A bibliometric analysis of the application of machine learning methods in the petroleum industry

With the emerge of Artificial Intelligence and Machin learning systems, the petroleum industry has witnessed a significant progress in its different disciplines to optimize decision making, time and costs. Despite the widespread application of using machine learning methods in the petroleum industry, a little attention has been devoted to build a framework to bring the main currents and researches on the topic. The current research is aimed at covering this gap through further analysis of complementary sources of bibliographic information, assessing 3163 bibliometric studies published in Web of Science (WOS) database. The descriptive statistics show that this field has an exponential growth in the last five years, such that more than 62 % of identified articles were published between 2018 and 2022. CHINA, IRAN and US are the pioneer countries with the highest number of publications on the application of artificial intelligence and machine learning in the upstream sector of the petroleum industry. The most influential journal in this field is 'JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING' (with 416 articles) (the current journal title is Geoenergy Science and Engineering) and the most productive author is SALAHELDIN ELKATATNY (with 54 articles) in WOS database. Also, the co-occurrence word analysis show that most of the artificial intelligence and machine learning applications in the upstream sector of the petroleum industry was the prediction and optimization in the field of 'porosity', 'well logs' and 'permeability'. This paper contributes to the body of knowledge by providing a comprehensive overview of the application of artificial intelligence and machine learning in the upstream petroleum industry.