In the quest to unlock the secrets of the Earth’s subsurface, a team of researchers led by Mitra Khalilidermani from the Department of Drilling and Geoengineering at the AGH University of Krakow has made significant strides in understanding and predicting shear wave velocity (Vs). This critical geomechanical variable is pivotal in exploring and managing subsurface resources, from hydrocarbon reservoirs to geothermal energy and even carbon capture and storage (CCS) projects. Their comprehensive review, published in the journal *Energies*, sheds light on the latest applications, estimation methods, and challenges in Vs prediction, with a particular focus on energy-efficient techniques.
Shear wave velocity is a key parameter in subsurface exploration, providing insights into the mechanical properties of rocks and sediments. Accurate prediction of Vs is essential for assessing the potential of hydrocarbon reservoirs, identifying geothermal resources, and even mitigating geohazards. However, traditional methods of estimating Vs can be time-consuming and costly, often requiring extensive field data and complex geophysical surveys.
Khalilidermani and her team have explored a range of innovative approaches to overcome these challenges. Among the most promising are artificial intelligence (AI) techniques, particularly machine learning (ML) and deep learning (DL). These methods have demonstrated superior accuracy by capturing complex subsurface relationships and integrating diverse datasets. “AI-driven models offer a more efficient and cost-effective way to predict Vs,” Khalilidermani explains. “They can automate the process, reducing the need for extensive field data and providing more reliable results.”
The integration of AI with traditional geophysical and remote sensing methods holds significant potential for the energy sector. By enhancing the accuracy and efficiency of Vs prediction, these advanced techniques can lead to more informed decision-making in subsurface exploration and resource management. This is particularly relevant for emerging applications like CCS, where understanding subsurface properties is crucial for safe and effective carbon storage.
However, challenges remain. Data availability, model interpretability, and generalization across different geological settings are key areas that need further attention. Khalilidermani emphasizes the importance of continued research in these areas. “While AI offers exciting possibilities, we need to ensure that these models are robust, interpretable, and applicable across diverse geological settings,” she notes.
The findings of this review offer valuable insights for geoscientists and engineers across various disciplines, including petroleum engineering, mining, geophysics, geology, hydrogeology, and geotechnics. By leveraging the latest advancements in AI and integrating them with traditional methods, the energy sector can enhance its capabilities in subsurface exploration and resource management.
As the world transitions towards more sustainable energy solutions, the accurate prediction of shear wave velocity will play a crucial role in unlocking the Earth’s subsurface resources. The work of Khalilidermani and her team not only advances our understanding of Vs prediction but also paves the way for more efficient and sustainable energy practices. With continued research and innovation, the energy sector can look forward to a future where AI-driven models and traditional geophysical methods work hand in hand to meet the challenges of subsurface exploration.