties (Syrah, Merlot, Riesling) tested under two water conditions where precise monitoring of physiological variables has been carried out. Hyperspectral images were acquired to form a spectral database and a weather station provided radiation (Rg), relative humidity (RH), temperature (Ta) and wind speed (Ws). First, Partial Least Squares (PLS) models were established to relate spectral data to physiological variables. Then, Sequential Orthogonalized-Partial Least Squares (SO-PLS) was used to predict these physiological variables with two blocks: spectral and climate data. PLS models are obtained for gs (R2= 0.656, bias = 8.76 mmol.m−2.s−1, RMSE = 64.7 mmol.m−2.s−1) and E (R2= 0.625, bias=-0.02 mmol.m−2.s−1, RMSE = 0.67 mmol.m−2.s−1). For E, improved results (R2= 0.699, bias = 0.055 mmol.m−2.s−1, RMSE = 0.614 mmol.m−2.s−1) are obtained by using climate data with SO-PLS. Generic PLS models achieved good predictive quality despite different coloured berry varieties. Quality of these prediction models could be improved by defining varietal models on a larger data set. Merging spectral data with climate data improves prediction quality of transpiration variable providing insights by adding further information with the aim of improving predictive qualities.