Traffic Noise Prediction Model Research Articles

Statistical Modelling of Traffic Noise Using Smart PLS-SEM In Urban Roads

The objectives of this study are to assess the traffic noise levels in Shah Alam, Selangor, Malaysia, and to propose traffic noise model among influential factors. Five factors and 20 attributes were measured at three locations using a sound level meter and analyzed using the PLS-SEM approach. The results of this study showed that high traffic noise levels on urban roads exceeded the maximum permissible limit of 60 dBA during the day, according to Malaysian guidelines. However, the integrated traffic noise prediction model approach has specific indirect effects: built environment -> climate conditions -> traffic flow.

Traffic noise prediction model using GIS and ensemble machine learning: a case study at Universiti Teknologi Malaysia (UTM) Campus.

This study represents a pioneering effort to integrate geographic information systems (GIS) and ensemble machine learning methods to predict noise levels on a university campus. Three ensemble models including random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGB) were developed to predict traffic noise based on data collected over a 4-week period at the Universiti Teknologi Malaysia (UTM) campus. Noise measurements were obtained during peak morning hours (7:30 to 9:30 a.m.) on weekdays within the UTM campus in Johor. Additional predictor variables, including data from the digital elevation model (DEM) and land use, were incorporated to capture the complex nonlinear relationships influencing noise levels. The models were optimized through hyperparameter tuning, resulting in high precision, as evidenced by performance metrics such as the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE). The XGB model emerged as the most accurate, with R2 = 0.96, MAE = 0.9, and MSE = 0.3. Noise maps generated using the inverse distance weighting (IDW) interpolation technique highlighted the spatial distribution of noise levels, classified into five classes considering WHO standards. The findings identified distance from roads, the number of light vehicles, and proximity to green areas as the most significant predictors. However, challenges remain in accurately predicting noise levels associated with other predictors. The outcomes of the study indicate the superior performance of the XGB model compared to the GB and RF models. The study recommends several measures to manage and control noise pollution on the UTM campus, including raising awareness, regulating and enforcing vehicle speed limits, reevaluating land use, installing sound insulation systems, and planting trees and vegetation buffer zones around and within educational buildings.

Simplified method to create vehicle sound model for road traffic noise simulation-By using sound limit value of noise regulation

Road traffic noise prediction model is used to evaluate and analyze current situation and predict future prospect for road traffic noise. The current models such as CNOSSOS-EU and ASJ-RTN (Acoustical Society of Japan-Road traffic noise prediction model) define the fixed vehicle sound power level formulas. There are vehicle sound formulas for limited vehicle categories, but they are not enough to analyze influence of emitted sound from the vehicles in detail. Looking at an actual road, there are several vehicle categories and old vehicles which mean different regulation stages (e.g. sound limit). Since it is not easy to update the vehicle sound formulas with current methodology such as ISO11819-1 (Measurement of the influence of road surfaces on traffic noise -Part1 Statistical Pass-by method), we have proposed the method for creating vehicle sound formulas with less measurements in proving ground. Furthermore, when test vehicles are difficult to obtain as in the case of vehicles that comply with older regulations, we would like to propose an approximated method for practical use from sound limit in vehicle regulation and database in this paper. And the proposed method is validated comparing with the precise model.

Road traffic noise prediction model "ASJ RTN-Model 2023" proposed by the Acoustical Society of Japan - Part 2: Structure-borne noise of viaducts

The latest road traffic noise prediction model "ASJ RTN-Model 2023" was published by the Research Committee on Road Traffic Noise of the Acoustical Society of Japan (ASJ) in this April. In this new version, the method for predicting structure-borne noise from viaducts was also updated. Specifically, the calculation method was updated to separate direct sound and ground-reflected sound, and the sound power levels on structure-borne noise from viaducts have revised accordingly based on the latest research results. This paper describes the method for measuring structure-borne noise, the latest values of noise emission and its frequency characteristics, and the method for predicting structure-borne noise.

Road traffic noise prediction model "ASJ RTN-Model 2023" proposed by the Acoustical Society of Japan - Part 1: Framework of the calculation model

The Acoustical Society of Japan (ASJ) has had the Research Committee on Road Traffic Noise to develop a prediction model for road traffic noise for more than 50 years. As a result of the continuous research activities, a new version of model, "ASJ RTN-Model 2023", was published in this April. It is an upgrade version of the previous model, "ASJ RTN-Model 2018", proposed in 2019. In developing the latest version, existing knowledge was widely taken into account, in particular, the sound power levels of road vehicles under acceleration running conditions and calculation methods for sound propagation were improved in wide range. This new model is introduced in three papers with the same main title in this congress. In this paper, the framework of the model, the general procedure of prediction calculation, and the outlines of sound emissions and the calculation equations of sound propagation are presented.

Road traffic noise prediction model "ASJ RTN-Model 2023" proposed by the Acoustical Society of Japan -Part 3: Case studies of prediction accuracy on Japanese highways and roundabouts

The Acoustical Society of Japan (ASJ) has published a new version of road traffic noise prediction model "ASJ RTN-Model 2023" this April. Some case studies of the prediction accuracy, namely the correspondence between the predicted and measured value, using the new model is presented in this paper, as one of the three papers with same main title in this congress. The case study on Japanese highways was examined using the measurement at the straight sections. The LAeq at the measurement point was calculated using obtained traffic data for each lane and the age of pavement. The mean difference between predicted and measured LAeq were less than 3 dB. The case study at the vicinity of roundabouts was also examined using the prediction method newly introduced in the ASJ RTN-Model 2023. The case measurements were conducted at two round abouts in Japan, and the predicted LAeq corresponded to within 3 dB of the measured values.

Road traffic noise prediction model based on artificial neural networks

This paper proposes a model based on machine learning for the prediction of road traffic noise for the city of Bogota-Colombia. The input variables of the model were: vehicle capacity, speed, type of flow and number of lanes. The input data were obtained through measurement campaigns in which audio and video recordings were made. The audio recordings, made with a measuring microphone calibrated at a height of 4 meters, made it possible to calculate the noise levels through software processing. On the other hand, by processing the video data, the capacity, and speed of the vehicle were obtained. This process was carried out by means of a classifier trained with images of vehicles taken in the field and free databases. In order to determine the machine learning algorithm to be used, five models were compared, which were configured with their respective hyperparameters obtained through mesh search. The results showed that the Multilayer Perceptron (MLP) regression had the best fit with an MAE of 0.86 dBA for the test data. Finally, the proposed MLP regressor was compared with some classical statistical models used for road traffic noise prediction. The main conclusion is that the MLP regressor obtained the best error and fit indicators with respect to traditional statistical models.

Validation of Road Traffic Noise Prediction Model (Stop and Go) for Road Traffic Conditions of Delhi, India

Validation of Road Traffic Noise Prediction Model (Stop and Go) for Road Traffic Conditions of Delhi, India

Random effect generalized linear model-based predictive modelling of traffic noise.

Noise pollution is one of the negative consequences of growth and development in cities. Traffic noise pollution due to traffic growth is the main aspect that worsens city quality of life. Therefore, research around the world is being conducted to manage and reduce traffic noise. A number of traffic noise prediction models have been proposed employing fixed effect modelling approach considering each observation as independent; however, observations may have spatial and temporal correlations and unobserved heterogeneity. Random effect models overcome these problems. This study attempts to develop a random effect generalized linear model (REGLM) along with a machine learning random forest (RF) model to validate the results, concerning the parameters related to road, traffic and environmental conditions. Models were developed based on the experimental quantities in Delhi in year 2022-2023. Both the models performed comparably well in terms of coefficient of determination. Random forest models with R2= 0.75, whereas random effect generalized linear model had an R2= 0.70. REGLM model has the ability to quantify the effects of explanatory variables over traffic noise pollution and will be more helpful in prioritizing of resources and chalking out control strategies.

Study on the network acoustics environment effects of traffic management measures by a bilevel programming model

This study examines the mechanisms of environmentally oriented traffic management measures through an environmental network design problem. An improved user equilibrium (UE) model was proposed to simulate the traffic state under traffic management measures and combine a traffic noise prediction model to obtain the noise distribution, while the environmental noise functional zone compliance was considered as the objective. A bilevel programming model was established to find the optimal solution for the acoustic environment and traffic under different strategy spaces. As results, with sufficient strategy space, speed limits can increase the compliance rate of the environmental noise functional zones from 53.7% to 100%, and flow limits can increase the compliance rate by 7.1%. With insufficient strategy space, collaborative control can achieve better environmental optimization than speed and flow limits, but there are serious traffic efficiency costs which travel time increases of 24%–45%. This is due to the detour phenomena under flow limits. In addition, road classification is an important control reference and coupling effects occur during the control of speed and flow limits. This study of the mechanism underlying the optimization of the acoustic environment under traffic management measures can provide theoretical guidance for planners.

Traffic Noise Prediction for Delhi-NCR using Multiple RegressionModelling Approach

Traffic noise prediction models are crucial for designing highways to implement preventive measures against traffic noise pollution by analyzing future trends. This study aims to identify the traffic, road geometrical, and environmental parameters that escalate traffic noise pollution, enabling rectification of influencing factors and enhancement of strategies to reduce this pollution. A traffic noise prediction model was developed for the highways of Delhi-NCR using the Multiple Regression approach, incorporating various traffic, geometric, and environmental parameters. Statistical analysis was conducted, and the model was formulated based on data collected from 31 sampling stations on two major Delhi highways. Significant variables identified include the number of lanes, average building height, international roughness index, temperature, wind speed, and humidity. The model’s validity is affirmed by a coefficient of determination R2 = 0.75, indicating a good fit.

Comparison of sound emission in ASJ RTN-Model 2018 and several European prediction models

The road traffic noise prediction model ASJ RTN-Model 2018 is used widely as a support tool in the environmental impact assessment of development projects in Southeast Asia as well as in Japan. In European countries, various prediction models such as Nord and CNOSSOS-EU have been published. Since 2018, the specific noise emission, which can be incorporated into CNOSSOS-EU, was proposed in several countries: CNOSSOS-NL, -FR and sonROAD. Also, the coefficients of the emission model in CNOSSOS-EU were replaced in 2021. In this study, the values of noise emission and its frequency characteristics were compared between these prediction models using immission values calculated considering the effects of the ground surface and a barrier. The results revealed that the emission values for three vehicle types in ASJ RTN-Model 2018 are almost 1 dB lower on average than those in European models, and the immission values on the reflective ground are independent of differences in the frequency characteristic between the emission models.

Sound power level determination of roads in Tokyo using aerial photographs, machine learning, and ASJ RTN-Model 2018

The traffic noise map is a visual representation of the sound level distribution in and around a road based on the sound power levels of vehicles on the road and the diffraction and reflection by the surrounding buildings. The purpose of creating the traffic noise map is to facilitate the government, researchers, industry, and the public in their efforts to track trends in transportation-related noise. To create noise maps, sound power level determination is the most important. The road traffic noise prediction model "ASJ RTN-Model 2018" has been widely used for road traffic noise prediction in Japan. Provided a method of calculating sound power level by vehicle classification, traveling speed, and driving mode. In the study, to obtain the vehicles' classification and coordinates, YOLO (You Only Look Once) was used to process the aerial photos. This study constructed sound power level distribution on the road network in Tokyo. Additionally, the estimated data were compared with the measured data to confirm the estimated data's reliability.

Consideration on accuracy on road traffic noise prediction model "ASJ RTN-Model 2018" in power level and equivalent noise level

This paper introduces the study on verification of prediction accuracy about road traffic noise prediction model "ASJ RTN-Model 2018" used as standard for prediction of road traffic noise in Japan. The effects of vehicle type classification, traffic volume and regional characteristics on prediction accuracy were examined for the power level LWA representing the sound source characteristics of the traveling vehicle and the equivalent noise level LAeq of the evaluation value used for noise control standards. As a result, it was confirmed that the prediction accuracy of this model was generally good regardless of the traffic volume, regional characteristics and the vehicle type classification.

Employing the maximum likelihood fitting method in the principle of probability and statistics to continually apply the original FHWA road traffic noise prediction model

The original federal highway administration (FHWA) model for road traffic noise (RTN) prediction in the United States (US) has been widely applied in many countries. However, the condition was that the intensities of vehicle noise sources at the reference distance must be determined based on the empirical formula related to vehicle speed and road surface obtained by applying the measured results of a large number of different vehicles in the US. Because the dominant vehicle types and road pavement structures in other countries are not the same, the classification of vehicles and the calculation formula for the source intensity will be different. Even in the US, because of the older modeling data, the current vehicles and their changed noise source, and the new traffic noise model (TNM), the original FHWA model may produce errors if applied in other countries. Therefore, by employing the maximum likelihood method in probability and statistics, this study proposes a method that can continue to directly apply the original FHWA model according to the local vehicle traffic flow, together with a simple method of measuring the attenuation of RTN with distance, to eliminate the uncertainty of the source intensity.

Drastic mobility restrictions during SARS-CoV-2 pandemic: an opportunity to learn about constraints on the way to a pollution-free city.

Road traffic is one of the main sources of pollution in modern cities. If there is a desire to move towards healthier cities, it may be necessary to modify the current model of mobility. The SARS-CoV-2 pandemic, together with the measures applied by most governments in the world to control the mobility of citizens, offered a unique opportunity to assess the changes in pollution levels after a drastic reduction in road traffic. In this study, air and noise pollution levels and road traffic flow were analyzed in the city of Cáceres, Spain, before and during the state of emergency imposed by the Spanish government. The values obtained were compared with the quality limits established by both the Spanish government and the World Health Organization (WHO). A traffic noise prediction model has been employed to evaluate the acoustic impact resulting from the reduction in traffic flow. As a result of this study, it was found that air pollution was indeed reduced due to the mobility restrictions imposed to control the pandemic, but that the WHO's recommendations for the values of the day-evening-night noise indicator (Lden) and the night-time noise indicator (Ln) for road traffic noise, which should not be exceeded, were not met. These findings highlight the need to review current urban mobility models if the WHO's recommendations are to be reached with regard to reducing the effects of exposure of the population to urban noise.

Modelling of traffic noise in the vicinity of urban road intersections

Traffic noise is continuously rising alongside roadways, especially at intersections, due to rapid urbanization, eventually affecting acoustical climate and quality of life. This present study develops a traffic noise model for intersections with minimal evidence of interrelationships among influential traffic noise factors. An integrated Bayesian networks and Partial least squares structural equation modelling approach has been employed on 342-hour field measurement data collected from nineteen intersections in Kanpur, India. The integrated approach developed the traffic noise prediction model with 62.4% explanatory power and identified direct and indirect effects of five influential factors on traffic noise. For instance, Traffic flow attributes, i.e., traffic volume and honking, are the most crucial ones to degrade acoustical climate at intersections. Besides, Built environment and Climate conditions induce only indirect effects on traffic noise. Thus, this study provides a useful basis for planners to understand traffic noise relationships and deploy noise mitigation strategies accordingly.

The Comparative Study on Traffic Noise Prediction Model between Classical Algorithm and Neural Network Methods

Traffic is the main noise source in urban environment, which has a significant impact on people's physical and mental health and labor productivity. To solve the problem of highway noise pollution, we should not only strengthen the prevention and control measures in the later stage but also scientifically and accurately predict and evaluate its noise impact in the early stage. The selection of the noise prediction model and the determination of its parameters is the necessary premise for the accurate prediction of highway noise. This paper introduces several traditional noise prediction algorithms based on statistical methods. Then the application of the artificial neural network method in traffic noise prediction is analyzed. The results show that artificial neural network is an effective noise prediction tool with high prediction accuracy. Compared with other statistical methods, the artificial neural network method has obvious advantages in traffic noise prediction.

Parameter analysis and Reliability Evaluation of Road Traffic Noise Prediction Model for Highway Traffic Noise Evaluation

The purpose of this study is to evaluate the reliability of prediction models(KHTN, RLS-90, CRTN, NMPB-08) that are widely used in road traffic noise analysis. For this purpose, the accuracy and difference values of the prediction model were analyzed by comparing the measurement values performed at the total of 21 highway sites, reflecting various conditions such as road structure, road pavement type, and noise barrier installation. In addition, the correlation between commercial programs(SoundPlan, CadnaA) was compared and reviewed for each of the same prediction models. First of all, as a result of analyzing the accuracy of each prediction model, KHTN is rated as 92.8% the most accurate based on ±3 dB error range. And CRTN is rated as 74.0~76.8% the most accurate among prediction models inherent in commercial programs. And, as a result of analyzing the correlation between commercial programs for prediction models, CRTN is 100% highly correlated and NMPB has the lowest correlation by 69.6%.

Construction and Analysis of Urban Traffic Noise Prediction Model Based on PSO Algorithm and BRF Network Structure

Due to the current nonlinear traffic noise and changing natural environment, accurate prediction of traffic noise has become a major challenge. In order to improve the accuracy of traffic noise prediction, this paper constructs a short-term traffic noise prediction model based on PSO algorithm and BRF network structure. The model can predict the noise state of future traffic according to historical traffic information. Particle swarm optimization (PSO) network is used for short-term traffic prediction to deal with the problems of low accuracy and long-time consumption. A BRF (one-dimensional convolution)-PSO short-term traffic noise prediction model is proposed. BRF method is used to extract the spatial features of traffic noise and compared with PCA (principal component analysis)-PSO model and PSO model. The results show that the prediction accuracy of BRF-PSO model is 2% higher than that of PCA-PSO model and 6% higher than that of PSO model, which proves the effectiveness of BRF-PSO model. This study provides a technical reference for the short-term traffic noise prediction of intelligent city and the effective improvement of urban traffic environment.