Construction of surrogate model ensembles with sparse data

Construction of neural network ensembles (NNE) with sparse data requires comprehensive performance measure, multi-stage validation and usually a large member size. This paper presents a hybrid method which takes a selective optimization approach and is characterized with several novel features. First, candidate ensembles are widely explored using a multi-objective genetic algorithm. Secondly, the best local ensembles registered with each distinct objective weighting are determined based on the multi-stage validation results. Finally, a large global ensemble is formed by combining several local ensembles and virtually evaluated in the voids of possible parameter space. The demonstration of the proposed method is presented in a case study in which sparse data from FEA simulations are used to construct NNE for expandable pipe design, a novel application in oil and gas industry.