Perspectives of Machine Learning Development on Kerogen Molecular Model Reconstruction and Shale Oil/Gas Exploitation

Abstract

The shale revolution has provided abundant shale oil/gas resources for the world, but the efficient, sustainable, and environmentally friendly exploitation of shale oil/gas is still challenging. Kerogen is the primary hydrocarbon source of shale oil/gas. The research on the kerogen chemo-mechanical properties significantly influences the development of shale oil/gas extraction technology. Rapid reconstruction of the kerogen molecular models is the most effective way to study the generation mechanism of shale oil/gas from the bottom-up molecular level. However, due to the combinatorial explosion problem, the reconstruction complexity of kerogen increases sharply because of the kerogen’s characteristics of complex origin, large molecular weight, and diverse functional groups. The traditional kerogen molecular reconstruction methods require professionals to comprehensively analyze various experimental information to approximate the actual kerogen molecular models through trial-and-error. So, the traditional methods are time and material-consuming and extremely inefficient. These shortcomings make researchers spend too much strength on the reconstruction of kerogen molecular models and cannot focus on the study of kerogen chemo-mechanical properties. For the past few years, state-of-the-art machine learning (ML) methods have been applied to intelligently reconstruct the kerogen molecular models through high-throughput and predict shale oil/gas production mechanisms. Although the current work is still in the infancy stage, ML methods are believed to be the most promising way to solve the drawbacks of traditional methods and reconstruct kerogen in reliable and large molecular weight. Hence, mechano-energetics is proposed to study the efficient development and utilization of energy based on mechanics and ML. This paper briefly reviews the development history of kerogen molecular model reconstruction methods and the research of ML in the fields of kerogen reconstruction and shale oil/gas exploitation. Some recommendations for further ML-based work are also suggested. We are convinced that the ML methods will accelerate the research of kerogen and promote the significant development of unconventional oil/gas exploitation technologies.