Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction

In this paper five neural network models were developed using NARX-SP neural network type in order to predict air pollutants concentrations (SO2, PM10, NO2, O3 and CO ) for the 72nd hour ahead for Sarajevo. Hourly values of air pollutants concentrations and meteorological parameters (air temperature...

Full description

Bibliographic Details
Main Authors: Mirza Pasic, Izet Bijelonja, Edin Kadric, Hadis Bajric
Format: Article
Language:English
Published: UIKTEN 2020-08-01
Series:TEM Journal
Subjects:
Online Access:http://www.temjournal.com/content/93/TEMJournalAugust_852_861.pdf
id doaj-a439963099eb476f8f8126f9bbe29fb8
record_format Article
spelling doaj-a439963099eb476f8f8126f9bbe29fb82020-11-25T02:53:01ZengUIKTENTEM Journal2217-83092217-83332020-08-019385286110.18421/TEM93-03Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality PredictionMirza PasicIzet BijelonjaEdin KadricHadis BajricIn this paper five neural network models were developed using NARX-SP neural network type in order to predict air pollutants concentrations (SO2, PM10, NO2, O3 and CO ) for the 72nd hour ahead for Sarajevo. Hourly values of air pollutants concentrations and meteorological parameters (air temperature, pressure and humidity, wind speed and direction) for Sarajevo were used. Optimal model was selected based on the values of R2, MSE and the complexity of models. Optimal neural network model can predict air pollutants concentrations for the 72nd hour ahead with high accuracy, as well as for all hours up to 72nd hour.http://www.temjournal.com/content/93/TEMJournalAugust_852_861.pdfnarx-spneural networkair pollutant concentrationmeteorological parameters
collection DOAJ
language English
format Article
sources DOAJ
author Mirza Pasic
Izet Bijelonja
Edin Kadric
Hadis Bajric
spellingShingle Mirza Pasic
Izet Bijelonja
Edin Kadric
Hadis Bajric
Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
TEM Journal
narx-sp
neural network
air pollutant concentration
meteorological parameters
author_facet Mirza Pasic
Izet Bijelonja
Edin Kadric
Hadis Bajric
author_sort Mirza Pasic
title Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
title_short Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
title_full Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
title_fullStr Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
title_full_unstemmed Modeling of Nonlinear Autoregressive Neural Network for Multi-Step Ahead Air Quality Prediction
title_sort modeling of nonlinear autoregressive neural network for multi-step ahead air quality prediction
publisher UIKTEN
series TEM Journal
issn 2217-8309
2217-8333
publishDate 2020-08-01
description In this paper five neural network models were developed using NARX-SP neural network type in order to predict air pollutants concentrations (SO2, PM10, NO2, O3 and CO ) for the 72nd hour ahead for Sarajevo. Hourly values of air pollutants concentrations and meteorological parameters (air temperature, pressure and humidity, wind speed and direction) for Sarajevo were used. Optimal model was selected based on the values of R2, MSE and the complexity of models. Optimal neural network model can predict air pollutants concentrations for the 72nd hour ahead with high accuracy, as well as for all hours up to 72nd hour.
topic narx-sp
neural network
air pollutant concentration
meteorological parameters
url http://www.temjournal.com/content/93/TEMJournalAugust_852_861.pdf
work_keys_str_mv AT mirzapasic modelingofnonlinearautoregressiveneuralnetworkformultistepaheadairqualityprediction
AT izetbijelonja modelingofnonlinearautoregressiveneuralnetworkformultistepaheadairqualityprediction
AT edinkadric modelingofnonlinearautoregressiveneuralnetworkformultistepaheadairqualityprediction
AT hadisbajric modelingofnonlinearautoregressiveneuralnetworkformultistepaheadairqualityprediction
_version_ 1724727150654783488