PRESTO: Predictive REcommendation of Surrogate models To approximate and Optimize

Surrogate models are used to map input data output when the actual relationship between two is unknown or computationally expensive evaluate. Many techniques exist for surrogate modeling; however, selecting suitable a given application remains an open challenge. This work describes PRESTO, Random Forest classifier-based tool, recommend appropriate modeling dataset surface approximation and surrogate-based optimization, using attributes calculated only data. The tool identifies with accuracy of 91% precision 90% optimization 98% 99%. PRESTO was tested on generated from high fidelity process model cumene production process. Its performance this case study comparable training enables computational time savings forms by avoiding trial-and-error methods.