Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network

Klemens Katterbauer; Saleh Komies; Mohd Azizi Ibrahim; Alberto Ache

Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network

Abstract

The economic success of horizontal wells in complex carbonate reservoirs is profoundly sensitive to precise wellbore placement within narrow target zones. Conventional geosteering, which relies on the real-time subjective interpretation of Logging-While-Drilling (LWD) data, is susceptible to human bias and often leads to suboptimal decisions. While data-driven machine learning offers an alternative, purely statistical models frequently produce physically implausible predictions. This paper introduces a novel Physics-Informed Neural Network (PINN) framework that seamlessly integrates domain knowledge with a deep learning architecture to automate and enhance geosteering classification. The methodology employs a multi-layer perceptron trained with a custom composite loss function, which augments standard cross-entropy loss with two physics-derived penalty terms: one enforcing petrophysical consistency between sensor readings and predicted steering actions, and another promoting wellbore trajectory smoothness. Trained and validated on a sophisticated synthetic dataset engineered to replicate the geological complexities of a Central Asia Shu formation carbonate reservoir, the model demonstrates a significant performance improvement over a purely data-driven baseline. The refined PINN model achieved a test accuracy of 91.18%, a substantial increase over the baseline Logistic Regression model's 86.68%. Crucially, the physics-informed constraints led to a dramatic enhancement in recognizing the optimal 'stay' condition, with the F1-score for this critical class rising from 0.01 to 0.51. An ablation study confirmed the petrophysical constraint as the primary driver of this improvement. Post-hoc explainability analysis using LIME (Local Interpretable Model-agnostic Explanations) verified that the model's decision-making aligns with established geological principles. This work successfully demonstrates that embedding physical constraints directly into the ML learning process yields a more robust, reliable, and interpretable autonomous geosteering system, paving the way for more objective, data-optimized well placement and reduced reliance on subjective interpretation.

Keywords

References

Akbari, A., Ranjbar, A., Kazemzadeh, Y., Martyushev, D.A., 2025. Enhanced water saturation estimation in hydrocarbon reservoirs using machine learning. Scientific Reports 15 (1), 29846. https://doi.org/10.1038/s41598-025-13982-5.
Alrashed, A.M., Sodagar, T.M., Wang, W., 2025. Integration of Diagenetic Rock Typing with Advanced Geophysical Attributes for Well Placement Optimization in Underbalanced Coiled Tubing Drilling. SPE Middle East Oil and Gas Show and Conference, D021S061R007. https://doi.org/10.2118/226971-MS.
AlSaad, M.S., Sawidan, H.H., 2025. Beyond Conventional Limits–Mastering Selective Zone Drilling with Whipstock Evaluation and Underbalanced Coiled Tubing Drilling. SPE/IADC Managed Pressure Drilling and Underbalanced Operations Conference and Exhibition, D021S010R002. https://doi.org/10.2118/SPE-228381-MS.
Alsaud, S.A., Katterbauer, K., Alshehri, A., 2024. Geosteering and Monitoring Methods for Underbalanced Coiled Tubing Operations in Gas Reservoirs. SPE EOR Conference at Oil and Gas West Asia, D031S036R003. https://doi.org/10.2118/218680-MS.
AlShehri, A., Katterbauer, K., Yousef, A., 2023. Real-Time Autoregressive Deep Learning Framework for In-Line Automatic Surface Logging. SPE Gas & Oil Technology Showcase and Conference, D011S010R002. https://doi.org/10.2118/214079-MS.
Anderson, B.I., Barber, T.D., Gianzero, S.C., 2001. The effect of crossbedding anisotropy on induction tool response. Petrophysics-The SPWLA Journal of Formation Evaluation and Reservoir Description 42 (02), Paper Number: SPWLA-2001-v42n2a6.
Averianov, A., Sues, H-D., 2012. Correlation of Late Cretaceous continental vertebrate assemblages in Middle and Central Asia. Journal of Stratigraphy 36, (2) 462-485. http://hdl.handle.net/10088/19377.
Blanc, P., Breviere, J., Laran, F., Chauvin, H., Boehm, C., Frechin, N., Capot, M., Benayoun, A., 2003. Reducing uncertainties in formation evaluation through innovative mud logging techniques. SPE Annual Technical Conference and Exhibition?, SPE-84383. https://doi.org/10.2118/84383-MS.

Bouldin, B., Verma, C., Bellaci, I., Black, M., Dyer, S., Algerøy, J., Oliveira, T., Pan, Y., 2013. Prototype Test of an All-Electric Intelligent Completion System for Extreme Reservoir Contact (ERC) Wells. SPE Annual Technical Conference and Exhibition 2013. https://dx.doi.org/10.2118/166507-MS.
Chen, J., Li, T., Zhang, Y., 2015. Application of the unstructured grids in the numerical simulation of fractured horizontal wells in ultra-low permeability gas reservoirs. Journal of Natural Gas Science and Engineering 22, 580-590. https://doi.org/10.1016/j.jngse.2015.01.003.
Henriksen, N., Storegjerde, D., 1997. Cost effective horizontal drilling in the troll field through use of state of the art technology and optimal operations. SPE/IADC Drilling Conference and Exhibition, SPE-37577. https://doi.org/10.2118/37577-MS.
Hoekstra, T., Hopkins, C., Fleck, A., Bell, G., 2000. Technical challenges encountered during coiled tubing underbalanced drilling in Oman. Abu Dhabi International Petroleum Exhibition and Conference, SPE-87240. https://doi.org/10.2118/87240-MS.
Ibrahim, M.A., Enezi, F.N., Alnasser, F.M. ,2024. Acquiring Real-Time Data in Under Balanced Coiled Tubing Drilling for Geosteering: The Current Success and Factors Limiting Physics Boundaries. International Petroleum Technology Conference, D021S078R002. https://doi.org/10.2523/IPTC-24332-MS.
Katterbauer, K., Marsala, A.F., Schoepf, V., Donzier, E., 2021. A novel artificial intelligence automatic detection framework to increase reliability of PLT gas bubble sensing. Journal of Petroleum Exploration and Production Technology 11 (3), 1263-1273. https://doi.org/10.1007/s13202-021-01098-1.
Katterbauer, K., Shehri, A.A.,2 022. Enhancing Interwell Saturation Mapping via an Innovative Quantum Machine Learning Framework. Asia Petroleum Geoscience Conference and Exhibition (APGCE), 1–5. https://doi.org/10.3997/2214-4609.202270076.
Kavanagh, T.G., Pruitt, R.D., Reynolds, M., Ortiz, R.A., Shotenski, M., Coe, R.N., Davis, P., Bergum, R., 2005. Underbalanced Coiled Tubing Drilling Practices in a Deep, Low-Pressure Gas Reservoir. International Petroleum Technology Conference, IPTC-10308. https://doi.org/10.2523/IPTC-10308-MS.
Krueger, S., Gray, K., Killip, D., 2013. Fifteen years of successful coiled tubing re-entry drilling projects in the middle east: Driving efficiency and economics in maturing gas fields. SPE/IADC Middle East Drilling Technology Conference and Exhibition, SPE-166692. https://doi.org/10.2118/166692-MS.
Lallemand, M., Funes, D., Shaikh, M., 2025. Thirty Years of Successful Coiled Tubing Re-Entry Drilling to Enhance Production in Mature Assets. SPE Gas & Oil Technology Showcase and Conference, D021S017R001. https://doi.org/10.2118/224810-MS.
Mamman, H., Goyal, S., Al-Ansari, Y., Albaqami, N., 2025. Coiled Tubing Operation and the Use of Non-Azimuthal Inversion of Ultra-Slim Multiple Propagation Resistivity. SPE Middle East Oil and Gas Show and Conference, D021S068R004. https://doi.org/10.2118/227501-MS.
Salavati, S., 2022. Applied high power laser in drilling oil and gas wells. Fiber Lasers XIX: Technology and Systems, 11981, 45–64.
Shu, L., Faure, M., Wang, B., Zhou, X., Song, B., 2008. Late Palaeozoic–Early Mesozoic geological features of South China: Response to the Indosinian collision events in Southeast Asia. Comptes Rendus. Géoscience 340 (2-3), 151-165. https://doi.org/10.1016/j.crte.2007.10.010.
Tulemissova, Z.S., Buslov, M.M., Bekmukhametova, Z.A., 2019. Geodynamic conditions of formation of sedimentary basins of South Kazakhstan (Shu-Sarysu, Pre-Balkhash, Ili). IOP Conference Series: Earth and Environmental Science 319 (1), 012021. https://doi.org/10.1088/1755-1315/319/1/012021.
Yang, H., Liu, X., Yan, X., Zhang, H., 2015. Discovery and reservoir-forming geological characteristics of the Shenmu Gas Field in the Ordos Basin. Natural Gas Industry B 2 (4), 295-306. https://doi.org/10.1016/j.ngib.2015.09.002.
Zhong, X., Chang, Y., Santoso, G., Gremillion, J., Conghui, S., Beltran, V., Murphy, J., Cabas, L., 2025. Unraveling Anticorrelation Interpretation in High Resistivity Geosteering During Coiled Tubing Drilling Operations. International Petroleum Technology Conference, D022S006R001. https://doi.org/10.2523/IPTC-24679-MS.

Details

Primary Language

English

Subjects

Marine Geology and Geophysics

Journal Section

Research Article

Authors

Klemens Katterbauer ^*
Saudi Arabia

Saleh Komies This is me
Saudi Arabia

Mohd Azizi Ibrahim This is me
Saudi Arabia

Alberto Ache This is me
Saudi Arabia

Publication Date

September 4, 2026

Submission Date

April 14, 2026

Acceptance Date

May 21, 2026

Published in Issue

Year 2026 Volume: 8 Number: 2

IZ

https://izlik.org/JA66RF38FK

Cite

RIS / Bibtex

APA

Katterbauer, K., Komies, S., Ibrahim, M. A., & Ache, A. (2026). Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network. International Journal of Earth Sciences Knowledge and Applications, 8(2), 278-290. https://izlik.org/JA66RF38FK

AMA

1.Katterbauer K, Komies S, Ibrahim MA, Ache A. Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network. IJESKA. 2026;8(2):278-290. https://izlik.org/JA66RF38FK

Chicago

Katterbauer, Klemens, Saleh Komies, Mohd Azizi Ibrahim, and Alberto Ache. 2026. “Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network”. International Journal of Earth Sciences Knowledge and Applications 8 (2): 278-90. https://izlik.org/JA66RF38FK.

EndNote

Katterbauer K, Komies S, Ibrahim MA, Ache A (September 1, 2026) Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network. International Journal of Earth Sciences Knowledge and Applications 8 2 278–290.

IEEE

[1]K. Katterbauer, S. Komies, M. A. Ibrahim, and A. Ache, “Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network”, IJESKA, vol. 8, no. 2, pp. 278–290, Sept. 2026, [Online]. Available: https://izlik.org/JA66RF38FK

ISNAD

Katterbauer, Klemens - Komies, Saleh - Ibrahim, Mohd Azizi - Ache, Alberto. “Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network”. International Journal of Earth Sciences Knowledge and Applications 8/2 (September 1, 2026): 278-290. https://izlik.org/JA66RF38FK.

JAMA

1.Katterbauer K, Komies S, Ibrahim MA, Ache A. Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network. IJESKA. 2026;8:278–290.

MLA

Katterbauer, Klemens, et al. “Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network”. International Journal of Earth Sciences Knowledge and Applications, vol. 8, no. 2, Sept. 2026, pp. 278-90, https://izlik.org/JA66RF38FK.

Vancouver

1.Klemens Katterbauer, Saleh Komies, Mohd Azizi Ibrahim, Alberto Ache. Azimuthal LWD Data Interpretation for UBCTD Geosteering Using a Physics-Informed Neural Network. IJESKA [Internet]. 2026 Sep. 1;8(2):278-90. Available from: https://izlik.org/JA66RF38FK