LAUSR

Abstract The productivity and financial success of large-scale arable farming operations depends highly on how effectively resources are distributed among fields. Therefore, it is of interest to develop methods to determine (near optimal) resource inputs. In this paper we focus on computing the optimal irrigation policy for large-scale arable farming operations, where the number of irrigation machinery is much smaller than the number of fields that require irrigation inputs. We propose a model predictive control (MPC) framework that simultaneously computes the optimal division of irrigation over the fields and which irrigation machines should be allocated to which fields, such that the profit at the end of the season is maximized. The fact that the optimization of irrigation and allocation of irrigation machinery is done simultaneously makes our approach vastly different from strategies available in the literature. Another important novelty of our work is that we link short-term effects of crop growth to long-term effects on profit. The proposed framework has reasonable computation times when optimizing on a daily basis over many fields and irrigation machines and guarantees a feasible solution. The main principles of our approach are more widely applicable. Using simulations we demonstrate the robustness of the scheme with respect to changes in weather and benchmark it with respect to a heuristic approach.