COMPARATIVE STUDY OF K-NEAREST NEIGHBORS (KNN) AND ARTIFICIAL NEURAL NETWORK (ANN) FOR LITHOLOGY CLASSIFICATION
DOI:
https://doi.org/10.23960/jge.v12i1.511Keywords:
Artificial Neural Network, K-Nearest Neighbors, Lithology Classification, Machine Learning, Well LogAbstract
This study applies a machine learning approach to classify lithology using well log data from 14 wells in Ford County, Kansas, United States, to address the limitations of conventional interpretation, which is time-consuming and subjective due to overlapping log responses. Reference lithology labels were generated using predefined well-log interpretation criteria and grouped into four classes: sandstone, limestone, shale/clay, and coal. Two supervised learning algorithms, K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN), were evaluated and compared. The preprocessing stages included data cleaning by removing null values and inconsistencies, Z-score normalization, class balancing using SMOTE on the training data to prevent data leakage, and feature selection based on Pearson correlation. Model performance was evaluated using Classification Accuracy (CA), Area Under the Curve (AUC), Logarithmic Loss (Log Loss), and 5-fold cross-validation. The results indicate that ANN consistently outperformed KNN in lithology classification. ANN achieved classification accuracies above 95%, AUC values approaching 1.00, and low Log Loss, whereas KNN achieved testing accuracies of approximately 75-80% but exhibited lower cross-validation performance, indicating reduced robustness in intervals characterized by overlapping lithological responses. The optimal ANN architecture consisted of three hidden layers with 100-100-100 neurons and 100 training iterations. Visual evaluation of four test wells showed good agreement between the predicted and reference lithology distributions. These findings suggest that machine learning, combined with appropriate preprocessing techniques, can support lithology classification from well log data. Among the evaluated models, ANN demonstrated superior capability in capturing nonlinear relationships between well log responses and lithological variations within the study area.
References
Adiwiguna, Y. P., Purbaseno, H., Syuhara, H., Pribadi, F. J., Sarbani, A., & Kusuma, A. D. (2022). Membangun Tool Prediksi yang Komprehensif Guna Meningkatkan Akurasi Produk Akhir Pencampuran Kualitas Batubara Menerapkan Perbandingan Kolaboratif pada Algoritma Regresi Hingga Neural Network. Indonesian Mining Professionals Journal, 4(2 November 2022). https://doi.org/10.36986/impj.v4i2.79
Asquith, G. B., Krygowski, D., Henderson, S., & Hurley, N. F. (2004). Basic Well Log Analysis (2nd ed.). American Association of Petroleum Geologist.
Esiri, A. E., Jambol, D. D., & Ozowe, C. (2024). Enhancing Reservoir Characterization With Integrated Petrophysical Analysis and Geostatistical Methods. Open Access Research Journal of Multidisciplinary Studies, 7(2), 168–179. https://doi.org/10.53022/oarjms.2024.7.2.0038
Galupino, J. & Dungca, J. (2022). Machine Learning Models to Generate a Subsurface Soil Profile : A Case Of Makati City , Philippines. International Journal of GEOMATE, 23(95), 57–64. https://doi.org/https://doi.org/10.21660/2022.95.3029
Hamid, S. & Mousavi, R. (2024). A Novel Approach To Classify Lithology of Reservoir Formations Using GrowNet and Deep ‐ Insight With Physic ‐ Based Feature Augmentation. Energy Science & Engineering, July, 4453–4477. https://doi.org/10.1002/ese3.1895
Johnson, W.C. & Woodburn, T. L. (2009). Surficial Geology of Ford County, Kansas (Map Series 108). Kansas Geological Survey.
Kansas Geological Survey (KGS) (2004). Oil and Gas Well Log Database And Geological Data. University of Kansas. https://kgs.ku.edu/data-and-maps
Khatti, J. & Grover, K. S. (2022). Determination of Suitable Hyperparameters of Artificial Neural Network for the Best Prediction of Geotechnical Properties of Soil. International Journal For Research in Applied Science & Engineering Technology (IJRASET), 10(V May 2022).
Komara, E., Nugraha, M. F., & Rafi, M. (2024). Lithology Prediction Using K-Nearest Neighbors ( KNN ) Algorithm Study Case In Upper Cibulakan Formation. Geomatics International Conference 2024 (GEOICON 2024), IOP Conference Series Earth and Enviromental Science. https://doi.org/10.1088/1755-1315/1418/1/012062
Marembayev, T., Kurmangaliyev, D., Bekbaouv, B., & Amanbaek, Y. (2021). A Comparison of Machine Learning Algorithms in Predicting Lithofacies: Case Studies from Norway and Kazakhstan. Energies, 14(1986), 1–16. https://doi.org/https://doi.org/10.3390/en14071896
Maulana, A., Lepong, P., Rayzy, D., Sutaji, P., Munir, R., Fisika, S., Mulawarman, U., Geofisika, S., & Mulawarman, U. (2024). Identifikasi Keberadaan Hidrokarbon Menggunakan Inversi Impedansi Akustik dengan Algoritma Artificial Neural Network. Jurnal Geosains Kuta Basin, 7(1).
Mohamed, I. M., Mohamed, S., Petroleum, K., Mazher, I., & Chester, P. (2019). Formation Lithology Classification : Insights into Machine Learning Methods. Society of Petroleum Engineers, SPE-196096.
Nabilah, P., Masrurah, Z., Ikhlas, & Putra, R. R. (2023). Identifikasi Lapisan Akuifer Wilayah Aceh Besar Berdasarkan Korelasi Data Electrical Logging dan Cutting. Jurnal Geofisika Eksplorasi, 09(02), 131–141. https://doi.org/https://doi.org/10.23960/jge.v9i2.279
Prabowo, U. N., Ferdiyan, A., & Raharjo, S. A. (2023). Comparison of Facies Estimation Using Support Vector Machine ( SVM ) and K-Nearest Neighbor ( KNN ) Algorithm Based on Well Log Data. Aceh International Journal of Science and Technology, 12(August), 246–253. https://doi.org/10.13170/ aijst.12.2.28428
Putra, Army, M. I. R., Adiwarman, M., & Rassarandi, F. D. (2023). Pengolahan Citra Digital Untuk Penentuan Jenis Batubara di Pt Bukit Asam, Tbk. Dengan Menggunakan Metode Algoritma K-Nearest Neighbor. Jurnal Ilmiah Teknik Dan Sains (JITS), 1(1), 6–10. https://doi.org/https://doi.org/ 10.62278/jits.v1i1.2
Qamar, R. & Zardari, B. A. (2023). Artificial Neural Networks : An Overview. Mesopotamian Journal of Computer Science, 2023, 124–133. https://doi.org/10.58496/ MJCSC/2023/015
Rohmana, R. C., Triwanti, D., Setiyaningrum, P. R., Perminyakan, T., Perminyakan, T., & Perminyakan, T. (2024). Penerapan Machine Learning dalam Penentuan Porositas Batuan : Studi Kasus Menggunakan Regresi Linier Berganda dan Regresi KNN pada Data Log Sumur Application of Machine Learning in Rock Porosity Determination : Case Study Using Multiple Linear Regression. Jurnal Teknik (JT) FT UMT, 13(02), 42–50.
Sastra, M. M. & Rohmana, R. C. (2024). Perbandingan Metode Klasifikasi Machine Learning : Studi Kasus Prediksi Jenis Litologi Berdasarkan Data Well Log Pada Formasi Sleipner , North Sea Comparison of Machine Learning Classification Methods : Case Study of Lithology Type Prediction Based on Wel. Jurnal Teknik (JT) FT UMT, 13(02), 51–63.
Sephiana, S. E., Karyanto, & Sinambela, R. Z. (2023). Analisis Petrofisika dalam Mengidentifikasi Zona Hidrokarbon pada Formasi Tualang dan Lakat. Jurnal Geofisika Eksplorasi, 9(3), 165–183. https://doi.org/https://doi.org/10.23960/jge.v9i3.273
Septyandy, M. R., & Subroto, E. A. (2023). Penentuan Model Total Organic Carbon dengan Menggunakan Metode Artificial Neural Network dan Adaptive Neuro Fuzzy Inference System untuk Estimasi Potensi Gas Serpih di Cekungan Jawa Barat Utara. Jurnal Ilmiah Teknologi Informasi Asia, 17(1), 83–96.
Sudrazat, S. D., Purba, B., Wijaksono, E., Pranowo, W., & Hibatullah, M. I. (2020). Prediksi Kecepatan Gelombang S dengan Machine Learning pada Sumur “S-1”, Cekungan Sumatera Tengah Indonesia. Lembaran Publikasi Minyak Dan Gas Bumi, 54(1), 29–35.
Wang, X., Yang, S., Zhao, Y., & Wang, Y. (2018). Lithology Identification Using An Optimized KNN Clustering Method Based on Entropy-Weighed Cosine Distance in Mesozoic Strata of Gaoqing Field, Jiyang Depression. Journal of Petroleum Science and Engineering, 166, 157–174. https://doi.org/10.1016/ j.petrol.2018.03.034
Wardhana, S. G., Aldi, M., & Siregar, R. I. (2022). Prediksi Kecepatan Gelombang Geser (Vs) Menggunakan Machine Learning di Sumur X. Jurnal Geofisika Eksplorasi, 08(01), 67–77.
Wardhana, S. G. & Pakpahan, H. J. (2021). Algoritma Komputasi Machine Learning untuk Aplikasi Prediksi Nilai Total Organic Carbon ( TOC ). Lembaran Publikasi Minyak Dan Gas Bumi, 55(2), 75–87.
Downloads
Published
How to Cite
Issue
Section
Citation Check
License
Copyright (c) 2026 JGE (Jurnal Geofisika Eksplorasi)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors/Readers/Third Parties can read, print and download, redistribute or republish the article (e.g. display in a repository), translate the article, download for text and data mining purposes, reuse portions or extracts from the article in other works, sell or re-use for commercial purposes, remix, transform, or build upon the material, they must distribute their contributions under the same license as the original Creative Commons Attribution-NonComercial (CC BY-NC).
