Machine Learning Applications in Oil and Gas Industries Systems

Dear Colleagues,

We have organized a Special Issue on “Machine Learning Applications in Oil and Gas Industries Systems” in Fuels, and we would like to invite you to contribute to this Special Issue. Please feel free to disseminate this invitation within your group and among colleagues who may be interested.

Subsurface resources contribute to more than 80% of US energy resources (e.g., unconventional resources and geothermal energy) as well as 50% of US drinking water. The subsurface also serves as a reservoir for storing CO2 and energy waste. Therefore, optimizing subsurface resources in an environmentally friendly manner is critical for energy security. Achieving this optimization requires transformative advances in our ability to characterize, model, monitor, engineer, and sustain these resources. Recent advances in machine learning (ML) have shown promise in developing capabilities to characterize subsurface energy systems. Specifically, new approaches based on ML can effectively utilize multiple datasets (e.g., geological, geophysical, hydrological, geochemical, remote sensing, distributed temperature sensing, distributed acoustic sensing, electromagnetic, InSAR, LiDAR and GPR) that can sense the subsurface and identify critical system transitions (e.g., stress and evolution of fracture networks). As a result, ML can accelerate the development of advanced process control approaches to manage and engineer the subsurface for enhanced energy production. Examples include the development of reduced-order/surrogate models or emulators for predicting quantities of interest such as oil/water/gas production and dominant fracture paths for fluid flow.

The goal of our Special Issue is to include comprehensive review papers, case-studies, short communications, recent results, and studies related to the application of ML for oil and gas industries. Applications may also include machine learning methods and data analytics to discover and exploit new subsurface signatures; engineer subsurface systems; estimate the state of the stress; increase hydrocarbon extraction efficiency from unconventional reservoirs; control and manipulate permeability; optimize reservoir monitoring and analytics; improve prediction and detection of anomalous events during oil and gas operations.  

This Special Issue aims to bring ML researchers, geoscientists, hydrologists, oil and gas experts together in order to address key questions such as the following: How can we use machine learning and artificial intelligence tools to accelerate porous media model development, reduce simulation time, and detect more subsurface signatures from multiple datasets? How can we develop fast, reliable, and accurate emulators that can combine representative data across a range of scales to better calibrate process models? Topics of interest include but are not limited to the following:

• Surrogate models or emulators for energy production, storage, and extraction;
• Physics-informed machine learning for oil and gas systems;
• ML to discover and exploit oil and gas resources;
• ML-assisted inversion for subsurface imaging;
• ML models for subsurface fluid flow, thermal, and/or reactive transport;
• Artificial intelligence (AI) techniques/technologies/tools/software for subsurface resource management;
• Machine learning approaches or workflows to improve and optimize data acquisition;
• Advanced analytics for efficiency and automation in oil and gas operations;
• Efficient ML models for data compression, in situ monitoring, and/or edge computing;
• Explainable AI for geosciences;
• Advanced uncertainty quantification using machine learning.

Dr. Bulbul Ahmmed
Dr. Maruti Kumar Mudunuru
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fuels is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence； data mining and data analytics
• machine learning
• deep learning
• neural networks
• geothermal systems
• oil and gas
• fracture networks
• energy conversion and storage