MSc Industrial Engineering
«Delineation of rectangular zones of management and crop planning under conditions of uncertainty in soil properties»
This thesis covers two common problems that farmers have to face: the first one is generating a partition of an agricultural field into rectangular and homogeneous management zones or quarters according to a given soil property, which has variability in time that is presented as a number of possible scenarios. This is a problem that combines aspects of precision agriculture and optimization with the purpose of achieving a site and time specific management of the field properties that is consistent and effective in time for a medium term horizon. The second one consists in assigning correctly a crop rotation for a specific period for those management zones defined previously, the objective is to maximize the productivity of the quarters and also cover some necessities, for example, a specific demand for a specific crop. These two problems are treated independently in two steps, the first step solves the partitioning problem and when the decision is taken is possible to choice what crop will be planted in each zone. However, this thesis propose a two stage integer stochastic linear programming model with resource to solve a combined problem to face both problems in only one time, obtaining good results. In this work the proposal model, the methodology and results obtained are shown.