Current scenario of machine learning applications to hydrothermal liquefaction via bibliometric analysis [version 2; peer review: 1 approved with reservations, 1 not approved]

Background Energy shortages and global warming have been significant issues throughout history. Therefore, the search for environmentally friendly renewable energy sources is crucial for achieving sustainability. Biomass energy is gaining global attention as a renewable energy option, particularly through the process of hydrothermal liquefaction, which converts wet biomass into bio-crude oil. Methods Hydrothermal liquefaction is a complex process that is challenging to explain, leading to research on machine learning models for this process. These models aim to predict values and investigate the impact of variables on the hydrothermal liquefaction process. These models aim to predict values and investigate the impact of variables on the hydrothermal liquefaction process. However, the development of machine learning in hydrothermal liquefaction is still limited due to its novelty and the time required for comprehensive study. Thus, the objective of this study was to analyze relevant publications in the Scopus database, focusing on indexed ML and HTL keywords, to understand keyword associations and co-citations. Results The results reveal an increasing trend in the study of ML in the HTL process, with a growing interest from various countries. Conclusion Notably, China currently holds the largest share of ML research in HTL processes, with most published works falling within the field of engineering. The keyword “liquefaction” emerges as the most popular term in these publications.