Multi-Attribute Analysis and Probabilistic Neural Network (PNN) Method for Predicting Carbonate Volume and Water Saturation in Biogenic Gas Reservoir: A Case Study of the Nias Basin, North Sumatra
DOI:
https://doi.org/10.70561/geocelebes.v10i2.52563Keywords:
Biogenic Gas, Carbonate Reservoir, Carbonate Volume, Probabilistic Neural Network, Water SaturationAbstract
Carbonate reservoirs frequently exhibit high heterogeneity, complicating the lateral prediction of petrophysical properties from sparse well log data. This study evaluates the hydrocarbon potential of a biogenic gas-bearing carbonate reservoir in the ‘RC’ Field, Nias Basin, by integrating well log and 2D seismic data. A multi-attribute analysis was conducted to identify seismic attributes sensitive to reservoir properties, which were subsequently used as input to a Probabilistic Neural Network (PNN) algorithm to predict the lateral distribution of Carbonate Volume (Vcr) and Water Saturation (Sw). Results identify a prospective gas-bearing carbonate zone in Well S-1 at depths of 4990 – 5693 ft, characterized by favorable reservoir quality and water saturation values predicted by the PNN model, with an average 0.4 (v/v). The PNN model significantly improved prediction accuracy, achieving correlation coefficients of 0.88 for Carbonate Volume and 0.83 for Water Saturation. These findings demonstrate that the PNN method effectively captures non-linear relationships between seismic attributes and petrophysical parameters, providing a robust framework for mapping prospective biogenic gas zones and optimizing future exploration planning in the Nias Basin.
References
Abdulaziz, A. M. (2020). The effective seismic attributes in porosity prediction for different rock types: Some implications from four case studies. Egyptian Journal of Petroleum, 29(1), 95–104. https://doi.org/10.1016/j.ejpe.2019.12.001
Ahangarani, M. L., Mojeddifar, S., & Chegeni, M. H. (2022). Reservoir characterization and porosity classification using a probabilistic neural network (PNN) based on single and multi-smoothing parameters. International Journal of Mining and Geo-Engineering, 56(4), 383–390. https://doi.org/10.22059/IJMGE.2022.287780.594822
Ardinda, F., & Riyanto, A. (2020). Seismic Multi-Attribute Analysis for Petrophysics Reservoir Prediction with Probabilistic Neural Network in “FA” Field. E3S Web of Conferences, 200, 06010. https://doi.org/10.1051/e3sconf/202020006010.
Astawa, I. N., Setiady, D., Wijaya, P. H., Hermansyah, G. M., & Saputra, M. D. (2016). Indikasi Gas Biogenik Di Perairan Delta Mahakam, Provinsi Kalimantan Timur. Jurnal Geologi Kelautan, 14(2), 103–114. https://doi.org/10.32693/jgk.14.2.2016.354
Dewanto, O., Maulina, M., & Nainggolan, T. B. (2020). Identification of biogenic gas reservoir zone using log, petrophysics and geochemical data in S-1 well of Nias basin, North Sumatera. Journal of Physics: Conference Series, 1572(1), 012037. https://doi.org/10.1088/1742-6596/1572/1/012037
Durrani, M. Z. A., Talib, M., Ali, A., Sarosh, B., & Naseem, N. (2020). Characterization and probabilistic estimation of tight carbonate reservoir properties using quantitative geophysical approach: a case study from a mature gas field in the Middle Indus Basin of Pakistan. Journal of Petroleum Exploration and Production Technology, 10(7), 2785–2804. https://doi.org/10.1007/s13202-020-00942-0
Erryansyah, M., Nainggolan, T. B., & Manik, H. M. (2020). Acoustic impedance model-based inversion to identify target reservoir: a case study Nias Waters. IOP Conference Series: Earth and Environmental Science, 429(1), 012033. https://doi.org/10.1088/1755-1315/429/1/012033
Haris, N. A., Saphira, N., Fathkhurozak, M., Rifai, Y., Zulivandama, S. R., & Aswad, S. (2020). Biogenic Gas Reservoir Distribution Analysis Using AI Inversion and Seismic Attributes in The Nias Basin, North Sumatra. Proceedings of the Indonesian Petroleum Association, 14–17 September 2020. Indonesian Petroleum Association. https://doi.org/10.29118/IPA20-SG-164
Jassam, S. A., AL-Fatlawi, O., & Canbaz, C. H. (2023). Petrophysical Analysis Based on Well Logging Data for Tight Carbonate Reservoir: The SADI Formation Case in Halfaya Oil Field. Iraqi Journal of Chemical and Petroleum Engineering, 24(3), 55–68. https://doi.org/10.31699/ijcpe.2023.3.6
Joshi, A. K., & Sain, K. (2021). Subsurface porosity estimation: A case study from the Krishna Godavari offshore basin, eastern Indian margin. Journal of Natural Gas Science and Engineering, 89, 103866. https://doi.org/10.1016/j.jngse.2021.103866
Khan, M., Bery, A. A., Bashir, Y., Sharoni, S. M. H., Gnapragasan, J., & Imran, Q. S. (2025). Optimizing petrophysical property prediction in fluvial-deltaic reservoirs: A multi-seismic attribute transformation and probabilistic neural network approach. Journal of Petroleum Exploration and Production Technology, 15, 29. https://doi.org/10.1007/s13202-024-01912-6
Lestari, I., Ekawati, G. M., & Firdaus, R. (2023). Analisis Kuantitatif Seismik Inversi Impedansi Akustik dan Porositas Pada Zona Target Lapangan “II.” Jurnal Geofisika Eksplorasi, 9(1), 61–82. https://doi.org/10.23960/jge.v9i1.238
Mohebali, B., Tahmassebi, A., Meyer-Baese, A., & Gandomi, A. H. (2020). Chapter 14 - Probabilistic neural networks: a brief overview of theory, implementation, and application. Handbook of Probabilistic Models, 347–367. Butterworth-Heinemann. https://doi.org/10.1016/B978-0-12-816514-0.00014-X
PPGL. (2018). Report Penelitian gas methana Cekungan Nias. Bandung, Indonesia. Lemigas.
Rifai, F. Y., Bernhard Nainggolan, T., & Munandar Manik, H. (2019). Reservoir Characterization Using Acoustic Impedance Inversion and Multi-Attribute Analysis in Nias Waters, North Sumatra. Bulletin of the Marine Geology, 34(1), 51–62. https://doi.org/10.32693/bomg.34.1.2019.637
Saadu, Y. K., & Nwankwo, C. N. (2018). Petrophysical evaluation and volumetric estimation within Central swamp depobelt, Niger Delta, using 3-D seismic and well logs. Egyptian Journal of Petroleum, 27(4), 531–539. https://doi.org/10.1016/j.ejpe.2017.08.004
Schön, J. H. (2015). Basic Well Logging and Formation Evaluation. Bookboon the E-Book Company,
Shakir, U., Ali, A., Hussain, M., Radwan, A. E., & Aal, A. A. El. (2024). PNN Enhanced Seismic Inversion for Porosity Modeling and Delineating the Potential Heterogeneous Gas Sands via Comparative Inversion Analysis in the Lower Indus Basin. Pure and Applied Geophysics, 181, 2801–2821 (2024). https://doi.org/10.1007/s00024-024-03562-5
Sinaga, T. M., Rosid, M. S., & Wahdanadi Haidar, M. (2019). Porosity Prediction Using Neural Network Based on Seismic Inversion and Seismic Attributes. E3S Web of Conferences, 125, 15006. https://doi.org/10.1051/e3sconf/201912515006
Tariq, Z., Gudala, M., Yan, B., Sun, S., & Mahmoud, M. (2023). A fast method to infer Nuclear Magnetic Resonance based effective porosity in carbonate rocks using machine learning techniques. Geoenergy Science and Engineering, 222, 211333. https://doi.org/10.1016/j.geoen.2022.211333
Wenando, F. A., Fatma, Y., Ulfa, A., & Suroya Taurin, J. (2023). Aplikasi dan Kerentanan Algoritma Probabilistic Neural Network (PNN): Systematic Literature Review. Jurnal CoSciTech (Computer Science and Information Technology), 4(2), 491–499. https://doi.org/10.37859/coscitech.v4i3.5676
Wibowo, R., Setiadi, I., Firdaus, Y., & Rahardiawan, R. (2024). Gravity Modeling of Subsurface Structures and Reservoir Characterization Using Seismic Inversion in the Nias Basin. Bulletin of the Marine Geology, 39(2), 69–84. https://doi.org/10.32693/bomg.39.2.2024.890
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JURNAL GEOCELEBES
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
