Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF

Background: Exposure to air pollutants, such as PM2.5 is recognized as a significant health risk, contributing to the development of various diseases, and increased risk of premature mortality.Methods: Multilayer perceptron (MLP) and radial basis function (RBF) neural networks, were used to predict...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Mohammadi Bardshahi, Nematollah Jaafarzadeh, Tayebeh Tayebeh, Fazel Amiri
Format: Article
Language:English
Published: Kurdistan University of Medical Sciences 2025-02-01
Series:Journal of Advances in Environmental Health Research
Subjects:
Online Access:https://jaehr.muk.ac.ir/article_218995_6626606e4e06caa813dbcb75997c58ee.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314719165317120
author Ali Mohammadi Bardshahi
Nematollah Jaafarzadeh
Tayebeh Tayebeh
Fazel Amiri
author_facet Ali Mohammadi Bardshahi
Nematollah Jaafarzadeh
Tayebeh Tayebeh
Fazel Amiri
author_sort Ali Mohammadi Bardshahi
collection DOAJ
description Background: Exposure to air pollutants, such as PM2.5 is recognized as a significant health risk, contributing to the development of various diseases, and increased risk of premature mortality.Methods: Multilayer perceptron (MLP) and radial basis function (RBF) neural networks, were used to predict the hourly concentration of PM2.5 in Isfahan, Iran. The MLP model was designed with five input variables, including PM2.5 concentration and weather characteristics, ten hidden layers, and a single output layer. The dataset was divided into three subsets: 70% for training, 15% for testing, and 15% for validation.Results: The results showed that the average concentration of PM2.5 was 26.5 μg/m3. The root mean square error (RMSE) was estimated as 6.49 μg/m3. Increasing the input data resulted in a slight reduction in network error, with the RBF model, utilizing 1450 inputs and an RMSE of 6.47, achieving the same accuracy as the MLP model with 10 inputs.Conclusion: Given that the PM2.5 concentration estimates from the RBF and MLP models deviated by less than 23 and 25%, respectively, compared to the observed concentrations, both MLP and RBF can be regarded as reliable tools for predicting PM2.5 levels.
format Article
id doaj-art-a17b85abec464daf83ceb796a559ca06
institution Kabale University
issn 2345-3990
language English
publishDate 2025-02-01
publisher Kurdistan University of Medical Sciences
record_format Article
series Journal of Advances in Environmental Health Research
spelling doaj-art-a17b85abec464daf83ceb796a559ca062025-08-20T03:52:23ZengKurdistan University of Medical SciencesJournal of Advances in Environmental Health Research2345-39902025-02-0113212913410.34172/jaehr.1387218995Estimation of Ambient Air PM2.5 Concentration Using MLP and RBFAli Mohammadi Bardshahi0Nematollah Jaafarzadeh1Tayebeh Tayebeh2Fazel Amiri3Department of Environment, Bushehr Branch, Islamic Azad University, Bushehr, IranEnvironmental Technologies Research Center, Medical Basic Sciences Research Institute, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, IranDepartment of Environment, Bushehr Branch, Islamic Azad University, Bushehr, IranDepartment of Environment, Bushehr Branch, Islamic Azad University, Bushehr, IranBackground: Exposure to air pollutants, such as PM2.5 is recognized as a significant health risk, contributing to the development of various diseases, and increased risk of premature mortality.Methods: Multilayer perceptron (MLP) and radial basis function (RBF) neural networks, were used to predict the hourly concentration of PM2.5 in Isfahan, Iran. The MLP model was designed with five input variables, including PM2.5 concentration and weather characteristics, ten hidden layers, and a single output layer. The dataset was divided into three subsets: 70% for training, 15% for testing, and 15% for validation.Results: The results showed that the average concentration of PM2.5 was 26.5 μg/m3. The root mean square error (RMSE) was estimated as 6.49 μg/m3. Increasing the input data resulted in a slight reduction in network error, with the RBF model, utilizing 1450 inputs and an RMSE of 6.47, achieving the same accuracy as the MLP model with 10 inputs.Conclusion: Given that the PM2.5 concentration estimates from the RBF and MLP models deviated by less than 23 and 25%, respectively, compared to the observed concentrations, both MLP and RBF can be regarded as reliable tools for predicting PM2.5 levels.https://jaehr.muk.ac.ir/article_218995_6626606e4e06caa813dbcb75997c58ee.pdfartificial neural networkrbfmlpparticulate matterisfahan
spellingShingle Ali Mohammadi Bardshahi
Nematollah Jaafarzadeh
Tayebeh Tayebeh
Fazel Amiri
Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
Journal of Advances in Environmental Health Research
artificial neural network
rbf
mlp
particulate matter
isfahan
title Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
title_full Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
title_fullStr Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
title_full_unstemmed Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
title_short Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF
title_sort estimation of ambient air pm2 5 concentration using mlp and rbf
topic artificial neural network
rbf
mlp
particulate matter
isfahan
url https://jaehr.muk.ac.ir/article_218995_6626606e4e06caa813dbcb75997c58ee.pdf
work_keys_str_mv AT alimohammadibardshahi estimationofambientairpm25concentrationusingmlpandrbf
AT nematollahjaafarzadeh estimationofambientairpm25concentrationusingmlpandrbf
AT tayebehtayebeh estimationofambientairpm25concentrationusingmlpandrbf
AT fazelamiri estimationofambientairpm25concentrationusingmlpandrbf