A combined variational encoding and optimization framework for design of the water-energy-food nexus

Nowadays, water, energy and food supplies are among the main problems faced by humanity. These issues are strongly linked and must be addressed by considering their interactions. The linkage is formulated as a nonlinear multiobjective optimization problem. Moreover, the solution can benefit from large databases that lead to the development of surrogate models. In this work, surrogate models are used to incorporate recorded input information. To avoid large-scale models, we use generative deep learning strategies to build low-order models. The surrogate models are coupled to the optimization problem to render optimal operation and structure of the nexus. The results show that the reduced model benefits the performance of the optimization problem. Furthermore, we implemented a clustering algorithm to reduce the number of solutions found by the multiobjective approach. The proposed methodology establishes a contribution for the integration of traditional optimization and deep learning tools to address the complex interactions of the water-energy-food nexus.