Georeservoir engineering—including petroleum, geothermal, and CO₂ sequestration systems—plays a pivotal role in advancing global energy production, storage, and sustainability. This field has traditionally relied on physical models to inform decisions in reservoir characterization, drilling operations, and production management. However, these conventional approaches often rest on simplified assumptions and may lack the capacity to accurately capture the complex, dynamic behavior of reservoir systems. This can create challenges in operational efficiency and sustainability, leading to sub-optimal outcomes in resource recovery and environmental stewardship. Recent advances in artificial intelligence (AI), particularly machine learning (ML), have begun to offer transformative alternatives by leveraging large, multimodal datasets and integrating domain knowledge for more robust predictions, diagnostics, and real-time optimization.

Despite the promise of these AI-driven methodologies, important challenges remain. While early studies have demonstrated impressive performance in tasks like porosity and permeability estimation, drilling optimization, and anomaly detection, questions persist regarding the generalizability, interpretability, and reliability of ML models when applied to diverse reservoir types and real-world scenarios. Additionally, integrating physics-based understanding with data-driven methods to handle sparse, noisy, or heterogeneous data is an ongoing area of innovation. There is a strong need for systematic research and practical case studies that demonstrate the tangible benefits, address the limitations, and map the pathway for deploying ML technologies in the georeservoir domain.

This Research Topic aims to consolidate and showcase cutting-edge research that applies machine learning to improve georeservoir characterization, operational decision-making, and sustainability. It seeks to both highlight methodological innovations and present real-world case studies, with an emphasis on data integration across the reservoir lifecycle, uncertainty quantification, and intelligent automation. By fostering greater collaboration across geosciences, engineering, and AI, the topic intends to address open questions, drive deployment-ready advances, and promote energy efficiency while minimizing environmental impacts within georeservoir systems.

The scope of this Research Topic covers machine learning-enabled advancements for petroleum, geothermal, and CO₂ sequestration reservoirs, focusing on characterization, drilling, production, monitoring, and sustainability. Submissions should concentrate on the application and development of AI methods to solve practical and theoretical challenges in georeservoir management. To gather further insights in these areas, we welcome articles addressing, but not limited to, the following themes:

• Machine learning-based characterization of reservoir properties and integration of disparate geodata

• Predictive and automation models for efficient drilling and adaptive production

• Real-time monitoring, surveillance, anomaly detection, and predictive maintenance

• Data-driven strategies for environmental impact minimization, risk management, and sustainable operations

• Innovations in ML methodology, including hybrid models and the handling of sparse or noisy data.

Appendix on article types: We welcome original research, reviews, methods, perspectives, case studies, and brief research reports.

Are you interested in contributing a manuscript to this Research Topic?

Advancing Georeservoir Performance using Artificial Intelligence