24th November

Session 1: DBM Transformative journey: Milestones, Latest Progress, and the Road Ahead

Join us on a journey through the evolution of Decision-Based Modeling (DBM), a holistic approach that integrates geological, geophysical, and engineering data to support informed decision-making in reservoir modeling. DBM is a systematic process that quantifies uncertainty, evaluates multiple scenarios, and optimizes outcomes, enabling teams to make better decisions and reduce risk. This session will delve into the transformative progress of DBM, from its inception to the latest advancements and innovations. Key milestones, successes, and challenges will be underscored, providing valuable insights into the current state of DBM. Discover how DBM's unique blend of data-driven analysis, probabilistic modeling, and collaborative workflows enhances reservoir modeling, and explore the road ahead for this discipline. Gain insights from real-world case studies and benchmarked best practices, enabling you to unlock the full potential of DBM in your own reservoir modeling endeavors.

Session 2: Multidisciplinary Data Integration in Reservoir Modeling

Real time integration of diverse sources of data covering various spatio-temporal scales is a key component of DBM. It continues to be a challenge as the problems are typically ill posed meaning that non-uniqueness and uncertainty must feature in any proposed solution. This session will consider practical and innovative paradigms for this data integration, showcasing new approaches in geostatistics, geomodeling, data assimilation and multi-modal AI techniques. Topics will cover the integration of a range of drilling data, geophysical data and production data used for reservoir characterization and monitoring. Both new data types and innovative integration techniques will be considered. Attendees will learn and discuss about how to best integrate domain knowledge in modern data science approaches to increase model predictivity and interpretability. This session will provide new insights about how to best harness subsurface complexity, quantify uncertainties, assess the value of new data, and align data integration tasks with the needs of decision making.

25th November

Session 3: Embracing Innovation: AI and ML

This session highlights the transformative potential of Artificial Intelligence (AI) and Machine Learning (ML) in advancing Decision-Based Modeling (DBM) workflows in subsurface reservoirs. We will examine how emerging AI/ML techniques—ranging from deep learning to physics-informed neural networks—can be integrated with traditional reservoir modeling practices to deliver real-time data assimilation, heightened predictive accuracy, and more robust decision-making.

Attendees will gain insights into the synthesis of diverse datasets (seismic, well logs, production data, and geological interpretations) into unified predictive models that adapt continuously as new information becomes available. Breakthroughs in generative AI for geological modeling to create realistic geological representations that honor both spatial constraints and geological principles. We'll explore how these generative approaches enable rapid model updates and scenario generation while maintaining geological consistency, facilitating efficient exploration of multiple geological interpretations and uncertainty assessment.

Special attention will be paid to uncertainty quantification, where AI-driven probabilistic approaches offer deeper understanding of reservoir risk and reliability. The session demonstrates how modern ML-powered tools enable interactive model editing and real-time updates, allowing geoscientists to efficiently incorporate new data and expert knowledge while preserving geological realism. The session also explores how AI/ML solutions contribute to sustainable energy initiatives, such as geothermal exploration and Carbon Capture and Storage (CCS), by refining subsurface characterization and monitoring capabilities.

Session 4: The “Live Earth Model”: Reality or Illusion?

Conventional modeling techniques, such as decline curve analysis and reservoir simulation, often suffer from limitations of lagging behind actual reservoir conditions as they require periodic update and rely on historic data. The "Live Earth Model" represents a significant advancement in real-time monitoring and predictive modeling of subsurface static and dynamic conditions. This model leverages advanced algorithms and machine learning techniques to integrate various data sources, including seismic imaging, well logs, and production data, and ultimately create a continuously updated spatial representation of the subsurface environment. However, several challenges persist, such as the high cost of implementation, data integration complexities, and the need for continuous data quality assurance. Additionally, the model's accuracy can be affected by inherent uncertainties in subsurface data and the limitations of current technology. Recent advancements in artificial intelligence (AI) and machine learning (ML) are addressing some of these challenges by improving data processing in terms of time efficiency and predictive accuracy. Technologies like high-resolution 3D seismic imaging and advanced geo-mechanical modeling are also contributing to boost accuracy of subsurface models. Despite these innovations, the widespread adoption of the Live Earth Model will depend on overcoming the previously discussed challenges and demonstrating consistent value in diverse operational contexts.

26th November

Session 5: Role and Value of DBM in Energy Transition and Sustainability

This session explores the application of Decision-Based Modeling beyond its traditional use in the oil and gas industry, focusing on areas like energy transition and sustainability. The goal is to adapt established methods to new technologies and approaches in fields such as:

1. Geothermal Energy: Applying modeling techniques to optimize geothermal resource utilization.

2. Carbon Capture, Utilization, and Storage (CCUS): Using models to enhance efficiency in carbon management.

3. Hydrogen Production: Integrating decision-based models for efficient hydrogen production processes.

4. Subsurface Storage for Energy Vectors: Modeling optimal storage solutions for various energy forms.

5. Renewable Energy Integration: Employing decision support systems to streamline renewable energy integration into existing grids.

By leveraging these tried-and-tested methods with new technologies, industries can navigate complex decisions more effectively during the transition towards sustainable energy systems.