Traffic Noise Modeling Using Artificial Neural Network: A Case Study

The heterogeneous features of traffic noise, together with the characteristics of environmental noise, with their great spatial, temporal, and spectral variability makes the matter of modeling and prediction a very complex problem. A need is being felt to develop a traffic noise prediction model suitable for the Indian condition. The present work represents a traffic noise prediction model taking Patiala–Sangrur highway as a representative/demonstrative site. All the measurements of noise levels were made at selected points around the highway at different time on number of days in a staggered manner in order to account for statistical and temporal variations in traffic flow conditions. The noise measurement parameters recorded were traffic volume, i.e., number of vehicles passing through in a particular time period, vehicle speed, and the noise descriptors recorded were the equivalent noise level (L_eq) and percentile noise level (L₁₀). Artificial neural network (ANN) approach has been applied for traffic noise modeling in the present study. After training and testing of the ANN, it was found that the values of correlation coefficient (R) were 0.9486, 0.9577, and 0.9255 for the training, validation, and testing samples, respectively, and the percentage error varied from −0.19 to 0.64 and 0.54 to 0.99 for L_eq and L₁₀. Therefore, a good correlation coefficient and less percentage error between experimental and predicted output obtained is an indication of prediction capability of neural network.