A comparative analysis to forecast carbon dioxide emissions

<p dir="ltr">Despite the growing knowledge and commitment to climate change, carbon dioxide (CO<sub>2</sub>) emissions continue to rise dramatically throughout the planet. In recent years, the consequences of climate change have become more catastrophic and have attracted...

Full description

Saved in:
Bibliographic Details
Main Author: Md. Omer Faruque (17545671) (author)
Other Authors: Md. Afser Jani Rabby (17545674) (author), Md. Alamgir Hossain (1371456) (author), Md. Rashidul Islam (11636491) (author), Md Mamun Ur Rashid (11587099) (author), S.M. Muyeen (15746160) (author)
Published: 2022
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513536512753664
author Md. Omer Faruque (17545671)
author2 Md. Afser Jani Rabby (17545674)
Md. Alamgir Hossain (1371456)
Md. Rashidul Islam (11636491)
Md Mamun Ur Rashid (11587099)
S.M. Muyeen (15746160)
author2_role author
author
author
author
author
author_facet Md. Omer Faruque (17545671)
Md. Afser Jani Rabby (17545674)
Md. Alamgir Hossain (1371456)
Md. Rashidul Islam (11636491)
Md Mamun Ur Rashid (11587099)
S.M. Muyeen (15746160)
author_role author
dc.creator.none.fl_str_mv Md. Omer Faruque (17545671)
Md. Afser Jani Rabby (17545674)
Md. Alamgir Hossain (1371456)
Md. Rashidul Islam (11636491)
Md Mamun Ur Rashid (11587099)
S.M. Muyeen (15746160)
dc.date.none.fl_str_mv 2022-11-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.egyr.2022.06.025
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_comparative_analysis_to_forecast_carbon_dioxide_emissions/24720357
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Environmental engineering
Information and computing sciences
Machine learning
CO2
emissions
Forecasting
Deep learning
FMOLS
CNN–LSTM
dc.title.none.fl_str_mv A comparative analysis to forecast carbon dioxide emissions
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Despite the growing knowledge and commitment to climate change, carbon dioxide (CO<sub>2</sub>) emissions continue to rise dramatically throughout the planet. In recent years, the consequences of climate change have become more catastrophic and have attracted widespread attention globally. CO<sub>2</sub> emissions from the energy industry have lately been highlighted as one of the world’s most pressing concerns for all countries. This paper examines the relationships between CO<sub>2</sub> emissions, electrical energy consumption, and gross domestic product (GDP) in Bangladesh from 1972 to 2019 in the first section. In this purpose, we applied the fully modified ordinary least squares (FMOLS) approach. The findings indicate that CO<sub>2</sub> emissions, electrical energy consumption, and GDP have a statistically significant long-term cointegrating relationship. Developing an accurate CO<sub>2</sub> emissions forecasting model is crucial for tackling it safely. This leads to the second step, which involves formulating the multivariate time series CO<sub>2</sub> emissions forecasting challenges considering its influential factors. Based on multivariate time series prediction, four deep learning algorithms are analyzed in this work, those are convolution neural network (CNN), CNN long short-term memory (CNN–LSTM), long short-term memory (LSTM), and dense neural network (DNN). The root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) are used to analyze and compare the performances of the predictive models. The prediction errors in MAPE of the CNN, CNN–LSTM, LSTM, and DNN are 15.043, 5.065, 5.377, and 3.678, respectively. After evaluating those deep learning models, a multivariate polynomial regression has also been employed to forecast CO<sub>2 </sub>emissions. It seems to have nearly similar accuracy as the LSTM model, having a MAPE of 5.541.</p><h2>Other Information</h2><p dir="ltr">Published in: Energy Reports<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.egyr.2022.06.025" target="_blank">https://dx.doi.org/10.1016/j.egyr.2022.06.025</a></p>
eu_rights_str_mv openAccess
id Manara2_fbc1760c2c0ecf09198bdb62f54ae90c
identifier_str_mv 10.1016/j.egyr.2022.06.025
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24720357
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A comparative analysis to forecast carbon dioxide emissionsMd. Omer Faruque (17545671)Md. Afser Jani Rabby (17545674)Md. Alamgir Hossain (1371456)Md. Rashidul Islam (11636491)Md Mamun Ur Rashid (11587099)S.M. Muyeen (15746160)EngineeringElectrical engineeringEnvironmental engineeringInformation and computing sciencesMachine learningCO2emissionsForecastingDeep learningFMOLSCNN–LSTM<p dir="ltr">Despite the growing knowledge and commitment to climate change, carbon dioxide (CO<sub>2</sub>) emissions continue to rise dramatically throughout the planet. In recent years, the consequences of climate change have become more catastrophic and have attracted widespread attention globally. CO<sub>2</sub> emissions from the energy industry have lately been highlighted as one of the world’s most pressing concerns for all countries. This paper examines the relationships between CO<sub>2</sub> emissions, electrical energy consumption, and gross domestic product (GDP) in Bangladesh from 1972 to 2019 in the first section. In this purpose, we applied the fully modified ordinary least squares (FMOLS) approach. The findings indicate that CO<sub>2</sub> emissions, electrical energy consumption, and GDP have a statistically significant long-term cointegrating relationship. Developing an accurate CO<sub>2</sub> emissions forecasting model is crucial for tackling it safely. This leads to the second step, which involves formulating the multivariate time series CO<sub>2</sub> emissions forecasting challenges considering its influential factors. Based on multivariate time series prediction, four deep learning algorithms are analyzed in this work, those are convolution neural network (CNN), CNN long short-term memory (CNN–LSTM), long short-term memory (LSTM), and dense neural network (DNN). The root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) are used to analyze and compare the performances of the predictive models. The prediction errors in MAPE of the CNN, CNN–LSTM, LSTM, and DNN are 15.043, 5.065, 5.377, and 3.678, respectively. After evaluating those deep learning models, a multivariate polynomial regression has also been employed to forecast CO<sub>2 </sub>emissions. It seems to have nearly similar accuracy as the LSTM model, having a MAPE of 5.541.</p><h2>Other Information</h2><p dir="ltr">Published in: Energy Reports<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.egyr.2022.06.025" target="_blank">https://dx.doi.org/10.1016/j.egyr.2022.06.025</a></p>2022-11-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.egyr.2022.06.025https://figshare.com/articles/journal_contribution/A_comparative_analysis_to_forecast_carbon_dioxide_emissions/24720357CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/247203572022-11-01T00:00:00Z
spellingShingle A comparative analysis to forecast carbon dioxide emissions
Md. Omer Faruque (17545671)
Engineering
Electrical engineering
Environmental engineering
Information and computing sciences
Machine learning
CO2
emissions
Forecasting
Deep learning
FMOLS
CNN–LSTM
status_str publishedVersion
title A comparative analysis to forecast carbon dioxide emissions
title_full A comparative analysis to forecast carbon dioxide emissions
title_fullStr A comparative analysis to forecast carbon dioxide emissions
title_full_unstemmed A comparative analysis to forecast carbon dioxide emissions
title_short A comparative analysis to forecast carbon dioxide emissions
title_sort A comparative analysis to forecast carbon dioxide emissions
topic Engineering
Electrical engineering
Environmental engineering
Information and computing sciences
Machine learning
CO2
emissions
Forecasting
Deep learning
FMOLS
CNN–LSTM