UAV multispectral imagery and deep learning algorithms to map water stress in vineyards

C. Poblete-Echeverría, T. Chambers, L. Luus, A. Berry, D. Els, M. Vivier
Modern viticulture aims to maximize production while maintaining quality standards, keeping costs as low as possible and preserving the environment. In this context, water is the key factor affecting the quality and quantity of wine grapes. In practice, stem water potential is one of the most used in-situ methods, to assess water stress in vineyards. However, this measurement is acquired on a per-plant basis and does not account for the assessment of vine water status spatial variability. The development of novel methods to assess water stress in a spatial context are necessary to improve water management in heterogeneous vineyards. In this sense, remote sensing UAV technology together with machine learning techniques can provide an alternative to traditional in situ water status measurements. To test this premise a field experiment was carried out in a commercial vineyard in the Stellenbosch area, South Africa. Individual vine images obtained from aerial multispectral and RGB imagery were tested to estimate stem water potential using common artificial neural networks (ANN) and deep learning algorithms (convolutional neural networks – CNN). This exploratory study demonstrates the potentiality of UAV multispectral and RGB imagery to map water stress in vineyards and identify sectors of water stress within the vineyard for optimal irrigation management.
Poblete-Echeverría, C., Chambers, T., Luus, L., Berry, A., Els, D. and Vivier, M. (2023). UAV multispectral imagery and deep learning algorithms to map water stress in vineyards. Acta Hortic. 1370, 17-22
DOI: 10.17660/ActaHortic.2023.1370.3
https://doi.org/10.17660/ActaHortic.2023.1370.3
vegetation indexes, image segmentation, neural networks, spatial variability, vine water status
English

Acta Horticulturae