An extensive investigation on leveraging machine learning techniques for high-precision predictive modeling of CO₂ emission

ABSTRACT

Predictive analytics utilizing machine learning algorithms play a pivotal role in various domains, including the profiling of carbon dioxide (CO₂) emissions. This research paper delves into an extensive exploration of different algorithms, encompassing neural networks with diverse architectures, optimization, training, ensemble, and specialized algorithms. The primary objective of this research is to evaluate the efficacy of supervised and unsupervised algorithms, including Deep Belief Networks, Feed Forward Neural Networks, Gradient Boosting, and Regression, as well as Convolutional Neural Networks, Gaussian, Grey, and Markov models, and clustering and optimization algorithms. The study places particular emphasis on data-driven methodologies and cross-validation techniques with an evaluation of the learning models entailing comprehensive training, validation, and testing, employing evaluation metrics such as R2, MAE, and RMSE. The study employs correlation analysis to examine the relationship between input parameters and emission characteristics. The research highlights the advantageous attributes of these algorithms in accurately forecasting CO₂ emissions, evaluating energy sources, improving prediction accuracy, and estimating emissions. Notably, deep learning, Artificial Neural Networks (ANN), and Support Vector Machines (SVM) demonstrate effectiveness across diverse industries, while the Modified Regularized Fast Orthogonal-Extreme Learning Machine (MRFO-ELM) algorithm optimizes predictions specifically related to coal chemical emissions. Hybrid techniques demonstrate accuracy in predicting carbon emissions and energy consumption, whereas gray prediction models provide reliable estimates even with limited data. However, it is important to acknowledge certain limitations, including data requirements, potential inaccuracies arising from complex factors, constraints faced by developing countries, and the impact of electric vehicle expansion on the power grid. To optimize models, a survey is conducted, involving customization of parameters and learning rates, while exploring various performance metrics to evaluate model accuracy. The research outcomes contribute to the effective monitoring of CO₂ emissions in operational environments, thereby aiding executive decision-making processes.

KEYWORDS:

• Machine learning
• Deep learning
• CO₂ emission profiling
• Predictive analytics
• Hyperparameter tuning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Van Giao Nguyen

Van Giao Nguyen is a lecturer at HUTECH University. He received the Ph.D in Mechanical Engineering degree from Wuhan University of Technology, China in 2019. Dr. Van Giao Nguyen is a member of the AME Research Group at his university since 2022. His research interests include automobile engineering, biofuels, emission management, and general energy.

Xuan Quang Duong

Xuan Quang Duong is a lecturer at Vietnam Maritime University. He received the B.E. and M.S. degrees from Vietnam Maritime University, Hai Phong, Vietnam, in 2010 and 2014, respectively, and the PhD degree from Sejong University, Seoul, South Korea, in 2019, all in Mechanical Engineering. His research interests include thermal driven systems such as adsorption chiller or thermal storage systems using heat and mass transfer, biomass, robotics and mechanical design.

Lan Huong Nguyen

Lan Huong Nguyen is a lecturer at Vietnam Maritime University. She received the Ph.D degree from Vietnam Maritime University in 2016. Her research interests include diesel engines, biofuels, emission management, and general energy.

Phuoc Quy Phong Nguyen

Dr. Phuoc Quy Phong Nguyen is a lecturer at Ho Chi Minh city University of Transport, Ho Chi Minh, Vietnam. He received the Ph.D in 2014. His research interests lie in the fields of Renewable energy, Alternative fuels, Maritime Safety, and Engineering Transport. Dr. Phuoc Quy Phong Nguyen is a member of Progress of Applied Technology and Engineering in Transport Research Group (PATET) at the University since 2022.

Jayabal Chandra Priya

Dr. Jayabal Chandra Priya holds the designation of Assistant Professor in the Department of Computer Science and Engineering at Mepco Schlenk Engineering College, Sivakasi, Tamil Nadu, and possesses the certification of a Certified Blockchain Associate. In 2021, she served as an IEEE Ambassador for the IEEE Madras section. She earned her BE degree in Computer Science Engineering from Anjalai Ammal Mahalingam Engineering College, Tiruvarur, Anna University, Chennai, India, in the year 2013. Subsequently, in 2015, she obtained her M.E. in Computer Science Engineering from Anna University, Trichy, during which she was honored with a National fellowship from the Technical Education Quality Improvement Programme. Her academic journey also includes a Ph.D. pursued at MIT, Anna University, Chennai, India with research interests primarily encompass Wireless Networks, Cryptography, Blockchain, and Network Security. Her contributions to the field are evident through collaborations on book chapters and the publication of numerous research papers in various esteemed peer-reviewed international journals and conferences, indexed by renowned publishers such as Elsevier, Wiley, and Springer. She is also a distinguished lifetime member of the Indian Society for Technical Education.

Thanh Hai Truong

MSc Thanh Hai Truong is a lecturer at Ho Chi Minh city University of Transport University. His research interests lie in the fields of Renewable energy, Alternative fuels, Marine engines, and Engineering Transport. Thanh Hai Truong is a member of Progress of Applied Technology and Engineering in Transport Research Group (PATET) at the University since 2022.

Huu Cuong Le

MSc Huu Cuong Le is a lecturer at Ho Chi Minh city University of Transport University. His research interests lie in the fields of Alternative fuels and Marine engines.

Nguyen Dang Khoa Pham

Nguyen Dang Khoa Pham is a lecturer at Ho Chi Minh city University of Transport. He received the Ph.D degree from Ho Chi Minh city University of Transport, Ho Chi Minh, Vietnam in 2021. His research interests lie in the fields of Renewable energy, Alternative fuels, Maritime Safety, and Engineering Transport. Dr. Nguyen Dang Khoa Pham is a member of Progress of Applied Technology and Engineering in Transport Research Group (PATET) at the University since 2022.

Xuan Phuong Nguyen

Xuan Phuong Nguyen is an Associate Professor at the Ho Chi Minh City University of Transport, VietNam. He received a PhD degree in 2011. His research interests lie in the fields of Energy conservation, Renewable energy resources, Alternative fuels, Internal Combustion Engines, Maritime Safety, and Engineering Transport. Xuan Phuong Nguyen has been leading research from Progress of Applied Technology and Engineering in Transport Research Group (PATET) at the University since 2019. He is authored close to 80 publications with an h-index of 29.