Intelligent processing of geophysical logging data for assessing fractures in carbonate reservoirs
Abstract
Relevance. Fracture characterization of carbonate reservoirs remains one of the most challenging problems in petroleum geophysics because fracture systems significantly affect reservoir storage and flow properties. Conventional well-log interpretation techniques often provide insufficient reliability in identifying fractured intervals under complex geological conditions. Aim. To develop and evaluate intelligent data-processing approaches for predicting fracture distribution in carbonate reservoirs using well logging information. Methods. Acoustic, neutron, density, and electrical logging data, FMI images, and core analysis results were used. Machine learning methods including Random Forest, XGBoost, Support Vector Machine, and convolutional neural networks were applied. Data preprocessing, feature engineering, and model training were performed using labeled datasets. Results. Ensemble algorithms and integrated interpretation of well logging and FMI data demonstrated the highest prediction performance. The XGBoost model achieved a maximum classification accuracy of 92 %. Stable relationships between local variations of logging parameters and fracture development were identified. The obtained results confirm the effectiveness of intelligent data-processing methods for improving fracture detection reliability and enhancing geological characterization of carbonate reservoirs.
References
Aljurf S., Abu-Mahfouz I.S., Chan S. Methodological workflow for assessing heterogeneity in immature organic-rich carbonate reservoirs // MethodsX. – 2026. – Vol. 16. – Art. No. 103875. DOI: 10.1016/j.mex.2026.103875.
Almeida G.M.S., Barbosa C.H.S., Santo M.C.O.L., Landau L. A Comparison of supervised machine learning algorithms to predict porosity in carbonate reservoirs from well logs: a case study of quissama formation carbonate in the Campos Basin, Brazil // Journal of Petroleum Geology. – 2026. – Vol. 49. No. 2. – pp. 448–465. DOI: 10.1111/jpg.70036.
Castellanos Bassoult L.A., Perez Hernandez L.A., Alcantara R., Velasquez A. Data-Driven Sw prediction and porosity typing from synthetic Vp/Vs: a feasibility approach for enhancing hydrocarbon recovery in NFRs // IPTC Summit on AI for the Energy Industry (IPTC 2026). Dubai, UAE, 2026. DOI: 10.2523/IPTC-25211-MS.
Chinelatto G.F., Souza J.P.D.P., Basso M., Vidal A.C. The use of convolutional neural networks to predict carbonate dissolution features in acoustic borehole images: an example from brazilian pre-salt reservoirs // Earth Science Informatics. – 2026. – Vol. 19. No. 4. – Art. No. 45. DOI: 10.1007/s12145-026-02097-8.
Deng P., Tang J., Chen Y., Yu D. Precise Characterization of fluid logging responses in complex shale reservoirs: a case study from the Hongxing Area, Eastern Sichuan Basin // Geofluids. – 2026. – Vol. 2026. No. 1. – Art. No. 1419048. DOI: 10.1155/gfl/1419048.
Diffaa A., Al-Khalidy A.A., Aji A. Hybrid Traditional interpretation and machine learningbased log reconstruction for enhanced petrophysical evaluation of Hartha formation, of XS oil field, Central Iraq // Iraqi Geological Journal. – 2026. – Vol. 59. No. 1. – pp. 186–203. DOI: 10.46717/igj.2026.59.1C.14.
Elbalawy M.A., Takacs E., Velledits F. From subsurface data to heat economics: A novel machine-learning seismic workflow for geothermal reservoir delineation, subsurface derisking, and 3D modelling of deep triassic carbonates // Results in Engineering. – 2026a. – Vol. 30. – Art. No. 110343. DOI: 10.1016/j.rineng.2026.110343.
Elbalawy M.A., Eid M.H., Badawi M., Takacs E., Velledits F. From lithology prediction to geothermal energy production: Leveraging data-driven and financial insights to unlock geothermal potential of a carbonate reservoir, SE Hungary // Renewable Energy. – 2026b. – Vol. 259. – Art. No. 125031. DOI: 10.1016/j.renene.2025.125031.
Gao Y., Wu Q., Zhao W., Zhao L., Li J. Quantitative classification of microscopic pore structure in carbonate reservoirs using multi-source data fusion and machine learning integration // Processes. – 2026. – Vol. 14. No. 9. – Art. No. 1432. DOI: 10.3390/pr14091432.
Goncalves J.F.V., de Figueiredo J.J.S., Da Silveira J.R.B.S. et al. Vector-based and machine learning approaches for pore network parameters analysis // Geophysical Prospecting. – 2026. – Vol. 74. No. 1. – Art. No. e70117. DOI: 10.1111/1365-2478.70117.
Hussein H.A.A., Hadi F.A., Jweeg M.J., Issa M.A., Mohammed M.M., Jasim D.J. An intensive study to determine the in situ minimum horizontal stress using well logging data // Indian Geotechnical Journal. – 2026. – Vol. 56. No. 3. – pp. 1292–1306. DOI: 10.1007/s40098025-01221-7.
Li J., Liu H., Yan L. et al. Numerical Well Testing of Ultra-Deep Fault-controlled carbonate reservoirs: a geological model-based approach with machine learning assisted inversion // Processes. – 2026. – Vol. 14. No. 2. – Art. No. 187. DOI: 10.3390/pr14020187.
Maciel R.S., Carneiro J.N.E., Souza A.F.F., Monteiro D., Gunnerud V. A method for inorganic scaling simulation: multiphase flow and multi-ionic brine with a mass transfer approach // Journal of the Brazilian Society of Mechanical Sciences and Engineering. – 2026. – Vol. 48. No. 5. – Art. No. 355. DOI: 10.1007/s40430-025-06290-6.
Motaei E., Yunos K.A.B., Othman T.R.T., Ghadami N. AI-Guided ensemble modeling for optimized well test analysis to unlock exploration targets and narrow down uncertainty in volumetric assessment // Journal of Petroleum Geology. – 2026. DOI: 10.1111/jpg.70055.
Nabipour I., Raoof A., Qajar J. Resolution-aware multiscale 3D CNNs for permeability estimation in carbonate rocks: an architecture-agnostic transfer-learning framework // Advances in Water Resources. – 2026. – Vol. 213. – Art. No. 105311. DOI: 10.1016/j.advwatres.2026.105311.
Rahimi M., Riahi M.A. Integration of the RNN and geostatistics methods for permeability prediction: a case study from the surmeh formation, Persian Gulf // Discover Applied Sciences. – 2026. – Vol. 8. No. 4. – Art. No. 394. DOI: 10.1007/s42452-026-08350-5.
Santana H.M., Leite E.P. 3D facies modeling of a carbonate reservoir in the Santos Basin using machine learning // Journal of Applied Geophysics. – 2026. – Vol. 245. – Art. No. 106049. DOI: 10.1016/j.jappgeo.2025.106049.
Tahvildari S.P., Shojaei S., Masihi M. A physics-informed hybrid ML framework for pore pressure and fracture gradient prediction in carbonate reservoirs // Scientific Reports. – 2026. – Vol. 16. No. 1. – Art. No. 8925. DOI: 10.1038/s41598-026-41773-z.
Temizel C., Tutun S., Canbaz C.H. et al. AI applications in reservoir characterization, geology, and geophysics. in: artificial intelligence in the energy industry: theory, case studies, and applications. CRC Press, 2026. – pp. 81–159. DOI: 10.1201/9781003617327-2.
Wang L., Wang H., Wei S. et al. A Novel Quick-Win dual-branch neural operator proxy for real-time waterflood simulation in heterogeneous porous carbonate reservoirs // IPTC Summit on AI for the Energy Industry (IPTC 2026). 2026. DOI: 10.2523/IPTC-25133-MS.
Zhang T., Yan K., Feng Z., Liu Y., Xie K., Wang F., Meng L. A 3D Permeability prediction model for multicomponent carbonate rocks: multisoft-threshold transformer-UNet // SPE Journal. – 2026. – Vol. 31. No. 4. – pp. 2489–2499. DOI: 10.2118/231860-PA.
English
Русский
