Data-Driven Machine Learning Approaches and Advanced Numerical Modelling Technology for Sustainable Geo-Energy Management

Dear Colleagues:

Nowadays, various geo-energy resources, including oil fossil, geothermal and carbohydrate, etc., are widely distributed and abundant across the world. The subsurface flow mechanisms, e.g., multi-phase and multi-scale flow and physic–chemistry reaction in porous media, is highly complex. The description of the structures of media with different scales, such as matrix, natural fractures, and induced fracture network, is also difficult. In addition, some special flow behavior cannot be simulated by the use of conventional theory. That becomes a more critical issue whenever one faces intensive simulation-based applications, such as sensitivity analysis, optimization, or uncertainty quantification. Such time-consuming tasks often hamper the use of high-fidelity codes constructed upon physics-based models.  Their applications are largely restricted by the huge computational cost of, amongst other factors, the many runs of the full physics model. Therefore, it is necessary to propose advanced modelling technologies and acceleration methods for flow characterization.

At the same time, motivated by rapid advancements in the application of big data technology and deep learning to computer vision, image processing, simulation of dynamic systems, wide availability of high-performance processing units (GPU's) and deep learning frameworks (e.g., Tensorflow and PyTorch), smart development of subsurface resources has become increasingly popular recently. This is especially true in the context of groundwater hydrology, oil and gas production, geothermal energy extraction, and geologic carbon sequestration. The growing applications of these methods has been predicated on their potential to usher in exciting new developments related to: (1) acquiring and managing data in large volumes, of different varieties, and at high velocities, and (2) using statistical techniques to mine the data and discover hidden patterns of associations and relationships in large, complex, multivariate datasets. The ultimate goal in the use of these technologies is to build data-driven models and extract data-driven insights to understand and optimize the performance of injection/production systems involving flow in geologic systems. 

This Special Issue aims to present recent advances in various subjects addressing new data-driven approaches and modelling techniques for the exploration of subsurface resources efficiently and effectively. We will report some new findings to investigate how big data can be used for performance prediction, uncertainty reduction, and optimization in subsurface resource development. This will include topics such as the optimization of oil field, geothermal, carbohydrate and geological carbon storage operations, optimization under uncertainty, solution of inverse problems and geological model characterization. We invite investigators to contribute new work that will explore as many aspects as possible in the modelling of hydrocarbon energy exploration and development.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Complex geological model characterization and parameterization technology
• Machine learning-based big data compression and feature extraction
• Reservoir characterization and evaluation of subsurface modelling
• Advanced data assimilation and uncertainty quantification technology
• Advanced numerical modelling techniques, e.g., multi-scale modelling and operator-based linearization, ect.
• high-fidelity reservoir simulations in subsurface energy transition process
• Closed-loop subsurface resource management technology
• High-performance computing, e.g., parallel algorithms using multi-CPUs and GPU accelerators
• Design of deep learning architecture and automatic-optimization technology
• Surrogate modelling, e.g., reduced-order modeling, machine learning and deep learning, etc.
• Benchmark demonstrations in oil reservoir, geothermal, carbohydrate and deep saline geological carbon storage

We look forward to receiving your contributions.

Dr. Cong Xiao
Dr. Fei Wang
Dr. Xiaocong Lyu
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. Sustainability is an international peer-reviewed open access semimonthly 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 2400 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.

• geo-energy
• data-driven modeling sensitivity analysis
• optimization
• uncertainty quantification