Comparison of Geothermal Well Productivity Using KNN, SVM and Gradient Boost Methods
-
Mina Winawati Dwi Aryani
*
Budi Luhur University, Jakarta,
Indonesia
- Indra Nugraha Abdullah Budi Luhur University, Jakarta, Indonesia (*) Corresponding Author
Abstract
Manual and conventional processing of geothermal well production data is computationally inefficient and requires several hours to days to generate productivity assessments, particularly when dealing with large-scale and non-linear operational datasets. The complexity of geothermal production parameters this paper such as wellhead pressure (WHP), enthalpy, steam flow, brine flow, total flow, and generated power this paper creates challenges for accurate and timely productivity classification at the well level. This study utilizes 74,912 daily production records collected from January 2018 to June 2024, comprising 13 operational and production-related attributes. The objective is to identify the most effective machine learning algorithm for classifying geothermal well productivity levels to support faster and more reliable operational decision-making. A comparative machine learning classification approach was conducted using K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), and Gradient Boosting. Model evaluation was performed using three train–test split ratios: 70:30, 80:20, and 90:10. Two modelling scenarios were implemented: with and without Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. The results indicate that the K-NN model achieved the highest classification performance, reaching 94.22% accuracy using the 90:10 split ratio without SMOTE. Gradient Boosting demonstrated stable performance across all ratios, with its best accuracy of 91.39% at the 70:30 split without SMOTE. In contrast, SVM produced the lowest performance, with a maximum accuracy of 79.78% at the 90:10 ratio without SMOTE. The application of SMOTE improved minority class recall, particularly for SVM, but generally reduced overall model accuracy for K-NN and Gradient Boosting. These findings demonstrate that classical machine learning algorithms, particularly K-NN, provide an efficient and accurate solution for geothermal well productivity classification. The proposed approach significantly reduces processing time compared to conventional analytical methods and supports data-driven decision-making in geothermal production forecasting and development planning.
Downloads
References
A. Al-Fakih, A. Al-khudafi, A. Koeshidayatullah, S. Kaka, and A. Al-Gathe, “Forecasting geothermal temperature in western Yemen with Bayesian-optimized machine learning regression models,” Geothermal Energy, vol. 13, no. 1, p. 4, Jan. 2025, doi: 10.1186/s40517-024-00324-3.
N. Saxena et al., “Hybrid KNN-SVM machine learning approach for solar power forecasting,” Environmental Challenges, vol. 14, p. 100838, Jan. 2024, doi: 10.1016/j.envc.2024.100838.
A.-M. Koray, E. Gyimah, M. Metwally, H. Rahnema, and O. Tomomewo, “Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin,” Geothermal Energy, vol. 13, no. 1, p. 8, Jan. 2025, doi: 10.1186/s40517-024-00323-4.
B. Mukherjee, S. Kar, and K. Sain, “Machine Learning Assisted State-of-the-Art-of Petrographic Classification From Geophysical Logs,” Pure Appl. Geophys., vol. 181, no. 9, pp. 2839–2871, Sep. 2024, doi: 10.1007/s00024-024-03563-4.
R. Dwivedi et al., “Granite porosity prediction under varied thermal conditions using machine learning models,” Earth Sci. Inform., vol. 18, no. 2, p. 211, Jun. 2025, doi: 10.1007/s12145-025-01726-y.
J. He, K. Li, X. Wang, N. Gao, X. Mao, and L. Jia, “A Machine Learning Methodology for Predicting Geothermal Heat Flow in the Bohai Bay Basin, China,” Natural Resources Research, vol. 31, no. 1, pp. 237–260, Feb. 2022, doi: 10.1007/s11053-021-10002-x.
Mahmoud. M. AlGaiar, “Unlocking Geothermal Potential: Advancing Exploration with Artificial Intelligence for Sustainable Energy Solutions,” in ADIPEC, SPE, Nov. 2024, p. 25. doi: 10.2118/222269-MS.
M. Mahetaji and J. Brahma, “Enhancing wellbore stability through machine learning for sustainable hydrocarbon exploitation,” Sci. Rep., vol. 15, no. 1, p. 35268, Oct. 2025, doi: 10.1038/s41598-025-17588-9.
A. Saad et al., “Enhancing Geothermal Drilling Performance: Predicting Rate of Penetration with Machine Learning Utilizing Geomechanical and Petrophysical Data,” in SPE Offshore Europe Conference & Exhibition, SPE, Sep. 2025. doi: 10.2118/226760-MS.
Z. Guo, K. Li, H. Zhang, C. Gu, and J. He, “Predicting Geothermal Heat Flow in the Bohai Bay Basin Based on Machine Learning Methods,” Math. Geosci., vol. 57, no. 5, pp. 925–949, Jul. 2025, doi: 10.1007/s11004-025-10182-9.
Y. Xiong, M. Zhu, Y. Li, K. Huang, Y. Chen, and J. Liao, “Recognition of Geothermal Surface Manifestations: A Comparison of Machine Learning and Deep Learning,” Energies (Basel)., vol. 15, no. 8, p. 2913, Apr. 2022, doi: 10.3390/en15082913.
E. R. Ugarte and S. Salehi, “A Robust Screening Tool to Repurpose Hydrocarbon Wells to Geothermal Wells in Oklahoma,” in SPE Oklahoma City Oil and Gas Symposium, Oklahoma: SPE, Apr. 2023, pp. 11–21. doi: 10.2118/213068-MS.
T. yehia, M. Gasser, H. Ebaid, E. Okoroafor, and N. Meehan, “A Comparative Analysis of Machine Learning Techniques for Geothermal Wells’ Drilling Rate of Penetration (Rop) Prediction,” in Unconventional Resources Technology Conference, Texas: SPE/AAPG/SEG, Jun. 2024, pp. 5–8. doi: https://doi.org/10.15530/urtec-2024-4044244.
H. Ebaid, E. Rita Okoroafor, N. Meehan, T. Yehia, and M. Gasser, “A Comparative Analysis of Machine Learning Techniques for Geothermal Wells’ Drilling Rate of Penetration (ROP) Prediction,” in The Unconventional Resources Technology Conference, Tulsa, OK USA: American Association of Petroleum Geologists, Jun. 2024, pp. 8–16. doi: 10.15530/urtec-2024-4044244.
A. Al‐Fakih, A. Abdulraheem, and S. Kaka, “Application of machine learning and deep learning in geothermal resource development: Trends and perspectives,” Deep Underground Science and Engineering, vol. 3, no. 3, pp. 286–301, Sep. 2024, doi: 10.1002/dug2.12098.
M. Ahmadi, “Interpretable Machine Learning for High-Accuracy Reservoir Temperature Prediction in Geothermal Energy Systems,” Energies (Basel)., vol. 18, no. 13, p. 3366, Jun. 2025, doi: 10.3390/en18133366.
A. Shahdi, S. Lee, A. Karpatne, and B. Nojabaei, “Exploratory analysis of machine learning methods in predicting subsurface temperature and geothermal gradient of Northeastern United States,” Geothermal Energy, vol. 9, no. 1, p. 18, Dec. 2021, doi: 10.1186/s40517-021-00200-4.
T. Yehia, M. Gasser, H. Ebaid, N. Meehan, and E. R. Okoroafor, “Comparative analysis of machine learning techniques for predicting drilling rate of penetration (ROP) in geothermal wells: A case study of FORGE site,” Geothermics, vol. 121, p. 103028, Jul. 2024, doi: 10.1016/j.geothermics.2024.103028.
S. I. Mohammad et al., “Expedited and dependable geothermal rock characterization and absolute permeability modeling using advanced data-driven techniques,” Geothermal Energy, vol. 13, no. 1, p. 45, Dec. 2025, doi: 10.1186/s40517-025-00371-4.
Y. Chen, K. Li, H. Zhang, C. Gu, J. He, and W. Lu, “Enhanced Prediction of Geothermal Heat Flow Using an Improved GBRT Model with Genetic Algorithm,” Natural Resources Research, vol. 34, no. 5, pp. 2509–2535, Oct. 2025, doi: 10.1007/s11053-025-10501-1.
L. Wang, Z. Yu, Y. Zhang, and P. Yao, “Review of machine learning methods applied to enhanced geothermal systems,” Environ. Earth Sci., vol. 82, no. 3, p. 69, Feb. 2023, doi: 10.1007/s12665-023-10749-x.
Y. Duan, Y. Liang, Q. Ji, and Z. Wang, “A Machine Learning Approach for the Clustering and Classification of Geothermal Reservoirs in the Ying-Qiong Basin,” J. Mar. Sci. Eng., vol. 13, no. 3, p. 415, Feb. 2025, doi: 10.3390/jmse13030415.
S. Novianti, T. Nurkholifa, M. Suryana, E. Susanto Program Studi Usaha Perjalanan Wisata, and J. Administrasi Niaga Politeknik Negeri Bandung, “Penggunaan Geographical Information System (GIS) untuk Visualisasi Analisis Perilaku Spasial Wisatawan,” vol. 4, no. 2, pp. 2654–3894, 2021, doi: 10.17509/jithor.v4i2,%20October.37168.
P. U. Ekeopara, C. J. Nwosu, F. M. Kelechi, C. P. Nwadiaro, and K. K. ThankGod, “Prediction of Thermal Conductivity of Rocks in Geothermal Field Using Machine Learning Methods: a Comparative Approach,” in SPE Nigeria Annual International Conference and Exhibition, Lagos: SPE, Jul. 2023, pp. 11–14. doi: 10.2118/217217-MS.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Comparison of Geothermal Well Productivity Using KNN, SVM and Gradient Boost Methods
Pages: 2491-2506
Copyright (c) 2026 Mina Winawati Dwi Aryani, Indra Nugraha Abdullah
This work is licensed under a Creative Commons Attribution 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
