Research

The project addresses water scarcity in agriculture, focusing on vineyards, by developing innovative strategies and technologies to optimize water use. It aims to create advanced water consumption models and a low-cost, handheld 3D imaging system that integrates multimodal data (e.g., thermal, RGB, and multispectral imaging) to measure key plant traits like leaf area, grape cluster weight, and water consumption. Leveraging cutting-edge machine learning techniques, such as zero-shot learning and domain adaptation, the system will enable precise, non-destructive, and dynamic measurements directly in the field. This innovation combines 3D reconstruction with multimodal data to improve water management models, reduce irrigation reliance, and promote sustainable viticulture practices. The project also investigates the impact of canopy management on water use and yield, with potential applications to other crops like tomatoes and orchard trees. Current water budget models rely on climatic variables and static crop coefficients, failing to account for site-specific conditions, dynamic canopy changes, and agronomic practices. Existing methods for estimating leaf area are labor-intensive, destructive, and lack the resolution needed for dynamic modeling. While 3D reconstruction technologies (e.g., LiDAR, stereo cameras) show promise, they are expensive, complex, and sensitive to environmental conditions. Additionally, integrating multimodal data into 3D models is challenging due to issues like image registration and parallax effects. This project addresses these gaps by developing a scalable, multimodal 3D canopy reconstruction system that integrates plant-specific traits into water consumption models, enabling more accurate and sustainable water management in vineyards and other agricultural systems.

Iron (Fe) is a vital micronutrient for plants, playing a key role in processes like chlorophyll production, photosynthesis, respiration, and nitrogen fixation. When plants lack iron, they suffer from yellowing leaves, reduced growth, and significant losses in yield and quality. For grapevines—a cornerstone of global agriculture and winemaking—iron availability is especially critical. As perennial grafted plants, grapevines depend heavily on their rootstocks to withstand environmental stresses and maintain nutrient balance. The IronMan project is exploring the intricate relationship and interaction between iron and nitrogen uptake in grapevine rootstocks. Nitrogen, whether in the form of nitrate or ammonium, not only affects iron availability but also influences how plants absorb, store, and transport this essential nutrient. While it’s long been known that different grapevine rootstocks exhibit varying levels of stress tolerance, the underlying mechanisms remain a mystery. Through hydroponic experiments, the IronMan project will investigate how grapevine rootstocks adapt to changing nutrient conditions and stress. By simulating real-world challenges, researchers aim to uncover the strategies rootstocks use to maintain nutrient balance and thrive under pressure. The findings will pave the way for practical solutions to improve the nutritional health of grapevines by adapting currently available recommendations for fertilizer usage.

Berry Shrivel (BS, Traubenwelke) is a sugar accumulation disorder of grapevine of unknown causes, having a great negative impact on grape quality and incalculable risks for yield losses, and for which no reliable curative practices are available. The Austrian autochthonous red wine cultivar Blauer Zweigelt is heavily affected by BS, although the appearance of BS symptoms as well as their intensity can change from year to year making it unpredictable and hard to quantify. This has led to winegrowers avoiding planting Blauer Zweigelt with a consequent loss of typicity for the Austrian wine landscape. Therefore, the BAISIQ project aims to develop a reliable and standardized method to estimate BS occurrence in vineyards, and as a consequence yield loss. To do so, the BAISIQ partnership includes experts in the fields of grapevine biology working on BS, explainable artificial intelligence (AI), and Image-based yield Quantification on the proximal and remote scale. The interdisciplinary group of plant physiologists, computer scientist and technicians will apply multi-sensor technologies, machine learning algorithms and remote sensing equipment to achieve both, scientific and applied aims of BAISIQ. Ultimately, we aim to quantify BS in vineyards, to develop a service or a usable application, and to start establishing a BS database. Thereby we will adapt and further establish current grape cluster recognition machine learning methods and translate this knowledge into a high-throughput remote sensing application. A pre-symptomatic BS diagnostic would be of major relevance and highly innovative, and the knowledge on the expected yield loss would empower winegrowers to adapt their harvesting dates, cellar capacities and targeted wine styles. Furthermore, the innovative and pioneering approach developed in BAISIQ combining multi-sensor phenotyping and machine learning AI could be applied to other relevant features in viticulture.