A Bibliometric Analysis and Research Landscape of Machine Learning Applications in Greenhouse Gas Emissions

Abstract

This paper observes machine learning (ML) application in greenhouse gas (GHG) emission through a holistic bibliometric study, highlighting publication trends, influential contributors, and emerging research themes. Data were extracted from the Scopus database covering the period of 2008–2024. Bibliometric mapping was further performed to identify publication outputs, institutional contributions, collaboration patterns, and keyword co-occurrence networks. The analysis demonstrates a rapid growth in ML–GHG studies, with dominance of conference papers and journal articles. China and the United States are leading contributors especially in support of their institutions such as the U.S. Department of Energy and the Chinese Academy of Sciences. Research themes keep evolving from broad climate-related cases toward some advanced ML applications, including carbon capture optimization and real-time emissions monitoring. The study depends solely on Scopus data; it excluded relevant publications from other databases. Hence, expanding the data sources could offer a more inclusive perspective. The insights from the research can guide researchers, policymakers and industry practitioners on a deeper understanding of global trends as well as the identification of myriad opportunities for collaboration in applying ML for GHG/climate change mitigation. This research offers one of the first organized bibliometric overviews/summaries of ML applications in GHG mitigation, presenting a clearer picture of the field’s evolution, significant actors, and research hotspots.