Data Core

As industries scale AI and data-driven operations, the real challenge is no longer data integration, but the ability to share meaning consistently across systems and over time. Yet most so-called “ontologies” remain limited to taxonomies, schemas, or loosely structured graphs, failing to capture and govern meaning, and ultimately reproducing silos. This talk argues that true interoperability is not about connecting systems, but about aligning meaning under explicit and controlled conditions. Without formal semantics, interoperability degrades into mappings and transformations that are fragile, non-scalable, and semantically ambiguous.

Building on industrial deployments in complex engineering and operations contexts, we present a formal ontology stack combining Top-Level Ontologies (e.g., BFO: ISO 21838-2, 2021), industrial core ontologies (IOF), and domain business objects aligned with standards such as CFIHOS. The key differentiator lies in axiomatized semantics grounded in firstorder logic, enabling machine-verifiable constraints, consistency checking, and cross-domain reasoning.

However, technology alone is insufficient. Interoperability requires governance of meaning: formal rules to define, validate, version, and reuse semantic models; business objects treated as controlled semantic assets; and standards integrated at the semantic level: not just referenced. In a world where AI models are increasingly commoditized, competitive advantage shifts to the ability to formalize and govern knowledge. Organizations that control their semantic layer establish a shared human–machine language, enabling reusable knowledge, scalable interoperability, and explainable AI. This approach transforms knowledge into a persistent, governed, and platform-independent asset, ensuring long-term consistency, reducing technical debt, and enabling open, standard-based interoperability.

In geotechnical engineering, the challenge is often not a lack of data, but the ability to find, access, and integrate it across workflows. This is particularly evident in offshore projects, where ground models depend on combining seismic data (2D and 3D) with large volumes of in-situ geotechnical measurements and laboratory results.

Field Manager is a cloud-based platform that supports the full lifecycle of geotechnical survey data, from collection and quality assurance to visualization. In this talk, we present recently developed data structures and workflows for linking geotechnical data (0D/1D) with spatial references to seismic data (2D and 3D), enabling these datasets to be explored and interpreted in context. The focus is on the design and implementation of the underlying data model, and on how to balance flexibility and structure when building systems for complex, multi-source data.

To ensure alignment with Aker BP strategy to be the leading exploration and production company of the future and given the size and complexity of the Yggdrasil project, it quickly became clear that traditional approaches wouldn’t be sufficient. To address these challenges, we’ve adopted new, more digital ways of working, which have helped us streamline processes and improve overall efficiency.

A key aspect of our new approach involves making extended use of data. By leveraging dashboards, we can access, control, and quality check information in real-time, ensuring that our data remains both accurate and actionable. Additionally, we’ve incorporated AI tools to further enhance our capabilities, enabling us to handle large volumes of information and make smarter, faster decisions.

These digital advancements have positively impacted our workflow, allowing us to keep pace with the demands of the project and maintain high standards of information management.

As organizations invest in OSDU to modernize subsurface data management, a key question remains: how well does the platform perform with real, complex data—and what does that mean for business value?

This presentation shares practical insights from testing the OSDU data platform using actual well log datasets, including high-volume array data. The work focuses on understanding how platform capabilities translate into operational efficiency, scalability, and usability in real-world scenarios.

We explore the end-to-end lifecycle—from ingestion to consumption—highlighting the impact of data complexity on throughput, data accessibility, and downstream workflows such as interpretation and analytics. The session will demonstrate where OSDU enables faster access to subsurface insights, and where challenges—such as ingesting large datasets, managing complex schemas, and retrieving array-based data—can introduce friction and cost.

By connecting technical findings to business outcomes, this talk provides actionable guidance on how to optimize data onboarding strategies, improve user experience, and reduce time-to-value when working with subsurface data in OSDU.

As organizations transition toward Data & AI–driven workflows, seamless data access across applications is becoming a strategic priority. OSDU is widely recognized as a platform capable of addressing these integration needs. However, from an operational perspective, challenges remain. Despite growing adoption of OSDU as a common data platform, true integration between subsurface applications and cloud ecosystems continues to be a barrier.

This presentation explores how SLB connects subsurface applications such as Petrel and Techlog with OSDU, enabling efficient, governed data exchange while preserving the user experience within domain tools. The session spans multiple subsurface domains. In seismic, capabilities such as streaming allow interpreters to access large datasets directly from OSDU without duplication, improving performance and collaboration. In wellbore, connectors enable bi-directional exchange of logs and interpretations, ensuring consistency with OSDU schemas. The presentation also extends to interpretation workflows, including seismic interpretation outputs and reservoir models, supporting coherent data flows across disciplines, as well as RAFS data integration to broaden access to subsurface datasets.

A key focus is the tangible value for users. By connecting applications directly to OSDU, users benefit from reduced data handling, improved quality, and faster access to trusted data—while continuing to work in familiar environments. These connectors enable hybrid workflows where applications remain the primary interface and OSDU acts as the system of record.

Through practical examples, the session will highlight how integration reduces data silos, improves collaboration, and accelerates decision-making. Ultimately, these connectors provide a foundation for scalable, data-centric subsurface workflows, delivering measurable value to interpreters, petrophysicists, and reservoir engineers.

This project presents an AI-driven pipeline for subsurface data management, integrating automated classification and metadata extraction to transform large volumes of unstructured technical documents into a structured, searchable digital repository. The classification methodology employs file hashing to detect duplicates and identify master files, followed by AI-driven categorization that distinguishes between Petroleum Engineering and Geoscience assets based on a predefined data hierarchy. Processing an initial 30,545 technical documents, the system identified 17,950 unique master files, removed 12,595 redundant copies, and categorized assets into structured domain and its respective group folders, enabling rapid data standardization within minutes.

Building on this foundation, Large Language Models (LLMs) were applied to automate metadata extraction across thousands multi-format files, including well reports, geological records, and digital logs such as LAS and DLIS formats. Combining Optical Character Recognition (OCR) and Natural Language Processing (NLP), the system converts unstructured technical reports into machine-readable text, with ML models mapping key entities to four OSDU￾compliant templates tailored for distinct engineering workflows. A human-in-the-loop Quality Control (QC) engine allows Data Analysts and Subject Matter Experts to verify and refine AI outputs, resolving misclassifications and metadata inconsistencies. The most impactful outcome is an 80% reduction in processing time, compressing months of manual effort into weeks, redirecting engineers toward high-value analysis and establishing a scalable, high-fidelity foundation for OSDU operations.

The continuous accumulation of seismic data resulting from decades of new acquisitions and reprocessing cycles presents significant challenges for seismic data management. As data volumes grow, issues such as duplicate file instances and seismic datasets effectively lost within large‑scale file systems become increasingly common. This presentation demonstrates that, through the use of specialised softwares, these challenges can not only be addressed but also enable the creation of a new interface that changes how geoscientists interact with seismic data.

Effective subsurface data management plays a critical role in optimizing resources and supporting informed decisionmaking in geoscience operations. This study demonstrates a collaborative effort between Cegal and an upstream SEA NOC's innovation team to enhance data integrity and operational efficiency within the subsurface projects environment through the deployment of Blueback Project Tracker.

The initiative begins with a comprehensive evaluation of the existing data landscape, systematically identifying corrupt datasets, obsolete files, and coordinate reference system (CRS) inconsistencies across an extensive portfolio. During the initial phase, more than 5,000 subsurface projects spanning multiple software versions from 2007 to 2024 were assessed. This thorough inventory established the foundation for targeted data optimization activities.

A key focus involves addressing data duplication across well, interpretation, and seismic datasets. By implementing globally unique identifiers (GUIDs) and MD5 hashcode methodologies, redundant data entries were efficiently detected and eliminated. This systematic approach enhanced data integrity while achieving potential storage reduction of approximately 18 TB, significantly improving operational efficiency.

To sustain ongoing improvements, robust monitoring mechanisms were established to track project performance and data quality over time. A critical outcome of this continuous improvement process is maintaining a clean data environment, which enables the establishment of stronger governance protocols.

The results emphasize the value of modern data management methodologies in rationalizing subsurface data, maximizing operational efficiency, and reducing costs. This initiative demonstrates how structured approaches to data governance, combined with appropriate technological solutions, can transform geoscience data environments and support sustainable knowledge management practices.

Seismic data is one of the most important technical assets in upstream oil and gas, but in many organizations it is still managed mainly as large SEG-Y files stored in archives, project folders, or application-specific repositories. This makes the data difficult to discover, slow to access, hard to govern, and not ready for analytics or AI workflows.

This presentation proposes a greenfield architecture for a modern seismic data platform that transforms seismic from a file-centric archive into governed, AI-ready data products. The design preserves SEG-Y as the original archive format, while introducing MDIO/Zarr as a modern multidimensional working representation for seismic volumes. By storing the data on S3-compatible on-premise object storage, the platform enables scalable access while supporting organizations that need to keep sensitive subsurface data within their own environment.

The architecture covers the full seismic lifecycle, from SEG-Y ingestion and validation through MDIO/Zarr conversion, catalog publication, and API-based access. It is organized around Bronze, Silver, and Gold data zones, with metadata, lineage, quality, and entitlement treated as platform layers rather than afterthoughts. AI-ready products such as seismic slices, attributes, and 3D patches are exposed as governed datasets that can support machine learning for fault detection, facies analysis, and subsurface data discovery.

The presentation is based on an ongoing architecture and prototype effort using openly available seismic data such as Volve and F3. The expected contribution is a practical reference design for E&P data professionals who want to make seismic data more accessible, more governed, and ready for analytics and AI, built on infrastructure that organizations can realistically own, without depending solely on public cloud platforms.