Artificial neural networks based modelling of carbon monoxide

Effects of spatial parameters

Atakan Kurt, Ayşe Betül Oktay, Ferhat Karaca, Omar Alagha

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Web systems for air quality information and pollution modeling provide access to daily measured and predicted valuable information for the internet users. There are just a few examples around the world in this area. A recently developed web system at http://airpol.fatih.edu.tr is one such application. It provides information about air quality prediction for Istanbul, Turkey in a user friendly interface. New studies have been performed to increase the prediction efficiencies of the system and presented in this work. This paper presents a study on the prediction of carbon monoxide (CO) levels using Artificial Neural Networks (ANN). ANN models have been applied to the prediction of 3 day CO levels into future. The observed and predicted values were compared to determine the performance of the ANN models. The experimental results shows that spatial parameters (Universal Transverse Mercator coordinates) generally produce better forecasting (30% error) than ordinary, non-spatial parameters, although there are some cases where spatial parameters yield lower prediction accuracy. The experiments reveal that models with spatial input variables deserve further study and better models could be developed with higher accuracy.

Original languageEnglish
Title of host publicationInformation Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009
PublisherKluwer Academic Publishers
Pages345-356
Number of pages12
ISBN (Print)9783540883500
DOIs
Publication statusPublished - Jan 1 2009
Externally publishedYes
Event4th International ICSC Symposium on Information Technologies in Environmental Engineering, ITEE 2009 - Thessaloniki, Greece
Duration: May 28 2009May 29 2009

Publication series

NameEnvironmental Science and Engineering (Subseries: Environmental Science)
ISSN (Print)1863-5520

Conference

Conference4th International ICSC Symposium on Information Technologies in Environmental Engineering, ITEE 2009
CountryGreece
CityThessaloniki
Period5/28/095/29/09

Fingerprint

Carbon monoxide
Neural networks
Air quality
User interfaces
Pollution
Internet
Experiments

Keywords

  • Air pollution
  • Air quality prediction
  • CO
  • Forecasting
  • Neural networks

ASJC Scopus subject areas

  • Information Systems
  • Environmental Engineering

Cite this

Kurt, A., Oktay, A. B., Karaca, F., & Alagha, O. (2009). Artificial neural networks based modelling of carbon monoxide: Effects of spatial parameters. In Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009 (pp. 345-356). (Environmental Science and Engineering (Subseries: Environmental Science)). Kluwer Academic Publishers. https://doi.org/10.1007/978-3-540-88351-7-26

Artificial neural networks based modelling of carbon monoxide : Effects of spatial parameters. / Kurt, Atakan; Oktay, Ayşe Betül; Karaca, Ferhat; Alagha, Omar.

Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009. Kluwer Academic Publishers, 2009. p. 345-356 (Environmental Science and Engineering (Subseries: Environmental Science)).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kurt, A, Oktay, AB, Karaca, F & Alagha, O 2009, Artificial neural networks based modelling of carbon monoxide: Effects of spatial parameters. in Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009. Environmental Science and Engineering (Subseries: Environmental Science), Kluwer Academic Publishers, pp. 345-356, 4th International ICSC Symposium on Information Technologies in Environmental Engineering, ITEE 2009, Thessaloniki, Greece, 5/28/09. https://doi.org/10.1007/978-3-540-88351-7-26
Kurt A, Oktay AB, Karaca F, Alagha O. Artificial neural networks based modelling of carbon monoxide: Effects of spatial parameters. In Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009. Kluwer Academic Publishers. 2009. p. 345-356. (Environmental Science and Engineering (Subseries: Environmental Science)). https://doi.org/10.1007/978-3-540-88351-7-26
Kurt, Atakan ; Oktay, Ayşe Betül ; Karaca, Ferhat ; Alagha, Omar. / Artificial neural networks based modelling of carbon monoxide : Effects of spatial parameters. Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009. Kluwer Academic Publishers, 2009. pp. 345-356 (Environmental Science and Engineering (Subseries: Environmental Science)).
@inproceedings{884cb93da62444be9ac0d04da46829f6,
title = "Artificial neural networks based modelling of carbon monoxide: Effects of spatial parameters",
abstract = "Web systems for air quality information and pollution modeling provide access to daily measured and predicted valuable information for the internet users. There are just a few examples around the world in this area. A recently developed web system at http://airpol.fatih.edu.tr is one such application. It provides information about air quality prediction for Istanbul, Turkey in a user friendly interface. New studies have been performed to increase the prediction efficiencies of the system and presented in this work. This paper presents a study on the prediction of carbon monoxide (CO) levels using Artificial Neural Networks (ANN). ANN models have been applied to the prediction of 3 day CO levels into future. The observed and predicted values were compared to determine the performance of the ANN models. The experimental results shows that spatial parameters (Universal Transverse Mercator coordinates) generally produce better forecasting (30{\%} error) than ordinary, non-spatial parameters, although there are some cases where spatial parameters yield lower prediction accuracy. The experiments reveal that models with spatial input variables deserve further study and better models could be developed with higher accuracy.",
keywords = "Air pollution, Air quality prediction, CO, Forecasting, Neural networks",
author = "Atakan Kurt and Oktay, {Ayşe Bet{\"u}l} and Ferhat Karaca and Omar Alagha",
year = "2009",
month = "1",
day = "1",
doi = "10.1007/978-3-540-88351-7-26",
language = "English",
isbn = "9783540883500",
series = "Environmental Science and Engineering (Subseries: Environmental Science)",
publisher = "Kluwer Academic Publishers",
pages = "345--356",
booktitle = "Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009",
address = "Netherlands",

}

TY - GEN

T1 - Artificial neural networks based modelling of carbon monoxide

T2 - Effects of spatial parameters

AU - Kurt, Atakan

AU - Oktay, Ayşe Betül

AU - Karaca, Ferhat

AU - Alagha, Omar

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Web systems for air quality information and pollution modeling provide access to daily measured and predicted valuable information for the internet users. There are just a few examples around the world in this area. A recently developed web system at http://airpol.fatih.edu.tr is one such application. It provides information about air quality prediction for Istanbul, Turkey in a user friendly interface. New studies have been performed to increase the prediction efficiencies of the system and presented in this work. This paper presents a study on the prediction of carbon monoxide (CO) levels using Artificial Neural Networks (ANN). ANN models have been applied to the prediction of 3 day CO levels into future. The observed and predicted values were compared to determine the performance of the ANN models. The experimental results shows that spatial parameters (Universal Transverse Mercator coordinates) generally produce better forecasting (30% error) than ordinary, non-spatial parameters, although there are some cases where spatial parameters yield lower prediction accuracy. The experiments reveal that models with spatial input variables deserve further study and better models could be developed with higher accuracy.

AB - Web systems for air quality information and pollution modeling provide access to daily measured and predicted valuable information for the internet users. There are just a few examples around the world in this area. A recently developed web system at http://airpol.fatih.edu.tr is one such application. It provides information about air quality prediction for Istanbul, Turkey in a user friendly interface. New studies have been performed to increase the prediction efficiencies of the system and presented in this work. This paper presents a study on the prediction of carbon monoxide (CO) levels using Artificial Neural Networks (ANN). ANN models have been applied to the prediction of 3 day CO levels into future. The observed and predicted values were compared to determine the performance of the ANN models. The experimental results shows that spatial parameters (Universal Transverse Mercator coordinates) generally produce better forecasting (30% error) than ordinary, non-spatial parameters, although there are some cases where spatial parameters yield lower prediction accuracy. The experiments reveal that models with spatial input variables deserve further study and better models could be developed with higher accuracy.

KW - Air pollution

KW - Air quality prediction

KW - CO

KW - Forecasting

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=84879614642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879614642&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-88351-7-26

DO - 10.1007/978-3-540-88351-7-26

M3 - Conference contribution

SN - 9783540883500

T3 - Environmental Science and Engineering (Subseries: Environmental Science)

SP - 345

EP - 356

BT - Information Technologies in Environmental Engineering - Proceedings of the 4th International ICSC Symposium, ITEE 2009

PB - Kluwer Academic Publishers

ER -