Using Reflectance and Gray-Level Texture for Water Content Prediction in Grape Vines

Abstract

In this study, we used visible/near-infrared (Vis/NIR) hyperspectral imaging technology to measure the reflectance and gray-level texture features of grape leaf surfaces, and we predicted water content based on those features for more effective irrigation control. Grape vine specimens were potted in the actual field environment, and five levels of water treatment with two replicates were applied to create controlled water stresses. The reflectance and gray-level co-occurrence matrix (GLCM) texture features were used to develop partial least squares (PLS) models for water content prediction. The results showed that when using both reflectance and GLCM texture features, the results achieved a correlation coefficient (rp), root mean square error of prediction (RMSEP), bias, and residual predictive deviation (RPD) of 0.900, 0.826, -2.213e-04, and 2.084, respectively. The experimental results indicated that using a Vis/NIR hyperspectral imaging system could enable this combined method of reflectance and GLCM texture to predict water content of grape vines and be beneficial for grape vine management.