In this paper we propose a model for the design of an optimal network integration of multisite refinery and petrochemical systems under uncertainty. The proposed model was formulated as a two-stage stochastic mixed-integer problem with the objective of minimizing the refining cost over a given time horizon and maximizing the added value by the petrochemical network. Uncertainties considered in this study were in terms of imported crude oil price, refinery product price, petrochemical product price, refinery market demand, and petrochemical lower level product demand. The proposed method adopts the sample average approximation (SAA) method for scenario generation and optimal gap statistical bounding. The model performance was tested on an industrial case study of multiple refineries and a polyvinyl chloride (PVC) complex.