Economic valuation of traffic noise based on artificial neural networks

Abstract

The poster presents a new approach to value the willingness to pay to reduce road noise annoyance using an artificial neural network (ANN) ensemble. The model predicts, with adequate precision and accuracy, a willingness to pay range from subjetctive assessments of noise, a modeled noise exposure level, antd both demographic and socio-economic conditions. The results were compared with an ordered probit econometric model in terms of the performance mean relative error, and obtained a 85% better accuracy. The results of this study show that the model reach an adequate generalization level and can be applicable as a tool for valuing noise from transportation in order to obtain financial resources for action plans.