FARMWISE

FARMWISE transforms the EU agricultural sector by empowering farmers and decision-makers with a novel decision support system, combining precision agriculture, Artificial Intelligence, and remote sensing.

FARMWISE provides new insights into water quality, quantity, soil health, and nutrient management. FARMWISE’s state-of-the-art framework fosters knowledge sharing between scientists, farmers, and policymakers in a co-creation environment (Systems Thinking). It consolidates existing collaborations and promotes new long-term cooperation between European organizations, including Water4All and Water Europe.

The FARMWISE project will develop improved technologies based on artificial intelligence (AI) for more efficient European water policy and decision-making founded on research-based technologies to solve the most burning water pollution and climate change problems. For this purpose, the FARMWISE consortium brings together the best European water, agricultural, climate, and AI researchers to handle the sustainability of water resources, the natural environment, and efficient agriculture in the highly diverse European landscape, given present and future climate change.

FARMWISE’s impact will increase interest and bond cooperation of quadruple helix stakeholders, including government, academia, industry, and civil society, for science-based solutions.

The main objective of this project is to provide farmers and policy-makers with valuable local and regional insights and decision-support systems, which will help to guide data-driven policy decisions in these crucial areas. The project will involve collecting, analyzing, assessing, and compiling large amounts of data from various sources, including the European Member States, the European Commission (EC), and other international organizations. The methodology will involve the development of a new data architecture, which will allow for the efficient processing of large volumes of data and the generation of high-quality outputs. Ethical ML algorithms will be thoroughly validated and generalized before application to extract meaningful insights in identifying underlying patterns and trends.

The decision support system, which is mainly being developed by Darmstadt University of Applied Sciences (HDA) under the leadership of Professor Nazemi, is, therefore, the central element of the project. It seamlessly combines artificial intelligence methods with interactive visualizations to create innovative visual analytics systems. These enable a user-friendly analysis of the agricultural system thinking, including environmental, economic, social, and technological factors. Policies not yet implemented through an integrated option analysis are evaluated through artificial intelligence models to reduce inappropriate decisions. Possible future scenarios and their impacts are also modeled using AI methods and visualized for the specific target groups. The focus of research is particularly on reducing factors that are harmful to the environment. Here, systems thinking is also applied so that factors influencing water, air, and land pollution are identified and ideally eliminated. However, the sustainable use of these environmental resources also plays a crucial role in the overall project. The technology developed by Darmstadt University of Applied Sciences is being developed as a modular component of the project’s AI framework.

FARMWISE evaluates, monitors, and implements gender and diversity balance in the consortium during the planned activities. All partners’ have established policies to foster gender equality, diversity, and inclusion for all employees.

The FARMWISE project is funded by the European Union under Grant Agreement number 101135533 in the Horizon Europe framework program (Research & Innovation Action – Zero Pollution). A total of 20 partners from 12 countries are involved. The funding is around six million euros, of which Darmstadt University of Applied Sciences will receive about €600 thousand.

This project has received funding from European Union’s Horizon Europe research and innovation programme under grant agreement No 101135533 . This publication refelcts only the author’s view and the European Union is not liable for any use that may be made of the information contained therein.