Hyperspectral imaging and machine learning for monitoring grapevine physiology

Wine aroma is shaped by the wine’s chemical compositions, in which both grape constituents and microbes play crucial roles. Although wine quality is influenced by the microbial communities, less is known about their population interactions.

With climate change, the occurrence of wildfires has increased in several viticultural regions of the world. Subsequently, smoke taint has become a major issue, threatening the sustainability of the wine industry.

Aim: Through machine-learning modelling of plant water status from environmental characteristics, this work aims to develop a model able to predict grape phenolic composition in space and time to guide selective harvest decisions at the estate scale.

Nitrogen fertilization is an important practice to guarantee vineyards sustainability and performance over years, while ensuring berry quality. However, achieving a precise nitrogen fertilization to meet specific objectives of production is difficult. There is a lack of knowledge on the impact of nitrogen fertilizers (soil/foliar; organic/mineral) and different levels of fertilization on the interactions between carbon and nitrogen cycles within the vine. Crop models may be useful in that purpose because they can provide new insights of the effects of fertilization in carbon and nitrogen storage. The objective of this study is to build a model to simulate grapevine carbon and nitrogen content in vines to evaluate the impact of different fertilization strategies in vine growth and yield.

he intensification of t vineyard practices led to an impoverishment of the biological diversity. In vineyard management, the reflection to reduce pesticides uses concerns mainly the soil management of the vineyard, and often focuses on flora management in the inter-row.