Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index
The rise of air pollution has received much attention globally. As an early warning system for air quality control and management, it is important to provide precise future concentrations pollutant information. Using time series forecasting methods, the forecast of daily Air Pollutant Index (API) is...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Published: |
Akademi Sains Malaysia
2019
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/90346/ https://www.akademisains.gov.my/asmsj/article/hybrid-seasonal-arima-and-artificial-neural-network-in-forecasting-southeast-asia-city-air-pollutant-index/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.90346 |
---|---|
record_format |
eprints |
spelling |
my.utm.903462021-04-18T04:01:58Z http://eprints.utm.my/id/eprint/90346/ Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index Rahman, N. H. A. Lee, M. H. Suhartono, Suhartono Latif, M. T. QA Mathematics The rise of air pollution has received much attention globally. As an early warning system for air quality control and management, it is important to provide precise future concentrations pollutant information. Using time series forecasting methods, the forecast of daily Air Pollutant Index (API) is presented here. The hybrid method between seasonal autoregressive integrated moving average (SARIMA) and artificial neural network (ANN) are chosen. To verify, the accuracies are measured using error magnitude approach. However, evaluation of forecasting API is also in fluenced by the health classification based on the threshold value assigned in air quality guidelines. Thus, forecast accuracies based on index value, namely as true predicted rate (TPR), false positive rate (FPR), false alarm rate (FAR) and successful index (SI) are also used for forecast validation. As shown in the results, the hybrid model performs better in both model's evaluations group used. Hence, the hybrid method must be considered in the forecasting area due to the capability to analyze real data consisting of both linear and nonlinear patterns. Besides, using the appropriate measurement in accordance to the purpose of forecasting is important to produce an accurate forecast. Akademi Sains Malaysia 2019 Article PeerReviewed Rahman, N. H. A. and Lee, M. H. and Suhartono, Suhartono and Latif, M. T. (2019) Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index. ASM Science Journal, 12 (1). pp. 215-226. ISSN 1823-6782 https://www.akademisains.gov.my/asmsj/article/hybrid-seasonal-arima-and-artificial-neural-network-in-forecasting-southeast-asia-city-air-pollutant-index/ |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
QA Mathematics |
spellingShingle |
QA Mathematics Rahman, N. H. A. Lee, M. H. Suhartono, Suhartono Latif, M. T. Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
description |
The rise of air pollution has received much attention globally. As an early warning system for air quality control and management, it is important to provide precise future concentrations pollutant information. Using time series forecasting methods, the forecast of daily Air Pollutant Index (API) is presented here. The hybrid method between seasonal autoregressive integrated moving average (SARIMA) and artificial neural network (ANN) are chosen. To verify, the accuracies are measured using error magnitude approach. However, evaluation of forecasting API is also in fluenced by the health classification based on the threshold value assigned in air quality guidelines. Thus, forecast accuracies based on index value, namely as true predicted rate (TPR), false positive rate (FPR), false alarm rate (FAR) and successful index (SI) are also used for forecast validation. As shown in the results, the hybrid model performs better in both model's evaluations group used. Hence, the hybrid method must be considered in the forecasting area due to the capability to analyze real data consisting of both linear and nonlinear patterns. Besides, using the appropriate measurement in accordance to the purpose of forecasting is important to produce an accurate forecast. |
format |
Article |
author |
Rahman, N. H. A. Lee, M. H. Suhartono, Suhartono Latif, M. T. |
author_facet |
Rahman, N. H. A. Lee, M. H. Suhartono, Suhartono Latif, M. T. |
author_sort |
Rahman, N. H. A. |
title |
Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
title_short |
Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
title_full |
Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
title_fullStr |
Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
title_full_unstemmed |
Hybrid seasonal ARIMA and artificial neural network in forecasting Southeast Asia city air pollutant index |
title_sort |
hybrid seasonal arima and artificial neural network in forecasting southeast asia city air pollutant index |
publisher |
Akademi Sains Malaysia |
publishDate |
2019 |
url |
http://eprints.utm.my/id/eprint/90346/ https://www.akademisains.gov.my/asmsj/article/hybrid-seasonal-arima-and-artificial-neural-network-in-forecasting-southeast-asia-city-air-pollutant-index/ |
_version_ |
1698696922677641216 |
score |
13.159267 |