The decision-making of complex problems, such as epidemics monitoring and control, involves multiple heterogeneous data and spatial and temporal aspects. Most problems cannot be reduced to one objective, characterized as multi-criteria decision-making (MCDM) problems. Adding temporal and spatial aspects further increases the complexity of addressing those problems. This paper proposed a framework that uses evolutionary algorithms and map algebra for addressing spatial and temporal multidimensional complex problems. It was evaluated in a case study of dengue and tuberculosis diseases in an urban environment, considering multi-resolution data and a genetic algorithm. Several analyses were conducted, generating maps and information essential to generate insights into the problem and a better understanding of the spatial relations between the variables. The framework and the code implemented could be applied to different problems, spatial resolutions, and objectives.