Investigating Downhole Drilling Temperature Prediction: A Data-Driven Trial of Machine Learning and Deep Learning Methods

Abstract

Understanding the dynamic behavior of downhole temperature during drilling operations is crucial for optimizing tool configuration and maximizing the acquisition of logging data, thereby eliminating the need for additional tripping or wireline logging runs. This paper presents a comprehensive study on the application of machine learning and deep learning techniques for predicting downhole temperatures in drilling operations. Following an extensive preprocessing stage that included smoothing and normalizing drilling parameters and related well data, the study compares several machine learning algorithms and long short-term memory (LSTM) architectures. Notable models such as random forest, k-nearest neighbors, decision tree regressors, and LSTM (both sequential and encoder-decoder) were found to be effective for temperature prediction. The LSTM Encoder-Decoder model demonstrated the highest accuracy, with a root mean squared error (RMSE) of 0.892, though it requires higher computational resources. Sensitivity analysis of the model identified revolutions per minute (RPM) and borehole deviation as key factors, providing valuable insights for model refinement and improved thermal management.

Keywords

drilling temperature prediction / drilling parameters / downhole temperature / machine learning / deep learning / engineering geology

References

[1] Abadi M, Agarwal A, Barham P, et al.. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, 2015

[2] Abdelhafiz M M, Hegele L A, Oppelt J F. Temperature Modeling for Wellbore Circulation and Shut-in with Application in Vertical Geothermal Wells. Journal of Petroleum Science and Engineering, 2021, 204: 108660

[3] Abdelhafiz M M, Oppelt J, Mahmoud O, et al.. Effect of Drilling and Wellbore Geometry Parameters on Wellbore Temperature Profile: Implications for Geothermal Production. Advances in Geo-Energy Research, 2023, 8(3): 170-180

[4] Al-Fakih A, Li K W. Estimation of Bottom-Hole Temperature Based on Machine/Deep Learning. Proceedings of the 2021 International Petroleum and Petrochemical Technology Conference, 2022, Singapore, Springer

[5] Ali M. PyCaret: An Open Source, Low-Code Machine Learning Library in Python, 2020Pycaret Version 1.0 (2020)

[6] Al-Qahtani A S, Momtan B A. Generating Synthetic Temperature Surveys for Wells through Subsurface Spatial Machine Learning Modeling and Time Series Forecasting. ADIPEC, 2023, Richardson, Society of Petroleum EngineersOctober 2 - 5, 2023. Abu Dhabi, UAE

[7] Cheraghian G. Nanoparticles in Drilling Fluid: A Review of the State-of-the-Art. Journal of Materials Research and Technology, 2021, 13: 737-753

[8] Cho K, van Merrienboer B, Gulcehre C, et al.. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, Stroudsburg, PA, USA, ACL1724-1734 Doha, Qatar

[9] Dursun S, Kumar A, Samuel R. Using Data-Driven Predictive Analytics to Estimate Downhole Temperatures while Drilling. SPE Annual Technical Conference and Exhibition, 2014, Richardson, Society of Petroleum EngineersOctober 27 - 29, 2014. Amsterdam, The Netherlands

[10] Gautam S, Guria C, Gope L. Prediction of High-Pressure/ High-Temperature Rheological Properties of Drilling Fluids from the Viscosity Data Measured on a Coaxial Cylinder Viscometer. SPE Journal, 2021, 26(5): 2527-2548

[11] Gul S, Aslanoglu V, Tuzen M K, et al.. Estimation of Bottom Hole and Formation Temperature by Drilling Fluid Data: A Machine Learning Approach. Proceedings of the 44th Workshop on Geothermal Reservoir Engineering, 2019, Stanford, California, Stanford University

[12] Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735-1780

[13] Khaled M S, Wang N Y, Ashok P, et al.. Strategies for Prevention of Downhole Tool Failure Caused by High Bottomhole Temperature in Geothermal and High-Pressure/High-Temperature Oil and Gas Wells. SPE Drilling & Completion, 2023, 38(2): 243-260

[14] Kumar A, Samuel R. Analytical Model to Predict the Effect of Pipe Friction on Downhole Fluid Temperatures. SPE Drilling & Completion, 2013, 28(3): 270-277

[15] Liu C, Phan D T, Abousleiman Y N. Effects of Temperature and Rate-Dependent Mud Cake Buildup on Wellbore Stability in Multi-Permeability Formations. Middle East Oil, Gas and Geosciences Show, 2023, Richardson, Society of Petroleum EngineersFebruary 19 - 21, 2023. Manama, Bahrain

[16] Mao L J, Wei C J, Jia H, et al.. Prediction Model of Drilling Wellbore Temperature Considering Bit Heat Generation and Variation of Mud Thermophysical Parameters. Energy, 2023, 284: 129341

[17] Olukoga T A, Feng Y. Practical Machine-Learning Applications in Well-Drilling Operations. SPE Drilling & Completion, 2021, 36(4): 849-867

[18] Pedregosa F, Varoquaux G, Gramfort A, et al.. Scikit-Learn: Machine Learning in Python. Journal of Machine Learning Research, 2011, 12: 2825-2830

[19] Piccialli V, Sciandrone M. Nonlinear Optimization and Support Vector Machines. Annals of Operations Research, 2022, 314(115-47

[20] Ramadan A M, Osman A, Mehanna A, et al.. Simulation of Filter-Cake Formations on Vertical and Inclined Wells under Elevated Temperature and Pressure. SPE Journal, 2024, 29(5): 2212-2224

[21] Suryadi H, Bolchover P, Xin C, et al.. Application of Dynamic Temperature Modelling for Planning High Temperature Well. Middle East Oil & Gas Show and Conference, 2017

[22] Williams R J, Zipser D. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks. Neural Computation, 1989, 1(2): 270-280

[23] Xiao D, Hu Y F, Meng Y F, et al.. Research on Wellbore Temperature Control and Heat Extraction Methods while Drilling in High-Temperature Wells. Journal of Petroleum Science and Engineering, 2022, 209: 109814

[24] Zhang Y, Li Y A, Kong X W, et al.. Temperature Prediction Model in Multiphase Flow Considering Phase Transition in the Drilling Operations. Petroleum Science, 2024, 21(31969-1979

RIGHTS & PERMISSIONS

China University of Geosciences (Wuhan) and Springer-Verlag GmbH Germany, Part of Springer Nature

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.