Artificial intelligence methods for oil and gas reservoir development: Current progresses and perspectives

Методы искусственного интеллекта для разработки нефтегазовых залежей: современное состояние и перспективы
Liang Xue, Daolun Li, Hongen Dou
2023-10-23

artificial neural networksdeep learningphysics-informed neural networksreservoir engineeringreservoir simulation
Artificial neural networks have been widely applied in reservoir engineering. As a powerful tool, it changes the way to find solutions in reservoir simulation profoundly. Deep learning networks exhibit robust learning capabilities, enabling them not only to detect patterns in data, but also uncover underlying physical principles, incorporate prior knowledge of physics, and solve complex partial differential equations. This work presents the latest research advancements in the field of petroleum reservoir engineering, covering three key research directions based on artificial neural networks: data-driven methods, physics driven artificial neural network partial differential equation solver, and data and physics jointly driven methods. In addition, a wide range of neural network architectures are reviewed, including fully connected neural networks, convolutional neural networks, recurrent neural networks, and so on. The basic principles of these methods and their limitations in practical applications are also outlined. The future trends of artificial intelligence methods for oil and gas reservoir development are further discussed. The large language models are the most advanced neural networks so far, it is expected to be applied in reservoir simulation to predict the development performance. Document Type: Perspective Cited as: Xue, L., Li, D., Dou, H. Artificial intelligence methods for oil and gas reservoir development: Current progresses and perspectives. Advances in Geo-Energy Research, 2023, 10(1): 65-70. https://doi.org/10.46690/ager.2023.10.07
1
Artificial neural networks are transforming reservoir simulation by providing alternative approaches to solving complex reservoir-engineering problems.
2
Deep learning can detect data patterns, learn underlying physical principles, incorporate prior physics knowledge, and solve complex partial differential equations.
3
Large language models are identified as a prospective future technology for predicting oil and gas reservoir development performance.
4
The paper reviews fully connected, convolutional, recurrent, and other neural-network architectures, while outlining their fundamental principles and practical application limitations.
5
The review organizes current methods into data-driven approaches, physics-driven neural-network partial differential equation solvers, and jointly data- and physics-driven methods.

oil and gas reservoir development and simulation

applications, capabilities, limitations, and future prospects of artificial neural network and physics-informed AI methods for reservoir engineering

Publication Details
Publication Date
2023-10-23
Journal
Publisher
ISSN
Cited by
38
Access Type
Author Information
Authors
Liang Xue
Daolun Li
Hongen Dou
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%