Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks

This paper focuses on improving the prediction of the daily concentration of the pollutants, PM<sub>10</sub> and nitrogen oxides (NO, NO<sub>2</sub>) in the air at urban monitoring sites using 1D convolutional neural networks (CNN). The results show that the 1D CNN model outp...

Full description

Saved in:
Bibliographic Details
Main Authors: Ivan Gudelj, Mario Lovrić, Emmanuel Karlo Nyarko
Format: Article
Language:English
Published: MDPI AG 2024-07-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/68/1/16
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204414124490752
author Ivan Gudelj
Mario Lovrić
Emmanuel Karlo Nyarko
author_facet Ivan Gudelj
Mario Lovrić
Emmanuel Karlo Nyarko
author_sort Ivan Gudelj
collection DOAJ
description This paper focuses on improving the prediction of the daily concentration of the pollutants, PM<sub>10</sub> and nitrogen oxides (NO, NO<sub>2</sub>) in the air at urban monitoring sites using 1D convolutional neural networks (CNN). The results show that the 1D CNN model outperforms the other machine learning models (LSTM and Random Forest) in terms of the coefficients of determination and absolute errors.
format Article
id doaj-art-5f3ed0112e084d37bb49578936759ad3
institution OA Journals
issn 2673-4591
language English
publishDate 2024-07-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-5f3ed0112e084d37bb49578936759ad32025-08-20T02:11:17ZengMDPI AGEngineering Proceedings2673-45912024-07-016811610.3390/engproc2024068016Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural NetworksIvan Gudelj0Mario Lovrić1Emmanuel Karlo Nyarko2Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, CroatiaCentre for Bioanthropology, Institute for Anthropological Research, 10000 Zagreb, CroatiaFaculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, CroatiaThis paper focuses on improving the prediction of the daily concentration of the pollutants, PM<sub>10</sub> and nitrogen oxides (NO, NO<sub>2</sub>) in the air at urban monitoring sites using 1D convolutional neural networks (CNN). The results show that the 1D CNN model outperforms the other machine learning models (LSTM and Random Forest) in terms of the coefficients of determination and absolute errors.https://www.mdpi.com/2673-4591/68/1/16air pollutionmachine learning1D CNN
spellingShingle Ivan Gudelj
Mario Lovrić
Emmanuel Karlo Nyarko
Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
Engineering Proceedings
air pollution
machine learning
1D CNN
title Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
title_full Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
title_fullStr Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
title_full_unstemmed Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
title_short Modelling the Daily Concentration of Airborne Particles Using 1D Convolutional Neural Networks
title_sort modelling the daily concentration of airborne particles using 1d convolutional neural networks
topic air pollution
machine learning
1D CNN
url https://www.mdpi.com/2673-4591/68/1/16
work_keys_str_mv AT ivangudelj modellingthedailyconcentrationofairborneparticlesusing1dconvolutionalneuralnetworks
AT mariolovric modellingthedailyconcentrationofairborneparticlesusing1dconvolutionalneuralnetworks
AT emmanuelkarlonyarko modellingthedailyconcentrationofairborneparticlesusing1dconvolutionalneuralnetworks