Cover
Issue:2026 - Vol. 2 - Iss.2
Published:-
Articles:6 articles
Advanced Energy Systems and Intelligent Geoscience
Open access & Peer review··
AESIG
An international academic journal dedicated to the intersection of energy engineering, fundamental physics, and advanced computational science, dedicated to providing a high-quality academic exchange platform for researchers, scholars, and industry experts. The journal covers a wide range of research results, technological advancements, theoretical discussions, and practical applications in energy physics experimentation and computational technologies, with a particular focus on the cutting-edge dynamics and develo… More
2026 Vol.2 Iss.2 (5 articles)
Cover
Review Article
The Evolution of AI in the Oil and Gas Industry From Digitization to Intelligent Decision-Making
Abstract: Artificial intelligence and deep learning are becoming increasingly important in oil and gas field development, gradually becoming the development trend and research hotspot in the petroleum industry. Currently, over 70% of large oil and gas enterprises worldwide have listed the “physical-data dual-driven” model as their core strategy to make up for the shortcomings of pure data-driven models in generalization with small samples. This article focuses on the combination of the three major algorithms (CNN, RNN, and R…
Keywords: Artificial Intelligence; Deep Learning; Oil and Gas Development; Data-driven Model
AESIG 2026, 2(2), 4-16;
https://doi.org/10.58244/aesig.263718
Research Article
An Intelligent Water Injection Decision-Making and Production Optimization Method Based on SAC Deep Reinforcement Learning
Abstract: To address the failure of static water injection strategies in late-stage oilfield development caused by strong reservoir heterogeneity, this paper proposes an intelligent water injection and dynamic production optimization method using Soft Actor-Critic (SAC) deep reinforcement learning. By formulating waterflooding optimization as a Markov Decision Process (MDP), a Finite Volume Method (FVM) simulator is dynamically coupled with a deep learning environment. Departing from traditional methods that rely solely on w…
Keywords: Deep reinforcement learning; Soft Actor-Critic (SAC); Intelligent water injection decision-making; Closed-loop reservoir management; Spatial heterogeneity; Production optimization
AESIG 2026, 2(2), 17-33;
https://doi.org/10.58244/aesig.263879
Research Article
Application of a Geologically Constrained Bayesian Prototypical Network for Few-Shot Lithofacies Identification in Lacustrine Carbonate Rocks
Abstract: Accurate identification of lacustrine carbonate lithofacies is of critical importance for reservoir evaluation. However, conventional deep learning methods face significant bottlenecks in such complex settings, constrained by extreme class imbalance, the absence of uncertainty quantification in deterministic models, and insufficient geological prior knowledge. To address these limitations, this study proposes a Geologically Constrained Bayesian Prototypical Network (GC-BPN) that systematically overcomes these chall…
Keywords: Lacustrine carbonate rock; Lithofacies identification; Bayesian prototypical network; Geological constraint; Uncertainty quantification; Few-shot learning
AESIG 2026, 2(2), 34-50;
https://doi.org/10.58244/aesig.263906
Research Article
Prediction of Mineral Content and Petrophysical Parameters in Lacustrine Fine-Grained Mixed Sedimentary Rocks Based on a Physics-Informed Hybrid Deep Learning Framework
Abstract: To address the challenges of severe logging response overlap and quantitative mineral prediction caused by the strong heterogeneity of lacustrine carbonate reservoirs, this study proposes a hybrid framework integrating a physics-informed Gradient Boosting Decision Tree (LightGBM) and a Temporal Convolutional Network (PINN-TCN). The framework employs a sliding-window TCN to capture the deep contextual information of logging sequences, and introduces a truncation strategy along with a physics-constrained loss functio…
Keywords: Lacustrine carbonate; Mineral content prediction; Physics-informed constraints; Temporal Convolutional Network (TCN); Well logging interpretation; Model interpretability
AESIG 2026, 2(2), 51-64;
https://doi.org/10.58244/aesig.263907
Research Article
Zero-Shot Filling of FMI Blank Stripes Based on Deep Image Prior and an Attention-Enhanced Unet
Abstract: Fullbore Formation MicroImager (FMI) logging provides high-resolution electrical images of the borehole wall and has been widely used for fracture interpretation, dip analysis, and complex reservoir evaluation. However, due to limited pad coverage, borehole diameter variations, and unstable tool–wall contact, original FMI images commonly contain longitudinal blank stripes along the depth direction. These missing regions disrupt the continuity of key geological features, such as bedding interfaces, fractures, and vu…
Keywords: FMI logging; Blank-stripe filling; Deep image prior; U-Net; Poisson blending; Zero-shot learning
AESIG 2026, 2(2), 65-82;
https://doi.org/10.58244/aesig.263904
