@article {Baclet:2023:0736-2935:6040,
title = "A machine learning- and compressed sensing-based approach for surrogate modelling in environmental acoustics: towards fast evaluation of building fa{\c{c}}ade road traffic noise levels",
journal = "INTER-NOISE and NOISE-CON Congress and Conference Proceedings",
parent_itemid = "infobike://ince/incecp",
publishercode ="ince",
year = "2023",
volume = "265",
number = "1",
publication date ="2023-02-01T00:00:00",
pages = "6040-6051",
itemtype = "ARTICLE",
issn = "0736-2935",
url = "https://ince.publisher.ingentaconnect.com/content/ince/incecp/2023/00000265/00000001/art00006",
doi = "doi:10.3397/IN_2022_0898",
author = "Baclet, Sacha and Venkataraman, Siddharth and Gomez, Erik and Bouchouireb, Hamza",
abstract = "State-of-the-art urban road traffic noise propagation simulation methods such as the CNOSSOS-EU framework rely on ray tracing to estimate noise levels at specific locations on fa{\c{c}}ades, so-called receiver points; this method is computationally expensive and its cost increases
with the number of receiver points, which limits the spatial accuracy of such simulations in the context of real-time or near-real-time urban noise simulation applications. This contribution aims to investigate the applicability of multiple data-driven methods to the surrogate modelling of
traffic noise propagation for fast fa{\c{c}}ade noise calculation as an alternative to these traditional, ray-tracing-based methods. The proposed approach uses compressed sensing to select a small subset of receiver points from which the data set of the entire fa{\c{c}}ade may be reconstructed,
associated with a Kriging model and neural networks, used to predict noise levels for these sensors. The prediction performance of each of these steps is evaluated on an academic test case, with two levels of complexity based on the dimensionality of the problem.",
}