Optimal Irrigation Allocation for Large-Scale Arable Farming

In this article, we propose an optimization framework that computes the allocation of irrigation machinery (agents) and water to arable fields by maximization of a profit function in a receding horizon fashion using realistic models for crop growth dynamics. A key advantage of the proposed framework is that it can use many of the existing crop growth models for prediction and hence can be applied to a wide variety of crops, soils, locations, and weather patterns. The output of the framework is a feasible allocation of agents to fields and delivery of water over the growing season, in such a way that it allows for practical implementation by farmers. The allocation is feasible as the framework takes into account relevant real-world constraints such as the water-carrying capacity and application rates of the agents, but also traveling costs and refilling of water at designated locations. A realistic case study using validated crop-growth models by agronomists is used to show the strengths and the generality of the framework.