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

Published by: Macao Scientific Publishers (MOSP)
Editor-in-Chief: Prof. Hui Zhao, Prof. Yuhui Zhou, Prof. Xiang Rao
Copyright: Open access under CC BY 4.0
ISSN: Print-ISSN: 3106-9886 ｜ Online-ISSN: 3106-9894
indexed within: OpenAlex Crossref

Online First (4 articles)

Note: Accepted articles pending volume/issue assignment.

Research ArticleOnline First

Time-series Dynamic Prediction of Geological CO₂ Storage Based on Quantum-Inspired Kolmogorov-Arnold Network and Long Short-Term Memory Network

By: Xi Ouyang, Xiang Rao^*

Abstract: Against the background of the carbon peaking and carbon neutrality strategy, carbon capture, utilization and storage (CCUS) technologies are gradually transitioning from small‑scale demonstrations to large‑scale engineering deployment. Practical demands for batch site screening and long‑term storage risk assessment keep growing. High‑fidelity numerical simulation for conventional geological CO₂ storage incurs enormous computational cost, making it difficult to support rapid evaluation of numerous schemes. To tackle…

Keywords: carbon capture; utilization and storage (CCUS); geological CO₂; storage; quantum‑inspired machine learning; QKAN‑LSTM

AESIG 0000, 0(0), 1-6; https://doi.org/10.58244/aesig.260002

Full Text Views: 49 | Downloads: 0

Research ArticleOnline First

A High-fidelity Boundary Integral Neural Network (BINN) For Safety Monitoring and Localization Of CO₂ Leakage in Depleted Shale Reservoirs

By: Yina Liu, Xiang Rao^*, Qirun Fu, Hussein Hoteit

Abstract: Geological CO₂ storage in depleted shale reservoirs requires robust and efficient leakage monitoring. Conventional grid-based methods are limited by high computational cost and meshing complexity, while Physics-Informed Neural Networks (PINNs) suffer from slow convergence near boundaries and singularities. To overcome these limitations, this study proposes a Boundary‑Integral Neural Network (BINN) framework for rapid and accurate leakage inversion. BINN embeds the boundary integral form of the governing flow equati…

Keywords: CO₂ leakage monitoring; Physics-Informed Neural Networks (PINNs); Boundary-integral neural network (BINN); Inverse problem; Hybrid optimization

AESIG 0000, 0(0), 1-6; https://doi.org/10.58244/aesig.260001

Full Text Views: 45 | Downloads: 0

Research ArticleOnline First

Machine-Learning Identification of Sedimentary Microfacies by Integrating Well-Log Morphological Features: A Case Study of the PI Oil Group in the Lanea E2 Block, Chad

By: Meng Huang, Xiaolong Wang, Fei Yang, Xiaoliang Pan, Yipu Li, Weimin Zhang, Shangyuan Yang

Abstract: Accurate identification of sedimentary microfacies in fan-delta fronts is fundamental to reservoir heterogeneity characterization and exploration planning. Conventional manual interpretation of electrofacies is inefficient and subjective, while conventional log responses of different microfacies overlap substantially, making robust discrimination difficult when only amplitude information is used. This study quantifies well-log curve morphology as machine-learning features and develops an improved random forest meth…

Keywords: Keywords: fan-delta front; sedimentary microfacies; well-log curve morphology; random forest; Borderline-SMOTE; Lanea E2 Block

AESIG 0000, 0(0), 1-6; https://doi.org/10.58244/aesig.264025

Full Text Views: 76 | Downloads: 0

Research ArticleOnline First

Study on the Elastic-Plastic Properties of Deep Well Complex Fractured Loss Formations and the Performance and Plugging Characteristics of Drilling Lost Circulation Materials

By: Haoxian Guo, Guojia Li*, Han Lin, Zehan Yin, Chaomei Li

Abstract: To address issues in deep wells with complex fractured loss formations—such as drilling fluid lost circulation materials having difficulty entering fractures, challenges in controlling plugging locations, and material performance degradation under high temperatures—a ductile-elastic drilling fluid lost circulation material suitable for high-temperature and high-pressure environments has been developed. Through tests of physical and mechanical properties, porous media plugging experiments, and pressure-bearing evalu…

Keywords: Deep well; fracture-type loss; drilling fluid loss control; Resilience materials; sealing mechanism

AESIG 0000, 0(0), 1-6; https://doi.org/10.58244/aesig.263946

Full Text Views: 81 | Downloads: 0