Machine Learning Prediction of the Long-Term Environmental Acoustic Pattern of a City Location Using Short-Term Sound Pressure Level Measurements

To manage noise pollution, cities use monitoring systems over wireless acoustic sensor networks. These networks are mainly composed of fixed-location sound pressure level sensors deployed in outdoor sites of the city for long-term monitoring. However, due to high economic and human resource costs, it is not feasible to deploy fixed metering stations on every street in a city. Therefore, these continuous measurements are usually complemented with short-term measurements at different selected locations, which are carried out by acoustic sensors mounted on vehicles or at street level. In this research, the application of artificial neural networks is proposed for estimation of the long-term environmental acoustic pattern of a location based on the information collected during a short time period. An evaluation has been carried out through a comparison of eight artificial neural network architectures using real data from the acoustic sensor network of Barcelona, Spain, showing higher accuracy in prediction when the complexity of the model increases. Moreover, time slots with better performance can be detected, helping city managers to deploy temporal stations optimally.