Meta-modeling for urban noise mapping

Abstract

Urban noise mapping generally consists of simulating the emission and attenuation of noise in an area by following rules such as common noise assessment methods. The computational cost makes these models unsuitable for applications such as uncertainty quantification, where thousands of simulations may be required. One solution is to replace the model with a meta-model that reproduces the expected noise levels with highly reduced computational costs. The strategy is to generate the meta-model in three steps. The first step is to generate a training sample exploring the large dimension model's inputs set. The second step is to reduce the dimension of the outputs. In the third step, statistical interpolators are defined between the projected values of the training sample over the reduced space of the outputs. Radial basis functions or kriging are used as interpolators. The meta-model was built using the open source software NoiseModelling. This study compares the proximity of the meta-model outputs to the model outputs against the reduced basis, the class of the kriging covariance function, and the training sample size. Simulations using the meta-model are more than 10 000 times faster than the model while maintaining the main behavior.

Seeking the Nexus Between Building Acoustics and Urban Form: A Systematic Review

“…That study offers key engineering aspects with themes from’10 questions’ surrounding the importance of sound predictions and computations. Lesieur et al [ 12 ] created noise maps with the Noise Modelling software and obtained statistical output in Lorient, France, using the Kriging method. That study found the method considerably faster than the other models by testing physical modeling, with a 1.58 dB mean error.…”

The Internet of Sounds: Convergent Trends, Insights, and Future Directions

“…Second, noise maps produced by sound propagation techniques and ASNs have different biases. Considering both source of information helps reduce estimation biases in order to produce more reliable estimates [147]. Third, information about sources of interest, vehicle, humans, animals are very useful for prediction high-level attributes of the sound environment such as its pleasantness [148].…”

Predicting traffic induced noise using artificial neural network and multiple linear regression approach

“…Noise Modelling, an open-source software, was used to create the meta-model. The meta-model simulations are almost 10,000 times faster than the model while keeping the core characteristics [36]. To investigate traffic noise at roundabouts and signalised intersections, Li et al (2017) employed a traffic noise simulation method based on microscopic traffic simulation.…”

“…Lesieur et al (2020) [36] Traffic topography, meteorological data using noise modeling software Singh et al (2022) [27] Monte Carlo simulation, traffic composition Li et al (2017) [37] Light vehicle, medium vehicle, heavy vehicle, their acceleration using microscopic traffic simulation…”