Sustainable Cultivation Systems for Sugar Beet - Innovations and Artificial Intelligence

The coal phase-out and climate change pose major challenges for the Central German mining region in Saxony-Anhalt. Agriculture must adapt to ensure long-term resource efficiency and sustainability. For sugar beet cultivation, this means increasing water scarcity, erosion risks due to extreme weather events, and growing demands for transparent life cycle assessments—especially for calculating and reducing greenhouse gas (GHG) emissions. Ecological and economic resilience in agricultural systems can only be achieved through site-specific, integrated measures. However, assessing environmental indicators such as GHG emissions, water use, and eutrophication remains data- and cost-intensive, creating a barrier for many farms. Digital decision support and artificial intelligence (AI) offer promising solutions by simplifying the evaluation and optimization of farm processes—such as reducing evapotranspiration or input use—and enabling long-term sustainability and climate goals like carbon neutrality. The joint project “Sustainable Sugar Beet Cropping Systems – Innovations and Artificial Intelligence” (ZAZIkI) aims to develop, test, and evaluate practical, region-specific adaptation strategies for sugar beet cultivation. It addresses the needs of large-scale farms in an expansive agricultural landscape and leverages digital technologies focused on smaller units (e.g., field segments), allowing automation. Around 45,000 hectares of sugar beets are currently cultivated in Saxony-Anhalt, with 12,000 hectares in the Central German region. Processing takes place at two sugar factories (Zeitz, Könnern). In addition to securing the viability of sugar beet cultivation, the project will generate expertise and services for the local agri-tech and service sectors. ZAZIkI contributes to transforming cropping systems by making digital tools accessible, improving environmental performance, and supporting agriculture in achieving future-proof sustainability.