Project Duration

01.03.2026 - 28.02.2029

Summary

The proposed collaborative project aims to develop, test, and implement an innovative and practical integrated concept for sustainable plant protection in organic strawberry runner production. At its core is the integration of advanced AI-based digital image analysis - such as automated multispectral and RGB imaging using drones and camera systems - with novel biological plant protection strategies based on selected biological control agents (BCAs). This approach targets the effective, resource-efficient, and environmentally sound control of soil- and airborne pathogens such as Botrytis cinerea, Phytophthora spp., and Neopestalotiopsis spp. In coordinated work packages, standardized image data of strawberry runner plants will first be continuously collected on demonstration sites of project partners and under controlled conditions at the University of Hohenheim. These data will be analyzed using advanced deep learning models specifically trained and validated for runner plant production, enabling early, objective, and large-scale detection of disease and stress symptoms. In parallel, effective BCAs targeting the relevant pathogens will be identified in laboratory and greenhouse experiments. These will be comprehensively characterized - also in combination with reduced copper applications - regarding antagonistic activity, plant-strengthening and resistance-inducing effects, and practical applicability. Promising strains will then be further developed into stable, storable, and user-friendly formulations, produced at pilot scale using bioreactors. Large-scale field trials at demonstration farms and at the University of Hohenheim will evaluate the digital monitoring systems and integrated biological-chemical control strategies under real production conditions, including economic and ecological assessment and optimization for practical use. A strong emphasis is placed on knowledge transfer through targeted training and advisory services for farmers, consultants, and other stakeholders to foster adoption and dissemination. By combining cutting-edge research in AI, sensor technology, biotechnology, and ecology with practical implementation, the project offers significant potential for low-chemical, resilient specialty crop production and contributes to sustainable, climate-adapted, and socially accepted agricultural systems.