Artificial Intelligence-Based Reservoir Quality Clustering to Determine New Drilling Well Locations

Jeffier Winarta; Amega Yasutra; Fajril Ambia

doi:10.29017/scog.v49i2.2075

Authors

Jeffier Winarta Institut Teknologi Bandung
Amega Yasutra Institut Teknologi Bandung
Fajril Ambia SKK Migas

DOI:

https://doi.org/10.29017/scog.v49i2.2075

Keywords:

gradient boosting, K-Means clustering, KNIME, machine learning, random forest, simple regression

Abstract

Indonesia's oil and gas industry faces ongoing challenges in maintaining production due to the maturity and decline of many fields. Success in drilling new wells is vital for sustaining output, but performance forecasting is hampered by reservoir variability, geological complexity, and operational differences. These challenges underscore the need for adaptive, data-driven predictive methods in technical planning. This study develops a machine-learning-based model for predicting Estimated Ultimate Recovery (EUR) using a KNIME workflow. K-Means clustering groups wells by reservoir characteristics, and three regression algorithms (Simple Regression, Gradient Boosting, and Random Forest) are compared for predicting EUR. The combined workflow evaluates how reservoir segmentation improves EUR prediction accuracy. The methodology consists of four main stages: (1) collecting and preprocessing historical well data from long-producing oil fields located in the Pekanbaru region, (2) applying K-Means clustering using reservoir features such as porosity, permeability, Net Pay, Water Saturation, and well coordinates, (3) constructing EUR regression models using Simple Regression, Gradient Boosting, and Random Forest with an 80% training and 20% testing scheme, and (4) validating model performance using evaluation metrics such as R² and RMSE. All processes were performed using the KNIME platform to ensure a standardized, transparent, and easily replicable workflow. This study is expected to produce an EUR prediction model that is accurate and stable, while also identifying the most suitable regression algorithm for mature Indonesian reservoirs. Furthermore, the integrated KNIME workflow can serve as a foundation for a decision support system to assist in drilling planning, investment optimization, and the reduction of production uncertainties. In addition, the results of the clustering and modeling can be used to identify the best prospective reservoir zones, thereby supporting the selection of new well drilling locations in areas with the highest production potential.

Author Biographies

Jeffier Winarta, Institut Teknologi Bandung

Jeffier Winarta is affiliated with the Petroleum Engineering Department at Institut Teknologi Bandung (ITB) and SKK Migas. He currently serves as a Senior Analyst at SKK Migas, specializing in reservoir engineering and field development optimization. His professional work focuses on evaluating subsurface performance, production optimization, and supporting strategic decision-making in Indonesia’s upstream oil and gas sector. He is actively engaged in research on the application of machine learning and data-driven approaches to enhance reservoir characterization, well performance analysis, and development planning in mature fields
Amega Yasutra, Institut Teknologi Bandung

Amega Yasutra is a lecturer in the Petroleum Engineering Department at Institut Teknologi Bandung (ITB). He currently serves as the Head of the Master’s Program in Petroleum Engineering at ITB. His academic and research interests include reservoir engineering, production optimization, and the application of data-driven and machine learning approaches in the oil and gas industry. He has been actively involved in teaching, research, and academic program development, contributing to the advancement of petroleum engineering education in Indonesia
Fajril Ambia, SKK Migas

Fajril Ambia is a Senior Analyst at SKK Migas, where he is actively involved in the development and management of integrated database systems to support upstream oil and gas operations. His work focuses on data integration, digital transformation, and the utilization of data-driven systems to enhance decision-making processes in the industry. In addition to his role at SKK Migas, he serves as a lecturer in the Petroleum Engineering Department at Universitas Islam Riau. He has contributed to various academic and research activities, with a strong focus on the application of machine learning in the oil and gas sector, and has authored several publications in this field.

References

J. Chahar, J. Verma, D. Vyas, dan M. Goyal., Data driven approach for hydrocarbon production forecasting using machine learning techniques, Journal of Petroleum Science and Engineering 217, 110757 (2022).

T. M. Susantoro, K. Wikantika, S. Suliantara, H. L. Setiawan, A. B. Harto, dan A. D. Sakti., Applying random forest to oil and gas exploration in Central Sumatra Basin Indonesia based on surface and subsurface data, Remote Sensing Applications: Society and Environment 32, 101039 (2023).

X. Liu, X. Sang, J. Chang, Y. Zheng, dan Y. Han., The water supply association analysis method in Shenzhen based on k-means clustering discretization and apriori algorithm, PLOS ONE 16(8), e0255684 (2021).

G. Satriaji, I. P. Wijaya, H. Pasaribu, N. Mambu, P. Adinda, A. Munawar, dan R. Amar., Application of Machine Learning Algorithm Approach to Enhance the Workover Program Success Ratio in Pertamina Hulu Sanga Sanga Field, Sanga Sanga Block of East Kalimantan, Indonesia, SPE-221349-MS, Society of Petroleum Engineers (2024)

F. Maulana, A. Yasutra, dan Z. Syihab., Case Study of Heterogeneity Index’s Effect on The Successful Workover Based on The Apriori Algorithm, Scientific Contributions Oil and Gas (Lemigas) 48(1), 135–144 (2025). https://doi.org/10.29017/scog.v48i1.1658

S. G. Wardhana, H. J. Pakpahan, K. Simarmata, W. Pranowo, dan H. Purba., Algoritma Komputasi Machine Learning untuk Aplikasi Prediksi Nilai Total Organic Carbon (TOC), Lembaran Publikasi Minyak dan Gas Bumi 55(2), 75–87 (2021). https://doi.org/10.29017/LPMGB.55.2.606

E. Syahrial dan H. Purnomo., Peningkatan Produksi Minyak dengan Injeksi CO2 pada Lapangan Minyak Tua Sangatta Kalimantan Timur, Lembaran Publikasi Lemigas 43(2), 166–175 (2009). https://doi.org/10.29017/LPMGB.43.2.142

Sugiyanto, & Utama, D. N. Estimation of well flowing bottomhole pressure (FBHP) using machine learning. Scientific Contributions Oil and Gas, 48(3), 37–51 (2025). https://doi.org/10.29017/scog.v48i3.1851

Rohmana, R. C., Ariadji, T., Yasutra, A., & Irawan, D. A conceptual framework for cross-basin reservoir characterization: Integrating unsupervised-supervised learning to address geological heterogeneity. Scientific Contributions Oil and Gas, 49(1), 375–393 (2026). https://doi.org/10.29017/scog.v49i1.2001

Prayitno, S. H., Swadesi, B., Hariyadi, Nandiwardhana, D., Jayadianti, H., Widiyaningsih, I., Cahyaningtyas, N., & Imasuly, G. B. The application of machine learning in determining idle well reactivation candidates at PT. Pertamina EP. Scientific Contributions Oil and Gas, 48(2), 69–94 (2025). https://doi.org/10.29017/scog.v48i2.1657

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

Mahfudhoh, S. A., & Welayaturromadhona. Machine learning-based prediction of formation, facies, porosity, and permeability in a carbonate reservoir. Scientific Contributions Oil and Gas, 49(1), 31–47 (2026). https://doi.org/10.29017/scog.v49i1.1969

Rizal, A. A., Ambia, F., Rita, N., & Herawati, I. Comparative study of capacitance resistance model and machine learning for polymer injection performance. Scientific Contributions Oil and Gas, 48(4), 251–279 (2025). https://doi.org/10.29017/scog.v48i4.1929

Septiano, J., Yasutra, A., & Rahmawati, S. D. Build of machine learning proxy model for prediction of wax deposition rate in two-phase flow. Scientific Contributions Oil and Gas, 45(1), 27–41 (2021). https://doi.org/10.29017/SCOG.45.1.922

Rafsanjani, R., Dahlia, A., Ambia, F., Rita, N., & Husbani, A. Comparative analysis of capacitance-resistance models and machine learning for CO₂-EOR forecasting. Scientific Contributions Oil and Gas, 48(4), 433–462 (2025). https://doi.org/10.29017/scog.v48i4.1930

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

Maurenza, F., Yasutra, A., & Tungkup, I. L. Production forecasting using Arps decline curve model with the effect of artificial lift installation. Scientific Contributions Oil and Gas, 46(1), 9–18 (2023). https://doi.org/10.29017/SCOG.46.1.1310

Iskandar, U. P., & Kurihara, M. Long short-term memory (LSTM) networks for forecasting reservoir performances in carbon capture, utilisation, and storage (CCUS) operations. Scientific Contributions Oil and Gas, 45(1), 35–50 (2022). https://doi.org/10.29017/SCOG.45.1.943