Special Issue on Advances in Artificial Intelligence for Energy Systems and Subsurface Engineering

Introduction:

Artificial Intelligence (AI) enables data-driven decision-making, improving subsurface understanding, and optimizing complex engineering workflows. In energy geoscience systems, AI is no longer limited to predictive analytics; it is evolving toward integrated, autonomous, and physics-informed intelligence that can support end-to-end workflows from exploration to production and monitoring.

Recent advances in machine learning, physics-informed AI, and agentic systems have enabled new paradigms in subsurface interpretation, reservoir characterization, production optimization, and real-time operational control. In parallel, the increasing availability of multi-scale, multi-modal datasets—including seismic, well logs, production data, geochemical signals, and continuous monitoring sensor data—has created unprecedented opportunities for AI-driven integration and interpretation.

Despite these advances, notable challenges remain in model generalization, data quality, uncertainty quantification, and real-world deployment. There is a g need to bridge the gap between algorithm development and field-scale application, ensuring that AI solutions are robust, interpretable, and operationally actionable.

This Special Issue aims to present the latest achievements, implementations, and perspectives on AI applications in energy geoscience systems, with an emphasis on real-world case studies as well as future directions in intelligent sensing, data integration, and autonomous monitoring systems.

Topics of interest include but are not limited to:

1. Advanced AI for Subsurface Modeling

• Physics-informed neural networks, neural operators, and surrogate models
• Hybrid physics–ML approaches for prediction and uncertainty quantification

2. Data Integration and Subsurface Characterization

• AI-driven reservoir modeling and subsurface characterization
• Multi-modal data integration (seismic, well logs, geochemical, monitoring data)

3. Real-Time Prediction and Decision-Making

• Real-time data assimilation and adaptive model updating
• AI for production optimization and reservoir management
• Applications in geothermal systems and CO₂ storage

4. Digital Twins and Closed-Loop Systems

• AI-enabled digital twins integrating sensing, modeling, and control
• Scalable architectures and deployment frameworks

5. Validation, Benchmarking, and Trustworthy AI

• Field and laboratory case studies
• Benchmark datasets and reproducibility
• Uncertainty quantification and model interpretability

6. Emerging Directions

• Agentic AI, multi-agent systems, federated learning

We invite contributions that offer new insights, solutions, and case studies. By bringing together methodological innovations and practical experiences, this Special Issue seeks to define a forward-looking roadmap for AI-enabled transformation of global energy systems.

Important deadlines:

• Submission deadline: 31 October 2026

Submission instructions: 

Please read the Guide for Authors before submitting. All articles should be submitted online, please select "SI: AI for energy "on submission. All submissions will undergo a normal peer-review process.

Guest Editors:

• He Liu, Research Institute of Petroleum Exploration and Development, China. Email: liuhe@petrochina.com.cn
• Gensheng Li, China University of Petroleum (Beijing), China. Email: ligs@cup.edu.cn
• Pushpesh Sharma, AspenTech, USA. Email: s.pushpesh@gmail.com
• Xinming Wu, University of Science and Technology of China, China. Email: xinmwu@ustc.edu.cn
• Pejman Shoeibi Omrani, Geological Survey of the Netherlands, Netherlands. Email: pejman.shoeibiomrani@tno.nl
• Ali Syed Asghar, University of Colorado-Denver, USA. Email: syed51214@hotmail.com