Covid-19 Research

Case Study

Deep Learning-Based Drilling Rate Prediction for Composite Sedimentary Zones: A Case Study of the Lower Taedong River

Journal of Biomedical Research & Environmental Sciences article abstract with citation details, DOI, publication dates, subject areas, full text links, and references.

View DOI Submit Manuscript

Article Details

Publication record, authors, dates, abstract, and full text access.

Open Access
Article Type Case Study
Subject Environmental Sciences
OCLC JBRES Record
Kum-Hyok Choe*, Kum-Dol Pak, Yong-Nam Kim and Il-Jin Kim
Issue: Volume7-Issue4
Pages: 1-9
Received: 2026-03-25
Accepted: 2026-04-04
Published: 2026-04-05

Abstract

Background: The lower Taedong River (DPR Korea) is a typical fluvial-estuarine-marine composite sedimentary zone characterized by strong heterogeneity, complex hydrodynamics, and highly variable sediment properties. These geological and hydrological conditions give rise to severe drilling challenges, including unstable penetration rates, low construction efficiency, frequent bit clogging, and borehole collapse. This case study proposes a deep learning-based solution to address these engineering problems.
Case Presentation: A total of 350 field datasets were collected from 50 drilling points in the study area, encompassing 11 input parameters classified into three categories: 5 sediment geological indices, 3 hydrodynamic parameters, and 3 drilling operational parameters. A 4-layer Backpropagation (BP) neural network with a topological structure of 11–15–10–1 was constructed. The Adam optimization algorithm and early stopping strategy were employed in model training to mitigate overfitting.
Results: The trained BP neural network model achieved excellent prediction performance on the test set, with a root mean square error (RMSE) of 0.12 m/h, a coefficient of determination (R²) of 0.97, and an average relative error of 2.8%. This performance is significantly superior to that of the multiple nonlinear regression model (RMSE = 0.16 m/h, R² = 0.87, average relative error = 6.8%). More than 92% of the model’s predictions had a relative error within ±5%, meeting the accuracy requirements of practical geotechnical engineering.
Conclusion: This case study validates the effectiveness of deep learning in accurately predicting drilling rates in complex composite sedimentary environments. The proposed BP neural network model serves as a practical engineering tool for optimizing drilling parameters, reducing construction costs, and enhancing safety control in similar coastal drilling projects worldwide.

FullText HTML FullText PDF DOI: 10.37871/jbres2288 Crossmark

Certificate of Publication

Certificate of Publication

Copyright

© 2026 Kum-Hyok C et al. Distributed under Creative Commons CC-BY 4.0 Creative CommonsAttribution

How to cite this article

Kum-Hyok C, Pak KD, Kim YN, Kim J. Deep Learning-Based Drilling Rate Prediction for Composite Sedimentary Zones: A Case Study of the Lower Taedong River. J Biomed Res Environ Sci. 2026 Apr 05; 7(4): 9. Doi: 10.37872/jbres2288

Subject area(s)

GeosciencesEnvironmental Impacts

References

  1. Zhang Y, Li X, Wang H. Influencing factors and optimization of drilling rate in offshore bridge foundation engineering. Mar Georesour Geotechnol. 2020;38(5):567-578. doi:10.1080/1064119X.2019.1688443
  2. Chen C, Liu Y, Li J. Drilling rate prediction model based on geological and engineering parameters in marine sand areas. Ocean Eng. 2020;203:107123. doi:10.1016/j.oceaneng.2020.107123
  3. Wang Z, Li L, Zhang H. Quantitative analysis of influencing factors on drilling rate in fine-grained sedimentary areas. J Geotech Geoenviron Eng. 2021;147(3):04020198. doi:10.1061/(ASCE)GT.1943-5606.0002456
  4. Dalrymple RW, Choi K. Morphologic and facies trends through the fluvial–marine transition in tide-dominated depositional systems. Earth Sci Rev. 2007;81(3-4):135-174.
  5. Chough SK, Lee HJ, Yoon SH. Marine geology of Korean seas. 2nd ed. Amsterdam: Elsevier; 2000.
  6. Lee HJ, Chough SK. Sediment distribution, dispersal and budget in the Yellow Sea. Mar Geol. 1989;87(2-4):195-205.
  7. Lim DI, Choi JY, Jung HS, et al. Recent sediment accumulation and origin of shelf mud deposits in the Yellow and East China Seas. Prog Oceanogr. 2007;73(2):145-159.
  8. Li X, Zhang Y, Wang H. Comparative study on drilling rate influencing factors in different sedimentary environments. J Geophys Eng. 2022;19(2):025012.
  9. Bishop CM. Pattern recognition and machine learning. New York: Springer; 2006.
  10. Draper NR, Smith H. Applied regression analysis. 3rd ed. New York: John Wiley & Sons; 1998.
  11. Seber GAF, Wild CJ. Nonlinear regression. 2nd ed. Hoboken: John Wiley & Sons; 2003.
  12. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323(6088):533-536.
  13. Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge: MIT Press; 2016.
  14. Yu Y, Tian S, Li J, et al. Well-seismic joint data-driven resistivity-based prediction of 3D spatial rate of penetration. Front Earth Sci. 2025;13. doi:10.3389/feart.2025.1546094
  15. Research on the application of particle swarm optimization algorithm based on heterogeneous lithology analysis and drilling parameter correction to optimize the back propagation neural network rate of penetration prediction model. Scholarmate; 2025.
  16. Choe KH, Ri JM, Kim YN. Drilling speed modeling for river-sediment classification based on response surface methodology: In case of Taedong River, DPRK. Res Sq [Preprint]. 2025. doi:10.21203/rs.3.rs-8323852/v1
  17. Chang M, Zhong R, Johnson R, Chen Z. Enhancing rate of penetration predictions in the Surat Basin using supervised machine learning: A comparative study of ANN and XGBoost models. In: SPE Mediterranean Offshore Conference; 2024 Oct; Alexandria, Egypt. doi:10.2118/223344-MS
  18. Elkatatny S. Real-time prediction of drilling rate using artificial neural networks in heterogeneous carbonate formations. J Pet Sci Eng. 2021;200:108384. doi:10.1016/j.petrol.2021.108384
  19. Abbas AK, Al-Mudhafar WJ, Alsaba M. Hybrid machine learning models for rate of penetration prediction in directional wells. SPE J. 2022;27(4):2015-2030. doi:10.2118/209594-PA
  20. Li M, Liu G, Li J. A comparative study of LSTM, GRU, and BP neural networks for real-time ROP prediction. Geoenergy Sci Eng. 2023;225:211689. doi:10.1016/j.geoen.2023.211689
  21. Zhang L, Chen X, Wang Y. A review of data-driven methods for rate of penetration prediction in drilling engineering. Artif Intell Rev. 2025;58(1):45-78. doi:10.1007/s10462-024-10789
Publish with JBRES — Peer-reviewed, multidisciplinary Open Access with rapid review, DOI, and global visibility.
Double-Blind CrossRef DOI Discoverable
Submit Manuscript Membership