Home > Research > Publications & Outputs > A systematic review of machine learning approac...


Text available via DOI:

View graph of relations

A systematic review of machine learning approaches in carbon capture applications

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Article number102474
<mark>Journal publication date</mark>31/05/2023
<mark>Journal</mark>Journal of CO2 Utilization
Number of pages16
Publication StatusPublished
Early online date13/04/23
<mark>Original language</mark>English


Climate change and global warming are among of the most important environmental issues and require adequate and immediate global action to preserve the planet for future generations. One of the essential technologies used to reduce CO2 emissions and mitigate the worst effects of climate change is carbon capture technology. Many efforts have been made by scientists, industrial sectors, and policy-makers in looking for new technology to reduce greenhouse gas emissions and achieve net-zero emission goals. Research and development in creating new technology involve complex processes and require a digital system to optimize big data prediction as well as to reduce production time. A mathematical and statistical approach such as machine learning plays an important role in solving research problems, whereby this approach provides fast results in predicting big data and cost-efficient tools. In this study, a systematic review and bibliometric analysis were used to analyze the research trend, particularly on the keywords, number of publications, citations, countries, and authorship. This information is important for future research directions for researchers who venture into this area. In this study, the bibliometric analysis focuses on 2 main categories: co-authorship (countries and organizations) and keywords (author keyword). Based on the research trend, the United States (USA), China, Iran, Canada, and the United Kingdom are the leading countries contributing to this field since they have the highest publications and citations. Furthermore, the most common keywords used in the selected articles ranked according to the highest link strength. The top 6 keyword list includes machine learning, artificial neural network, CO2 capture, CO2 solubility, metal-organic frameworks (MOFs) and carbon capture and storage. The findings from this study can be used to open a wider spectrum for the research communities by providing global research trends, current innovations and current technology on machine learning in carbon capture application, identifying the active research areas or hot topics and future research direction to help fight climate change issue using smart advanced technology.