Estimating grapevine water status: a combined analysis of hyperspectral image and 3d point clouds

Abstract

Context and purpose of the study

Mild to moderate and timely water deficit is desirable in grape production to optimize fruit quality for winemaking. It is crucial to develop robust and rapid approaches to assess grapevine water stress for scheduling deficit irrigation. Hyperspectral imaging (HSI) has the potential to detect changes in leaf water status, but the robustness and accuracy are restricted in field applications. The varying leaf orientations can significantly affect how light interacts with the plant, ultimately influencing the reflectance properties. This study focused on developing an approach for detecting grapevine water status using HSI and 3D data. Leaf orientation parameters derived from 3D point clouds were integrated with spectral signatures to address the spectral variance caused by variations in leaf orientation. A water status assessment model was developed based on multiblock partial least squares (MBPLS) to estimate leaf water potential (Ψ_L) using spectral signatures and leaf orientation parameters.

Material and methods

HSI and 3D point clouds of selected leaves were captured simultaneously in a vineyard during the 2021 growing season, and Ψ_L was measured as the groundtruth to assess the model performance. Mean spectral reflectance was derived from the hyperspectral images, while leaf orientation parameters were extracted from 3D point cloud data. The dataset was split randomly into 70% training/calibration and 30% test datasets.

Results

The test result shows that the model estimated the Ψ_L with R² = 0.8942, RMSE = 0.1153 MPa and MAE = 0.0894 MPa. The leaf orientation parameters derived from 3D point clouds acted as an enhancing component that explained the spectral variance caused by variations in leaf orientation and improved the underlying relationship between spectral reflectance and vine water status.