Traffic Noise Modeling under Mixed Traffic Condition in Mid-Sized Indian City: A Linear Regression and Neural Network-Based Approach
Rohit Patel, Prasoon Kumar Singh, Shivam Saw
Abstract
Noise pollution is a significant concern in urban settings, caused by traffic increases, urban expansion, and industrial activity. The transportation sector is a crucial contributor to overall noise pollution, particularly in India, where different vehicles ply the roads, resulting in highly fluctuating noise levels. Consequently, traffic noise modeling is essential for addressing this severe issue. The present study employs the MLR (Multiple Linear Regression) and Artificial Neural Network (ANN) approach to model and predict traffic-induced noise levels. The ANN approach outperforms the MLR technique. The architecture of the ANN model integrates different vehicle categories and average speeds as input, resulting in precise predictions. Evaluation of the model’s performance reveals an average Root Mean Squared Error (RMSE) of 0.204 and a high Coefficient of determination (R2) value of 0.93, emphasizing its accuracy. Similarly, in the case of MLR model the RMSE for the training and testing dataset are 1.55 and 1.69 dBA, respectively with R2 value of 0.84. Subsequently, sensitivity analysis highlights the substantial impact of 2-wheelers, tractors/trailers, and 3-wheelers on noise predictions. This study contributes valuable insights into noise management, urban planning, and sustainable development. It demonstrates the efficiency of the ANN approach in addressing complex noise pollution challenges, offering a path toward quieter and healthier urban environments.