From ‘Text Soup’ to a Trusted AI Foundation; Semanticising OSDU Data for a Multi-Attribute Future

Dr Thibaud Freyd; Dr Raphael Peltzer

doi:10.3997/1365-2397.fb2026014

ISSN: 0263-5046
E-ISSN: 1365-2397

From ‘Text Soup’ to a Trusted AI Foundation; Semanticising OSDU Data for a Multi-Attribute Future
Authors Dr Thibaud Freyd¹ and Dr Raphael Peltzer¹
View Affiliations Hide Affiliations

¹ Cegal
Publisher: European Association of Geoscientists & Engineers
Source: First Break, Volume 44, Issue 2, Feb 2026, p. 63 - 69
DOI: https://doi.org/10.3997/1365-2397.fb2026014
- Published online: 01 Feb 2026

Abstract

The oil and gas industry continues to digitise subsurface data, yet much of the high value information remains trapped in unstructured formats such as scanned final well reports, daily drilling reports, and biostratigraphy analyses. While the OSDU® Data Platform standardises structured datasets, unlocking value from unstructured records requires semantic enrichment and rigorous security.

This article presents a scalable, entitlement first Retrieval Augmented Generation (RAG) architecture that transforms unstructured, OSDU referenced content into actionable intelligence. The approach combines document reconstruction, header aware chunking, and hybrid retrieval - Best Matching 25 (BM25) + vector search fused via Reciprocal Rank Fusion (RFF) – with preretrieval filtering that maps Entra ID identities to OSDU Access Control Lists (ACLs). On a curated 250 question pilot set representative of subsurface workflows, semantic reconstruction and hybrid retrieval improved recall and precision by up to 20% relative to a naïve baseline, with reported reductions in time-to-answer. The article clarifies how RAG grounds generation and how ReAct agents can orchestrate multistep decision support on top of a trusted foundation.

Overall, the study outlines a practical path from unstructured ‘text soup’ to compliant, auditable answers suitable for enterprise deployment at scale.

EAGE Publications BV

Article metrics loading...

/content/journals/10.3997/1365-2397.fb2026014

2026-02-01

2026-02-16

From This Site

/content/journals/10.3997/1365-2397.fb2026014

dcterms_title,dcterms_subject,pub_keyword

-contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution

10

5

Full text loading...

References

Cormack, G.V., Clarke, C.L.A. and Buettcher, S. [2009] Reciprocal rank fusion outperforms Condorcet and individual rank learning methods. SIGIR ′09: Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, 403–410.
[Google Scholar]
IDC [2023] Worldwide Global DataSphere Structured and Unstructured Data Forecast, 2023–2027. International Data Corporation.
[Google Scholar]
Kumar, P, Tveritnev, A., Jan, S.A. and Iqbal, R. [2023] Challenges to Opportunity: Getting Value Out of Unstructured Data Management. SPE Annual Technical Conference and Exhibition, SPE-214251-MS.
[Google Scholar]
Lewis, P, Perez, E., Piktus, A., Petroni, F., Karpukhin, V, Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S. and Kiela, D. [2020] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS), 33, 9459–9474.
[Google Scholar]
MIT Sloan [2021] Tapping the Power of Unstructured Data. MIT Sloan Management Review.
[Google Scholar]
OSDU Forum [2023] OSDU Data Platform Technical Standard. The Open Group.
[Google Scholar]
Robertson, S. and Zaragoza, H. [2009] The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval, 3(4), 333–389.
[Google Scholar]
Walker, A. [2019] Oil and Gas Has a Problem With Unstructured Data. Journal of Petroleum Technology, 71(11), 32–34.
[Google Scholar]
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. and Cao, Y. [2023] ReAct: Synergising Reasoning and Acting in Language Models. International Conference on Learning Representations (ICLR).
[Google Scholar]

/content/journals/10.3997/1365-2397.fb2026014

From ‘Text Soup’ to a Trusted AI Foundation; Semanticising OSDU Data for a Multi-Attribute Future

First Break 44, 63 (2026); https://doi.org/10.3997/1365-2397.fb2026014

/content/journals/10.3997/1365-2397.fb2026014

Data & Media loading...

Article Type: Research Article

Keyword(s): Azure AI Search; BM25; Entitlements; Microsoft Copilot; Microsoft Fabric; OSDU® Data Platform; Reciprocal Rank Fusion (RRF); Retrieval Augmented Generation (RAG)

Most Cited This Month Most Cited RSS feed

- Curvature attributes and their application to 3D interpreted horizons
  
  Authors A. Roberts
- Thematic Set: Full waveform inversion: the next leap forward in imaging at Valhall
  
  Authors L. Sirgue, O.I. Barkved, J. Dellinger, J. Etgen, U. Albertin and J.H. Kommedal
- Distributed Acoustic Sensing – a new tool for seismic applications
  
  Authors Tom Parker, Sergey Shatalin and Mahmoud Farhadiroushan
- 2D resistivity surveying for environmental and engineering applications
  
  Authors T. Dahlin
- Effects of igneous intrusions on the petroleum system: a review
  
  Authors Kim Senger, John Millett, Sverre Planke, Kei Ogata, Christian Haug Eide, Marte Festøy, Olivier Galland and Dougal A. Jerram
- Geostatistical inversion - a sequential method of stochastic reservoir modelling constrained by seismic data
  
  Authors A. Haas and O. Dubrule
- Two-dimensional resistivity mapping with a computer-controlled array
  
  Authors D.H. Griffiths, J. Turnbull and A.I. Olayinka
- Virtual outcrop models of petroleum reservoir analogues: a review of the current state-of-the-art
  
  Authors J. K. Pringle, J. A. Howell, D. Hodgetts, A. R. Westerman and D. M. Hodgson
- Seismic Inversion Methods and some of their constraints
  
  Authors P.C.H. Veeken and M. Da Silva
- What is DMO?
  
  Authors S.M. Deregowski
More Less

From ‘Text Soup’ to a Trusted AI Foundation; Semanticising OSDU Data for a Multi-Attribute Future

Abstract

Most Read This Month

Most Cited This Month Most Cited RSS feed