Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms
To accurately predict tropospheric ozone concentration(O3), it is needed to investigate the variety of artificial intelligence techniques� performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variable...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Taylor and Francis Ltd.
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-26537 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-265372023-05-29T17:11:41Z Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms Yafouz A. Ahmed A.N. Zaini N. Sherif M. Sefelnasr A. El-Shafie A. 57221981418 57214837520 56905328500 7005414714 6505592467 16068189400 To accurately predict tropospheric ozone concentration(O3), it is needed to investigate the variety of artificial intelligence techniques� performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variables. This ozone prediction attempt is performed on diversity data of air pollutants (NO2, NOx, CO, SO2) and meteorological parameters (wind-speed and humidity). The historical datasets are collected from 3 sites in Malaysia. The study�s methodology progressed in two paths: standalone and hybrid models where hourly-averaged datasets are applied based on 5-time horizon analysis scenario, with different inputs� combinations. For evaluation, all models are tested throughout 5-performance indicator and illustrated on Modified Taylor diagram. Sensitivity analysis of input variables is quantified. Additionally, uncertainty analysis is conducted to assess their confidence level associated with Willmott Index. Based on R 2, results indicated that XGBoost has higher accuracy compared to MLP and SVR; meanwhile, LSTM and CNN outweighs XGBoost. In terms of robustness and accuracy, the proposed hybrid model possesses superlative performance compared to all above-mentioned techniques. The proposed model achieved exceptional results as the highest R 2, the highest 95% confidence degree, and narrower confidence interval width, are 93.48%, 98.16%, and 0.0014195, respectively. � 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. Final 2023-05-29T09:11:41Z 2023-05-29T09:11:41Z 2021 Article 10.1080/19942060.2021.1926328 2-s2.0-85106308124 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85106308124&doi=10.1080%2f19942060.2021.1926328&partnerID=40&md5=4524da5088f50ee5d7d3ac871a2279a2 https://irepository.uniten.edu.my/handle/123456789/26537 15 1 902 933 All Open Access, Gold Taylor and Francis Ltd. Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
To accurately predict tropospheric ozone concentration(O3), it is needed to investigate the variety of artificial intelligence techniques� performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variables. This ozone prediction attempt is performed on diversity data of air pollutants (NO2, NOx, CO, SO2) and meteorological parameters (wind-speed and humidity). The historical datasets are collected from 3 sites in Malaysia. The study�s methodology progressed in two paths: standalone and hybrid models where hourly-averaged datasets are applied based on 5-time horizon analysis scenario, with different inputs� combinations. For evaluation, all models are tested throughout 5-performance indicator and illustrated on Modified Taylor diagram. Sensitivity analysis of input variables is quantified. Additionally, uncertainty analysis is conducted to assess their confidence level associated with Willmott Index. Based on R 2, results indicated that XGBoost has higher accuracy compared to MLP and SVR; meanwhile, LSTM and CNN outweighs XGBoost. In terms of robustness and accuracy, the proposed hybrid model possesses superlative performance compared to all above-mentioned techniques. The proposed model achieved exceptional results as the highest R 2, the highest 95% confidence degree, and narrower confidence interval width, are 93.48%, 98.16%, and 0.0014195, respectively. � 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. |
| author2 |
57221981418 |
| author_facet |
57221981418 Yafouz A. Ahmed A.N. Zaini N. Sherif M. Sefelnasr A. El-Shafie A. |
| format |
Article |
| author |
Yafouz A. Ahmed A.N. Zaini N. Sherif M. Sefelnasr A. El-Shafie A. |
| spellingShingle |
Yafouz A. Ahmed A.N. Zaini N. Sherif M. Sefelnasr A. El-Shafie A. Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| author_sort |
Yafouz A. |
| title |
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| title_short |
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| title_full |
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| title_fullStr |
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| title_full_unstemmed |
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| title_sort |
hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms |
| publisher |
Taylor and Francis Ltd. |
| publishDate |
2023 |
| _version_ |
1806426006552051712 |
| score |
13.222552 |