A Conceptual Framework for Cross-Basin Reservoir Characterization: Integrating Unsupervised-Supervised Learning to Address Geological Heterogeneity

Rian Cahya Rohmana; Tutuka Ariadji; Amega Yasutra; Dedy Irawan

doi:10.29017/scog.v49i1.2001

Authors

Rian Cahya Rohmana Department of Petroleum Engineering, Institut Teknologi Bandung; Petroleum Engineering, Tanri Abeng University
Tutuka Ariadji Department of Petroleum Engineering, Institut Teknologi Bandung
Amega Yasutra Department of Petroleum Engineering, Institut Teknologi Bandung
Dedy Irawan Department of Petroleum Engineering, Institut Teknologi Bandung

DOI:

https://doi.org/10.29017/scog.v49i1.2001

Keywords:

machine learning, reservoir characterization, cross-Basin validation, geological heterogeneity

Abstract

Machine Learning (ML) offers an innovative approach to reservoir characterization, yet its widespread application is hindered by poor cross-basin generalization. Specifically, most models validated on intra-basin data fail to account for the geological heterogeneity encountered in new settings. This study addresses this limitation by quantifying the geological domain shift that hinders direct model transferability and by proposing a conceptual framework to overcome it. This approach is designed to systematically address geological variability by identifying local electrofacies structures before attempting predictive modelling. To validate the necessity of this framework, we conducted a preliminary empirical study comparing the Talang Akar Formation in the North West Java Basin and the Menggala Formation in the Central Sumatera Basin (Basins A and B). This study empirically demonstrates that, despite shared fluvial-deltaic depositional environments, the intrinsic statistical structures of the two basins diverge significantly. A quantitative analysis revealed a severe domain shift, evidenced by a large Euclidean distance between cluster centroids and a low adjusted Rand index (ARI) of 0.113 when applying direct analog mapping. These findings empirically demonstrate that direct model transfer is ineffective because of second-order geological controls. Consequently, this study establishes the critical need for the proposed UL-SL strategy to adaptively handle domain shifts, providing a geologically grounded roadmap for accurate characterization in frontier and data-scarce basins.

References

Abdel-Fattah, M. I. (2015). Impact of depositional environment on petrophysical reservoir characteristics in Obaiyed Field, Western Desert, Egypt. Arabian Journal of Geosciences, 8(11), 9301–9314. https://doi.org/10.1007/s12517-015-1913-5

Alaskari, G. M. K. (2018). XRD evaluation of clay minerals in shaley formation and its comparison with cross plotting of log data. Progress in Petrochemical Science, 1(3), 64–67. https://doi.org/10.31031/PPS.2018.01.000513

Badan Geologi, Kementerian ESDM. (2022). Peta cekungan sedimen Indonesia 2022. https://www.esdm.go.id/assets/media/content/content-peta-cekungan-sedimen-indonesia-2022.pdf

Beard, D. C., & Weyl, P. K. (1973). Influence of texture on porosity and permeability of unconsolidated sand. AAPG bulletin, 57(2), 349-369.

Brackenridge, R. E., Demyanov, V., Vashutin, O., & Nigmatullin, R. (2022). Improving subsurface characterisation with ‘big data’ mining and machine learning. Energies, 15(3), 1070. https://doi.org/10.3390/en15031070

Candra, A. D., Rahalintar, P., Sulistiyono, S., & Prabowo, U. N. (2024). Comparison of facies estimation of well log data using machine learning. Scientific Contributions Oil and Gas, 47(1), 21–30. https://doi.org/10.29017/SCOG.47.1.1593

Cuddy, S. J. (2000). Litho-facies and permeability prediction from electrical logs using fuzzy logic. Society of Petroleum Engineers.

DeMenocal, P. B., Bristow, J. F., & Stein, R. (1992). Paleoclimatic applications of downhole logs: Pliocene-Pleistocene results from Hole 798B, Sea of Japan. In Proceedings of the Ocean Drilling Program Vol. 127, No. Pt. 1, p. 337). Ocean Drilling Program.

Díaz-Curiel, J., Miguel, M. J., Biosca, B., & Arévalo-Lomas, L. (2021). Gamma ray log to estimate clay content in the layers of water boreholes. Journal of Applied Geophysics, 195, 104481.

Dong, Y., Zhang, Y., Liu, F., & Cheng, X. (2021). Reservoir production prediction model based on a stacked LSTM network and transfer learning. ACS Omega, 6(50), 34700–34711. https://doi.org/10.1021/acsomega.1c05132

Dramsch, J. S. (2020). 70 years of machine learning in geoscience in review. Advances in Geophysics, 61, 1–55. Elsevier. https://doi.org/10.1016/bs.agph.2020.08.002

Dwihusna, N. (2020). Seismic and Well Log Based Machine Learning Facies Classification in the Panoma-Hugoton Field, Kansas and Raudhatain Field, North Kuwait. Colorado School of Mines.

Euzen, T., & Power, M. R. (2012). Well log cluster analysis and electrofacies classification: a probabilistic approach for integrating log with mineralogical data. In 2012 CSPG CSEG CWLS Convention.

Fuchs, S., & Förster, A. (2014). Well-log based prediction of thermal conductivity of sedimentary successions: a case study from the North German Basin. Geophysical Journal International, 196(1), 291-311.

Gonçalves, C. A., Harvey, P. K., & Lovell, M. A. (1997). Prediction of petrophysical parameter logs using a multilayer backpropagation neural network. Geological Society, London, Special Publications, 122(1), 169–180. https://doi.org/10.1144/GSL.SP.1997.122.01.13

Goulty, N. R., & Sargent, C. (2016). Compaction of diagenetically altered mudstones–Part 2: Implications for pore pressure estimation. Marine and Petroleum Geology, 77, 806-818.

Gu, Y., Bao, Z., Song, X., Patil, S., & Ling, K. (2019). Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization. Journal of Petroleum Science and Engineering, 179, 966–978. https://doi.org/10.1016/j.petrol.2019.05.032

He, M., Gu, H., & Wan, H. (2020). Log interpretation for lithology and fluid identification using deep neural network combined with MAHAKIL in a tight sandstone reservoir. Journal of Petroleum Science and Engineering, 194, 107498. https://doi.org/10.1016/j.petrol.2020.107498

Imamverdiyev, Y., & Sukhostat, L. (2019). Lithological facies classification using deep convolutional neural network. Journal of Petroleum Science and Engineering, 174, 216–228. https://doi.org/10.1016/j.petrol.2018.11.023

Iraji, S., Soltanmohammadi, R., Matheus, G. F., Basso, M., & Vidal, A. C. (2023). Application of unsupervised learning and deep learning for rock type prediction and petrophysical characterization using multi-scale data. Geoenergy Science and Engineering, 230, 212241. https://doi.org/10.1016/j.geoen.2023.212241

Ismail, H., Shehata, A. A., Ismail, A., & Attia, T. E. (2025). Facies analysis and depositional environments interpretation and petrophysical evaluation of the Pliocene Kafr El-Sheikh reservoirs at Sapphire Field, West Delta Deep Marine, Egypt. Alfarama Journal of Basic & Applied Sciences, 6(2), 184–198. https://doi.org/10.21608/ajbas.2025.361285.1250

Jafari, J., Mahboubi, A., Moussavi-Harami, R., & Al-Aasm, I. S. (2020). The effects of diagenesis on the petrophysical and geochemical attributes of the Asmari Formation, Marun oil field, southwest Iran. Petroleum Science, 17(2), 292–316. https://doi.org/10.1007/s12182-019-00421-0

Kansas Geological Survey. (2017). The photoelectric factor (PeF). Retrieved February 26, 2026, from https://www.kgs.ku.edu/Publications/Bulletins/LA/06_photo.html

Khan, H., Srivastav, A., & Mishra, A. K. (2019). Estimation of permeability of a reservoir using deep learning algorithms on well logs. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.3349570

Kompantsev, G. (2024). Transfer learning for variable well locations and permeability distributions in physics-aware deep learning reservoir simulation proxy models. In SPE Annual Technical Conference and Exhibition. https://doi.org/10.2118/223505-STU

Lang, W. H. (1994). Compaction/diagenesis of sediments and compaction gradients in relation to interval transit time. The log analyst, 35(04).

Lee, S. H., & Datta-Gupta, A. (1999). Electrofacies characterization and permeability predictions in carbonate reservoirs: Role of multivariate analysis and nonparametric regression. Society of Petroleum Engineers.

Leila, M., & Moscariello, A. (2018). Depositional and petrophysical controls on the volumes of hydrocarbons trapped in the Messinian reservoirs, onshore Nile Delta, Egypt. Petroleum, 4(3), 250–267. https://doi.org/10.1016/j.petlm.2018.04.003

Li, Z., Kang, Y., Feng, D., Wang, X.-M., Lv, W., Chang, J., & Zheng, W. X. (2020). Semi-supervised learning for lithology identification using Laplacian support vector machine. Journal of Petroleum Science and Engineering, 195, 107510. https://doi.org/10.1016/j.petrol.2020.107510

Li, Z., Wang, Z., Wei, Z., Zhou, X., Wang, Y., Huai, B., Liu, Q., Yuan, N. J., Gong, R., & Chen, E. (2021). Cross-oilfield reservoir classification via multi-scale sensor knowledge transfer. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4215–4223. https://doi.org/10.1609/aaai.v35i5.16545

Lima, M. C. O., Pontedeiro, E. M., Ramirez, M. G., Favoreto, J., Dos Santos, H. N., Van Genuchten, M. Th., Borghi, L., Couto, P., & Raoof, A. (2022). Impacts of mineralogy on petrophysical properties. Transport in Porous Media, 145(1), 103–125. https://doi.org/10.1007/s11242-022-01829-w

Lorenz, J. C., Sattler, A. A., & Stein, C. L. (1989). The effects of depositional environment on petrophysical properties of Mesaverde reservoirs, Northwestern Colorado. Society of Petroleum Engineers.

Magoba, M., Opuwari, M., & Liu, K. (2024). The effect of diagenetic minerals on the petrophysical properties of sandstone reservoir: A case study of the Upper Shallow Marine sandstones in the Central Bredasdorp Basin, offshore South Africa. Minerals, 14(4), 396. https://doi.org/10.3390/min14040396

Merletti, G. D., Spain, D. R., Melick, J., Armitage, P., Hamman, J., Shabro, V., & Gramin, P. (2017). Integration of depositional, petrophysical, and petrographic facies for predicting permeability in tight gas reservoirs. Interpretation, 5(2), SE29–SE41. https://doi.org/10.1190/INT-2016-0112.1

Misra, S., Elkady, M., Kumar, V., Odi, U., & Silver, A. (2024). Use of transfer learning in shale production forecasting. In International Petroleum Technology Conference. https://doi.org/10.2523/IPTC-23438-MS

Mohaghegh, S., Arefi, R., Bilgesu, I., Ameri, S., & Rose, D. (1995). Design and development of an artificial neural network for estimation of formation permeability. SPE Computer Applications, 7(06), 151–154. https://doi.org/10.2118/28237-PA

Mohaghegh, S., Bogdan, B., & Ameri, S. (1997). Permeability determination from well log data. SPE Formation Evaluation, 12(3), 170–174.

Nugroho, I. D. R., Trisna, M. D., & Saroji, S. (2024). An implementation of XGBoost and Random Forest algorithm to estimate effective porosity and permeability on well log data at Fajar Field, South Sumatera Basin, Indonesia. Indonesian Journal of Applied Physics, 14(2), 271. https://doi.org/10.13057/ijap.v14i2.82901

Omoboriowo, A. O., Chiadikobi, K. C., & Chiaghanam, O. I. (2012). Depositional environment and petrophysical characteristics of “LEPA” reservoir, Amma Field, Eastern Niger Delta, Nigeria. International Journal of Pure and Applied Sciences and Technology, 10(2), 38–61.

Pan, W. (2022). Reservoir Description via Statistical and Machine-Learning Approaches. The University of Texas at Austin.

Pratama, H. (2018). Machine learning: Using optimized KNN (k-nearest neighbors) to predict the facies classifications. In Proceedings of the 13th SEGJ International Symposium (pp. 538–541). https://doi.org/10.1190/SEGJ2018-139.1

Rashid, F., Hussein, D., Glover, P. W. J., Lorinczi, P., & Lawrence, J. A. (2022). Quantitative diagenesis: Methods for studying the evolution of the physical properties of tight carbonate reservoir rocks. Marine and Petroleum Geology, 139, 105603. https://doi.org/10.1016/j.marpetgeo.2022.105603

Sarhan, M. A. (2022). Geophysical appraisal of the Abu Madi gas reservoir, Nile Delta Basin, Egypt: Implications for the tectonic effect on the lateral distribution of petrophysical parameters. Petroleum Research, 7(4), 511–520. https://doi.org/10.1016/j.ptlrs.2022.03.002

Scherer, M. (1987). Parameters influencing porosity in sandstones: a model for sandstone porosity prediction. AAPG bulletin, 71(5), 485-491.

Serra, O. (1984). Fundamentals of well-log interpretation: The acquisition of logging data. Elsevier.

Singh, H., Seol, Y., & Myshakin, E. M. (2020). Automated well-log processing and lithology classification by identifying optimal features through unsupervised and supervised machine-learning algorithms. SPE Journal, 25(05), 2778–2800. https://doi.org/10.2118/202477-PA

Smeraglia, L., Trippetta, F., Carminati, E., & Mollo, S. (2014). Tectonic control on the petrophysical properties of foredeep sandstone in the Central Apennines, Italy. Journal of Geophysical Research: Solid Earth, 119(12), 9077–9094. https://doi.org/10.1002/2014JB011221

Talebkeikhah, M., Sadeghtabaghi, Z., & Shabani, M. (2021). A comparison of machine learning approaches for prediction of permeability using well log data in the hydrocarbon reservoirs. Journal of Human, Earth, and Future, 2(2), 82–99. https://doi.org/10.28991/HEF-2021-02-02-01

Ulil, M. R., Winardhi, S., & Dinanto, E. (2025). Machine learning-based prediction of shear wave velocity: Performance evaluation of Bi-GRU, ANN, and the Greenberg-Castagna empirical method. Scientific Contributions Oil and Gas, 48(3), 125–134. https://doi.org/10.29017/scog.v48i3.1797

Verma, S., Bhattacharya, S., Chowdhury, N. U. M. K., & Tian, M. (2021). A new workflow for multi-well lithofacies interpretation integrating joint petrophysical inversion, unsupervised, and supervised machine learning. In First International Meeting for Applied Geoscience & Energy (pp. 2213–2217). https://doi.org/10.1190/segam2021-3584118.1

Wibowo, R. C., Pertiwi, A. P., & Kurniati, S. (2020). Identification of Clay Mineral Content Using Spectral Gamma Ray on Y1 Well in Karawang Area, West Java, Indonesia. Journal of geoscience, engineering, environment, and technology, 5(3), 136-142.

Wong, P. M., Gedeon, T. D., & Taggart, I. J. (1995). An improved technique in porosity prediction: A neural network approach. IEEE Transactions on Geoscience and Remote Sensing, 33(4), 971–980. https://doi.org/10.1109/36.406683

Wood, D. A. (2020). Predicting porosity, permeability and water saturation applying an optimized nearest-neighbour, machine-learning and data-mining network of well-log data. Journal of Petroleum Science and Engineering, 184, 106587. https://doi.org/10.1016/j.petrol.2019.106587

Yang, L., Wang, S., Chen, X., Chen, W., Saad, O. M., Zhou, X., Pham, N., Geng, Z., Fomel, S., & Chen, Y. (2023). High-fidelity permeability and porosity prediction using deep learning with the self-attention mechanism. IEEE Transactions on Neural Networks and Learning Systems, 34(7), 3429–3443. https://doi.org/10.1109/TNNLS.2022.3157765

Yao, J., Liu, Q., Liu, W., Liu, Y., Chen, X., & Pan, M. (2020). 3D reservoir geological modeling algorithm based on a deep feedforward neural network: A case study of the Delta Reservoir of Upper Urho Formation in the X Area of Karamay, Xinjiang, China. Energies, 13(24). https://doi.org/10.3390/en13246699

Zainuri, A. P. P., Sinurat, P. D., Irawan, D., & Sasongko, H. (2023). Trap prevention in machine learning in prediction of petrophysical parameters: A case study in The Field X. Scientific Contributions Oil and Gas, 46(3), 115–127. https://doi.org/10.29017/SCOG.46.3.1586

Zhang, Y., Hu, J., & Zhang, Q. (2021). Application of locality preserving projection-based unsupervised learning in predicting the oil production for low-permeability reservoirs. SPE Journal, 26(03), 1302–1313. https://doi.org/10.2118/201231-PA

Zhu, L. Q., Sun, J., Zhou, X. Q., Li, Q. P., Fan, Q., Wu, S. L., & Wu, S. G. (2023). Well logging evaluation of fine-grained hydrate-bearing sediment reservoirs: Considering the effect of clay content. Petroleum Science, 20(2), 879-892.