Nowcasting CO2 emissions in Bangladesh: a machine learning approach. Hossain, M., M., Abdulla, F., Rahman, A., Uddin, M., G., & Olbert, A., I. Discover Sustainability 2026, Springer, 2026. ![Nowcasting CO2 emissions in Bangladesh: a machine learning approach [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex Carbon dioxide (CO2) remains the leading contributor to global warming, primarily released through the combustion of fossil fuels in electricity generation, transportation, industry, and residential use. Accurate estimation of CO2 emissions from different sources is therefore essential for designing effective policies to achieve the Sustainable Development Goals (SDGs). This study aimed to nowcast annual CO2 emissions in Bangladesh from 1955 to 2021 using various machine learning models, including Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and Support Vector Model (SVM), and compared them with the traditional ARIMA model. The best-performing model was selected based on root mean square error (RMSE) and mean absolute percentage error (MAPE). Among the models, SVM achieved the best performance for oil, cement, and gas, while ANN outperformed others for coal. These findings demonstrate that machine learning models provide the most accurate nowcasting compared to ARIMA, and it is recommended to consider a machine learning model for the nowcasting of CO2 emissions in Bangladesh.
@article{
title = {Nowcasting CO2 emissions in Bangladesh: a machine learning approach},
type = {article},
year = {2026},
keywords = {Environment,Sustainable Development,general},
websites = {https://link.springer.com/article/10.1007/s43621-025-02579-7},
publisher = {Springer},
id = {40482f60-095d-3547-8f78-e573672a5419},
created = {2026-01-31T10:01:38.246Z},
file_attached = {false},
profile_id = {3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f},
last_modified = {2026-01-31T10:01:38.246Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
source_type = {JOUR},
private_publication = {false},
abstract = {Carbon dioxide (CO2) remains the leading contributor to global warming, primarily released through the combustion of fossil fuels in electricity generation, transportation, industry, and residential use. Accurate estimation of CO2 emissions from different sources is therefore essential for designing effective policies to achieve the Sustainable Development Goals (SDGs). This study aimed to nowcast annual CO2 emissions in Bangladesh from 1955 to 2021 using various machine learning models, including Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and Support Vector Model (SVM), and compared them with the traditional ARIMA model. The best-performing model was selected based on root mean square error (RMSE) and mean absolute percentage error (MAPE). Among the models, SVM achieved the best performance for oil, cement, and gas, while ANN outperformed others for coal. These findings demonstrate that machine learning models provide the most accurate nowcasting compared to ARIMA, and it is recommended to consider a machine learning model for the nowcasting of CO2 emissions in Bangladesh.},
bibtype = {article},
author = {Hossain, Md. Moyazzem and Abdulla, Faruq and Rahman, Azizur and Uddin, Md Galal and Olbert, Agnieszka I},
doi = {10.1007/S43621-025-02579-7},
journal = {Discover Sustainability 2026}
}
Downloads: 0
{"_id":"QjKchAu9YfkvbCDtw","bibbaseid":"hossain-abdulla-rahman-uddin-olbert-nowcastingco2emissionsinbangladeshamachinelearningapproach-2026","author_short":["Hossain, M., M.","Abdulla, F.","Rahman, A.","Uddin, M., G.","Olbert, A., I."],"bibdata":{"title":"Nowcasting CO2 emissions in Bangladesh: a machine learning approach","type":"article","year":"2026","keywords":"Environment,Sustainable Development,general","websites":"https://link.springer.com/article/10.1007/s43621-025-02579-7","publisher":"Springer","id":"40482f60-095d-3547-8f78-e573672a5419","created":"2026-01-31T10:01:38.246Z","file_attached":false,"profile_id":"3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","last_modified":"2026-01-31T10:01:38.246Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"source_type":"JOUR","private_publication":false,"abstract":"Carbon dioxide (CO2) remains the leading contributor to global warming, primarily released through the combustion of fossil fuels in electricity generation, transportation, industry, and residential use. Accurate estimation of CO2 emissions from different sources is therefore essential for designing effective policies to achieve the Sustainable Development Goals (SDGs). This study aimed to nowcast annual CO2 emissions in Bangladesh from 1955 to 2021 using various machine learning models, including Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and Support Vector Model (SVM), and compared them with the traditional ARIMA model. The best-performing model was selected based on root mean square error (RMSE) and mean absolute percentage error (MAPE). Among the models, SVM achieved the best performance for oil, cement, and gas, while ANN outperformed others for coal. These findings demonstrate that machine learning models provide the most accurate nowcasting compared to ARIMA, and it is recommended to consider a machine learning model for the nowcasting of CO2 emissions in Bangladesh.","bibtype":"article","author":"Hossain, Md. Moyazzem and Abdulla, Faruq and Rahman, Azizur and Uddin, Md Galal and Olbert, Agnieszka I","doi":"10.1007/S43621-025-02579-7","journal":"Discover Sustainability 2026","bibtex":"@article{\n title = {Nowcasting CO2 emissions in Bangladesh: a machine learning approach},\n type = {article},\n year = {2026},\n keywords = {Environment,Sustainable Development,general},\n websites = {https://link.springer.com/article/10.1007/s43621-025-02579-7},\n publisher = {Springer},\n id = {40482f60-095d-3547-8f78-e573672a5419},\n created = {2026-01-31T10:01:38.246Z},\n file_attached = {false},\n profile_id = {3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f},\n last_modified = {2026-01-31T10:01:38.246Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n source_type = {JOUR},\n private_publication = {false},\n abstract = {Carbon dioxide (CO2) remains the leading contributor to global warming, primarily released through the combustion of fossil fuels in electricity generation, transportation, industry, and residential use. Accurate estimation of CO2 emissions from different sources is therefore essential for designing effective policies to achieve the Sustainable Development Goals (SDGs). This study aimed to nowcast annual CO2 emissions in Bangladesh from 1955 to 2021 using various machine learning models, including Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and Support Vector Model (SVM), and compared them with the traditional ARIMA model. The best-performing model was selected based on root mean square error (RMSE) and mean absolute percentage error (MAPE). Among the models, SVM achieved the best performance for oil, cement, and gas, while ANN outperformed others for coal. These findings demonstrate that machine learning models provide the most accurate nowcasting compared to ARIMA, and it is recommended to consider a machine learning model for the nowcasting of CO2 emissions in Bangladesh.},\n bibtype = {article},\n author = {Hossain, Md. Moyazzem and Abdulla, Faruq and Rahman, Azizur and Uddin, Md Galal and Olbert, Agnieszka I},\n doi = {10.1007/S43621-025-02579-7},\n journal = {Discover Sustainability 2026}\n}","author_short":["Hossain, M., M.","Abdulla, F.","Rahman, A.","Uddin, M., G.","Olbert, A., I."],"urls":{"Website":"https://link.springer.com/article/10.1007/s43621-025-02579-7"},"biburl":"https://bibbase.org/service/mendeley/3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","bibbaseid":"hossain-abdulla-rahman-uddin-olbert-nowcastingco2emissionsinbangladeshamachinelearningapproach-2026","role":"author","keyword":["Environment","Sustainable Development","general"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","dataSources":["2252seNhipfTmjEBQ"],"keywords":["environment","sustainable development","general"],"search_terms":["nowcasting","co2","emissions","bangladesh","machine","learning","approach","hossain","abdulla","rahman","uddin","olbert"],"title":"Nowcasting CO2 emissions in Bangladesh: a machine learning approach","year":2026}