Evolutionary algorithms: Overview and applications to European transport

Abstract

The present paper aims to analyse the research potential of Evolutionary Algorithms (EAs) in the light of their possible applications in the space-economy. For this purpose the first part of the paper will be devoted to an overview and illustration of EAs, also in comparison with other recent tools emerging form bio-computing, like Neural Networks (NNs). The second part of the paper will then focus on empirical applications concerning analyses and forecasts of European freight transport flows (at a regional level). In this context, the results stemming from an integrated approach combining EAs with NNs will be compared with those from conventional methodologies, like logit models, as well as with the "usual" NN models. We will analyze the sensitivity of various results by using different environmental policy on scenarios on European transport. The empirical experiments highlight the advantages and limitations of these approaches from both a methodological and empirical viewpoint, by offering a plausible range of values of outcomes that may be useful for planners and operators in this field.