Machine Learning-based GIS Model for 2D and 3D Vehicular Noise Modelling in a Data-scarce Environment

Aug 6, 2026

Upload by Ivy

Vehicular traffic drives economic activity while generating frictional noise that degrades urban livability. Road traffic acts as a dominant noise source, and traditional regression-based approaches mainly yield 2D noise maps. This study investigates 2D and 3D GIS-driven visualization of noise using limited samples by building two models: a 2D road noise model and a 3D building noise model, which are combined into a comprehensive 3D noise map. Machine learning methods (ANN, RF, SVM) are compared via R, R² and RMSE, with ANN performing best and RF outperforming SVM, and GIS supports weekday morning and afternoon average noise assessment in the study area.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

I. Introduction

Noise generation and need for prediction

Limits of 2D noise mapping in dense high-rise areas

Motivation for 3D noise maps and GIS applications

INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS Research Article | DOI: 10.2478/ijssis-2024-0022 Issue 1 | Vol. 17 (2024) Machine Learning-based GIS Model for 2D and 3D Vehicular Noise Modelling in a Data-scarce Environment Biswajeet Pradhan1,*, Ahmed Abdulkareem Ahmed Aldulaimi1, Shilpa Gite2,3 , Abdullah Alamri4 and Subhas Chandra Mukhopadhyay5 1Center for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Civil and Environmental Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney, Australia 2Computer Science and Information Technology Department, Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune 412115, India 3Symbiosis Centre of Applied AI (SCAAI), Symbiosis International (Deemed) University, Pune 412115, India 4Department of Geology and Geophysics, College of Science, King Saud University, Riyadh, Saudi Arabia 5School of Engineering, Macquarie University, NSW 2109 Australia *E-mail: biswajeet.pradhan@uts. [edu.au](edu.au), [biswajeet24@gmail.com](biswajeet24@gmail.com)[ ](biswajeet24@gmail.com)Received for publication June 10, 2024. Abstract Vehicular traffic significantly contributes to economic growth but generates frictional noise that impacts urban environments negatively. Road traffic is a primary noise source, causing annoyance and interference. Traditional regression models predict twodimensional (2D) noise maps, but this study explores the impact and visualization of noise using 2D and three-dimensional (3D) GIS (Geospatial Information Systems) functionalities. Two models were assessed: (i) a 2D noise model for roads and (ii) a 3D noise model for buildings, utilizing limited noise samples. Combining these models produced a comprehensive 3D noise map. Machine learning (ML) models—artificial neural network (ANN), random forest (RF), and support vector machine (SVM)—were evaluated using performance measures: correlation (R), correlation coefficient (R²), and root mean square error (RMSE) . ANN outperformed others, with RF showing better results than SVM. GIS was applied to enhance the visualization of noise maps, reflecting average traffic noise levels during weekday mornings and afternoons in the study area. Keywords 2D noise model, 3D noise model, artificial neural network, random forest, support vector machine I. Introduction Despite the fact that road traffic is inevitable, its annoying sound called noise has continued to draw global attention and possible remedial measures [1–3] . Noise pollution has attracted great interest over the decade [4] . Road traffic is the most widespread source of noise in many countries, and it is the most prevalent cause of annoyance and interference [5–7] . Traffic noise is generated from engine sound and frictional contact between the ground and the vehicle tires [8] . Noise generated from traffic depends on traffic volume, vehicular speed, vehicular class (heavy duty or light cars), and the type of roads [9–13] . Noise prediction is necessary where a future situation cannot be ascertained [14–16] . More so, field measurement of noise pollution seems impractical and difficult Open Access. Published by Sciendo. 1 © 2024 Pradhan et al. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 License [https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by-nc-nd/4.0/](licenses/by-nc-nd/4.0/) Machine learning-based GIS model for 2D and 3D vehicular noise modelling in a data-scarce environment: Pradhan et al. since numerous points are required to be measured to ascertain the true position of the noise situation [17–20] . So, a considerable amount of work has been carried out with the aim of developing models to predict noise levels generated from road traffic. Urban noise maps have been developed in many countries. Most noise maps were produced in

FAQs

Why is vehicular noise modelling important in urban environments?

Vehicular traffic generates frictional noise that negatively affects urban conditions. Road traffic is a primary source, causing annoyance and interference, so accurate prediction supports better planning and mitigation.

How does the study structure its 2D and 3D noise modelling approach?

Two models are assessed: a 2D noise model for roads and a 3D noise model for buildings. Their combination produces a comprehensive 3D noise map with enhanced visualization.

Which machine learning model performs best for the noise prediction task?

Artificial neural network (ANN) outperforms the other evaluated methods. Random forest (RF) shows better performance than support vector machine (SVM) based on R, R², and RMSE.

Aug 6, 2026

Upload by Ivy