Applications of Artificial Intelligence in Subsurface Exploration

Geophysical data analysis encompasses seismic and well-log-related methods used to characterize the subsurface and support exploration, production, and environmental applications. The rapid growth in data volume, acquisition complexity, and interpretation demands has made conventional processing and analysis increasingly time-consuming and computationally intensive. Recent advances in artificial intelligence (AI) and machine learning (ML), particularly deep learning, transformers, transfer learning, and physics-informed approaches, have demonstrated substantial potential for automated feature extraction, seismic processing, structural interpretation, reservoir characterization, and time-lapse monitoring. However, challenges remain regarding data quality, limited and imbalanced training datasets, model generalization across geological settings, uncertainty quantification, physical consistency, interpretability, and integration with established geophysical workflows. Further investigation is therefore needed to develop robust, explainable, and computationally efficient AI/ML methods that can support reliable subsurface decision-making.This Research Topic aims to advance the development and application of AI/ML methods for processing, analyzing, assimilating, and interpreting seismic, well log, and other geophysical data (GPR). It seeks to identify innovative algorithms and integrated workflows that improve the accuracy, efficiency, scalability, and reliability of subsurface characterization and monitoring. Contributions may address both theoretical and applied questions, including how physical knowledge can be incorporated into data-driven models, how models can be transferred between geological settings, how uncertainty and risk can be quantified, and how AI/ML can support real-time interpretation and decision-making in exploration, production, carbon capture, utilization, and storage (CCUS), gas hydrate, coal, and related applications.To gather further insights into AI/ML-enabled geophysical processing and subsurface interpretation, this Research Topic will cover methods and applications involving seismic, well log, GPR, and related geophysical datasets, while recognizing the limitations imposed by data availability, computational requirements, geological variability, and model interpretability. We welcome articles addressing, but not limited to, the following themes:• Deep learning and physics-informed neural networks for seismic and well log interpretation• AI/ML-based structural interpretation and reservoir characterization• AI/ML for seismic data processing, denoising, imaging, inversion, and attribute analysis• Machine learning for time-lapse monitoring and change detection• Integration of AI/ML models with conventional geophysical workflows• Reinforcement learning and transformer-based models for geophysical exploration and decision-making• Transfer learning, domain adaptation and cross-survey model generalization• Explainable and interpretable AI for geophysical data analysis• Real-time geophysical data interpretation and monitoring• Hybrid approaches combining AI/ML with physics-based and traditional geophysical methods• AI/ML applications in basin analysis, oil and gas exploration and production, gas hydrates, and coal exploration• AI/ML applications for GPR data processing and interpretation in shallow subsurface analysis• Uncertainty estimation and probabilistic forecasting in subsurface models• Risk reduction and decision support for geophysical exploration• Subsurface modelling and monitoring for CO₂ sequestration Topic editors: Bappa Mukherjee, Atul Kumar Patidar, Uma Shankar, Prof. Moataz Barakat Source: https://www.frontiersin.org/research-topics/80283/applications-of-artificial-intelligence-in-subsurface-exploration