Résumé
The optimal allocation of crops to different parcels of land is a problem of paramount practical importance, not only to improve production, but also to address the challenges posed by climate change. However, this optimization problem is inherently complex, characterized by a vast search space that renders traditional optimization techniques impractical without oversimplified assumptions. Compounding this challenge, climate change introduces conflicting objectives, as solutions aiming to just maximize total yield may be more susceptible to extreme weather events, and thus obtain more unpredictable year-by-year outcomes. In order to tackle this complex optimization problem, we propose a multi-objective approach, simultaneously maximizing the overall yield, minimizing the year-on-year yield variance, and minimizing the total cultivated surface. The approach exploits an established multi-objective evolutionary algorithm, and employs a machine learning model able to predict yield from weather and soil conditions, trained on historical data, making it possible to tackle allocation problems of large size. An experimental evaluation focusing on the allocation of soybean crops in the European continent for the years 2000-2023 shows that the proposed methodology is able to identify different trade-offs between the conflicting objectives, that an expert analysis later reveals to be realistic and meaningful for driving stakeholder decisions.