Unsupervised Machine Learning for Reservoir Rock Type Classification in the Ngimbang Formation, Northeast Java Basin, Indonesia

Elizia Da Costa Alves; A.K.M. Eahsanul Haque; M. Azuwan B. Maoinser

doi:10.29017/scog.v49i3.2147

Authors

Elizia Da Costa Alves Universiti Teknologi PETRONAS
A.K.M. Eahsanul Haque Universiti Teknologi PETRONAS
M. Azuwan B. Maoinser Universiti Teknologi PETRONAS

DOI:

https://doi.org/10.29017/scog.v49i3.2147

Keywords:

unsupervised machine learning, reservoir characterization, rock type determination, net productive layer

Abstract

Reservoir characterisation is a fundamental step in hydrocarbon exploration and production, requiring accurate identification of rock types and productive zones. Conventional petrophysical analysis alone is often insufficient to capture the full complexity of heterogeneous carbonate formations. This study applies unsupervised machine learning, specifically K-means clustering, to classify reservoir rock types within the Lower Ngimbang Formation of the AXEL Field, Northeast Java Basin, Indonesia. Wireline log data from two wells AXEL-1 and AXEL-2 comprising Gamma Ray (GR), Deep Resistivity (ResD), Neutron Porosity (NPHI), Bulk Density (RHOB), and Sonic (DT) logs were used as input. Quantitative petrophysical analysis was first conducted to estimate shale volume (Vsh), effective porosity (PHIE), and water saturation (Sw) using Indonesian Equation. K-means clustering was subsequently applied, starting from 20 initial micro-clusters that were progressively consolidated into five geologically meaningful rock types: Hydrocarbon, Water-Bearing, Tight Formations, Coal, and Shale. The selection of five final groups was guided by a two-step validation approach using the Cluster Groups Randomness variance ratio generated within Interactive Petrophysics, which confirmed K=5 as the most geologically defensible configuration. In AXEL-1 Zone 1 yielded a net pay of 46.82 m (avg PHIE = 0.089, avg Sw = 0.352), confirmed by DST gas flow rates of up to 7.599 MMCFGPD, while AXEL-2 Zone 1 returned a net pay of 12.50 m (avg PHIE = 0.095, avg Sw = 0.057) reflecting lower hydrocarbon potential. The Hydrocarbon Potential facies (Group 3) identified by K-means showed strong spatial agreement with conventionally defined productive zones. These results demonstrate that unsupervised machine learning provides a practical and reproducible complementary framework for reservoir characterisation and rock type classification in complex carbonate reservoirs.

References

Ascaria, N. A. ; P. L. ; P. B. ; L. L. C. ; D. H. (2024). Paleogene Carbonate First Trap Play in the Northeast Java Basin Using a Sub-Basin Approach. Proceedings, Indonesian Petroleum Association, Forty-Eighth Annual Convention & Exhibition. https://proceedings.ipa.or.id

Ashraf, U., Anees, A., Zhang, H., Ali, M., Thanh, H. V., & Yuan, Y. (2024). Identifying payable cluster distributions for improved reservoir characterization: a robust unsupervised ML strategy for rock typing of depositional facies in heterogeneous rocks. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 10(1), 131. https://doi.org/10.1007/s40948-024-00848-9

Criollo, D., Fam, M., Hernández, Y. F., López, A. M., & Zafra, C. (2022). Practical Methodology for Characterizing Unconventional Plays using Conventional Logs, Cores and Cuttings Analysis: A Case Study. Fourth EAGE Workshop on Unconventional Resources, 1–5. https://doi.org/10.3997/2214-4609.202289002

Darmawan, H. I. ; W. A. K. (2022). Characteristics of Eocene Carbonate Reservoir - A Case Study of Ngimbang Carbonate in North Madura Platform, East Java Basin. Proceedings, Indonesian Petroleum Association, Forty-Sixth Annual Convention & Exhibition, IPA22-G-62.

Ficry, D. ; R. D. (2025). Identifikasi Net Pay dan Zona Prospektif Hidrokarbon Berdasarkan Analisis Petrofisika Log. SNTEM.

Glover, P. W. J., Mohammed-Sajed, O. K., Akyüz, C., Lorinczi, P., & Collier, R. (2022). Clustering of facies in tight carbonates using machine learning. Marine and Petroleum Geology, 144, 105828. https://doi.org/10.1016/j.marpetgeo.2022.105828

Handoyo, Ronlei, B. C., Wibowo, A. S., Sigalingging, A. S., Nathania, E. Y., Fatkhan, F., Erdi, A., Avseth, P., Carbonell, R., Nugroho, P., Bayu Pandito, R. H., Nasibov, A., & Ali Husein, A. A. (2025). Reservoir Characterization of Ngrayong Formation, Sandstone with Carbonate Intercalation, Using a Geostatistical Approach Based on Petrophysical Parameters, Northeast Java Basin, Indonesia. Scientific Contributions Oil and Gas, 48(3), 237–251. https://doi.org/10.29017/scog.v48i3.1828

Horsfall, O. I. ; O.-P. V. B. ; T. I. (2023). Correlation analysis between sonic and density logs for porosity determination in the south-eastern part of the Niger Delta Basin of Nigeria. Asian Journal of Science and Technology, 4(1).

Mohammadi Behboud, M., Ramezanzadeh, A., Tokhmechi, B., Mehrad, M., & Davoodi, S. (2023). Estimation of geomechanical rock characteristics from specific energy data using combination of wavelet transform with ANFIS-PSO algorithm. Journal of Petroleum Exploration and Production Technology, 13(8), 1715–1740. https://doi.org/10.1007/s13202-023-01644-z

Munir, M. N., Zafar, M., Ali, A., Ehsan, M., Abdelrahman, K., Radwan, A. E., & Al-Awah, H. (2024). A Comparative Study Based on Petrophysical and Cluster Analysis Approach for Identification of Rock Types in Heterogeneous Sandstone Reservoirs. ACS Omega, 9(31), 33397–33407. https://doi.org/10.1021/acsomega.3c08403

Ningsih, I. A. ; I. D. (2021). Analisis dan Interpretasi Data Well Logging Berdasarkan Parameter Petrofisika pada Sumur South Onin AI-X dan Sumur North Onin-1x di Lapangan X Papua. Jurnal Geosaintek, 7(2), 241–248.

Nurbilad, R. R. ; S. K. (2021). Analisis Petrofisika untuk Evaluasi Formasi Reservoar Karbonat dan Formasi Batupasir pada Lapangan “Geo”-Cekungan Sumatera Selatan. Jurnal Fisika, 4(1).

Pringgoprawiro, H. (1983). Biostratigraphy and Paleogeography of North East Java Basin: A New Approach. Institute of Technology Bandung.

Ramdhan, A. M. (2021). Tekanan Luap di Bagian Darat dan Cekungan Jawa Timur Utara dan Implikasinya terhadap Kondisi Tegasan pada Masa Kini. Lembaran Publikasi Minyak Dan Gas Bumi, 55(2), 115–127.

Rohmana, R. C., Ariadji, T., Yasutra, A., & Irawan, D. (2026). A Conceptual Framework for Cross-Basin Reservoir Characterization: Integrating Unsupervised-Supervised Learning to Address Geological Heterogeneity. Scientific Contributions Oil and Gas, 49(1), 375–394. https://doi.org/10.29017/scog.v49i1.2001

Sadeghi, M., Casey, P., Carranza, E. J. M., & Lynch, E. P. (2024). Principal components analysis and K-means clustering of till geochemical data: Mapping and targeting of prospective areas for lithium exploration in Västernorrland Region, Sweden. Ore Geology Reviews, 167, 106002. https://doi.org/10.1016/j.oregeorev.2024.106002

Shili, H. (2023). Clustering in big data analytics: a systematic review and comparative analysis (review article). Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 23(5), 967–979. https://doi.org/10.17586/2226-1494-2023-23-5-967-979

Sinaga, J. P., & Haris, A. (2018). Facies modeling of Ngimbang formation case study of North East Java Basin, Indonesia. 020246. https://doi.org/10.1063/1.5064243

Ulil, M. R., Sonny Winardhi, & 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), 159–171. https://doi.org/10.29017/scog.v48i3.1797

Wihdany, F. I., Irawan, D., Utomo, M. R., & Fitro, A. M. (2019). INTEGRATED INITIAL WATER SATURATION MODELLING. Scientific Contributions Oil and Gas, 42(3), 95–107. https://doi.org/10.29017/SCOG.42.3.396

Wijaya, A. K. ; R. M. H. B. ; M. M. ; D. H. I. ; I. R. B. (2022). Revealing New Hydrocarbon Potential in Mature Basin, A Case Study from North Madura Platform, East Java Basin, Indonesia. Proceedings, Indonesian Petroleum Association, Forty-Sixth Annual Convention & Exhibition, IPA22-G-236.

Winardi, S., Surjono, S. S., Amijaya, D. H., & Suryanto, W. (2024). Profil Perubahan Nilai Resistivitas Reservoar Pada Batu Pasir Karena Pengaruh Mineral Glaukonit. Lembaran Publikasi Minyak Dan Gas Bumi, 58(2), 65–79. https://doi.org/10.29017/LPMGB.58.2.1628

Wiryadinata, V. ; H. A. (2025). Integration of Log Analysis and Dutta Crossplot to Identify Overpressure Zones and Hydrocarbon Potential in the Kujung and Ngimbang Formations. Jurnal Penelitian Pendidikan IPA, 11(11).

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. https://doi.org/10.1016/j.petsci.2022.09.018