In this article we cover two problems that often farmers have to face. The first one is to generate a partition of an agricultural field into rectangular and homogeneous management zones according to a given soil property, which has variability in time that is presented by a set of possible scenarios. The second problem assigns the correct crop rotation for those management zones defined before. These problems combine aspects of precision agriculture and optimization with the purpose of achieving a site and time specific management of the field that is consistent and effective in time for a medium term horizon. Thus, we propose a two-stage stochastic integer programming model with recourse that solves the delineation problem facing a finite number of possible scenarios, after this we propose a deterministic crop planning model, and then we combine them into a new two-stage stochastic program that can solve both problems under ucertainty conditions simultaneously. We describe the proposed methodology and the results achieved in this research.