Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms

Guojie Zhang

doi:10.47297/taposatWSP2633-456913.20260703

PDF
Export
Share
Collection
Album

Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms

Volume 7, Issue 3

Views: 0 Downloads: 0

Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms
Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms
Weifang Commercial College Shandong Province, Weifan, Shandong, 261000, China
Vol. 7, Issue 3, Pages: 61-66(2026)
Published：30 March 2026
DOI：10.47297/taposatWSP2633-456913.20260703
Accepted：

Scan QR Code

Zhang Guojie.Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms[J].Theory and Practice of Science and Technology,2026,07(03):61-66.
DOI：

Zhang Guojie.Research on Intelligent Prediction of Formation Pressure and Log Curve Completion Based on Machine Learning Algorithms[J].Theory and Practice of Science and Technology,2026,07(03):61-66. DOI： 10.47297/taposatWSP2633-456913.20260703.

摘要

Abstract

Aiming at the problem of low accuracy in formation pressure prediction caused by missing logging data and severe noise interference in oil and gas fields

this paper integrates deep learning with geological prior knowledge and proposes an integrated method for log curve completion and intelligent formation pressure prediction. The method implements multi-dimensional data preprocessing through wavelet threshold denoising

adaptive hierarchical normalization and SMOTE oversampling

constructs a Cascaded LSTM model to accurately complete missing segments of logging curves

designs a PC-LSTM model for intelligent formation pressure prediction

and introduces an EnLSTM model to solve the problems of small-sample training and prediction uncertainty quantification. Verified by field data from the Daqing Oilfield

Williston Basin (USA) and Eagle Ford Shale Reservoir: the signal-to-noise ratio of data reaches 21.36 dB after wavelet denoising; the coefficient of determination (R²) of Cascaded LSTM completion is 0.931; the mean absolute error of PC-LSTM pressure prediction is only 0.82 MPa; EnLSTM achieves an accuracy of 88.5% and a 95% confidence interval coverage rate of 92.3% with only 10% training samples. This method realizes the collaborative optimization of logging data restoration and formation pressure prediction

and can provide technical support for the safe and efficient exploration and development of complex oil and gas reservoirs.

关键词

Keywords

references

Guo Jiahui. Research and Innovative Ideas on Exploration Technology for Oilfield Geological Engineering[J]. China Equipment Engineering, 2025, (S2):276-278.

Eaton J E. The Equation for Geopressure Prediction from Well Logs [J]. SPE Drilling & Completion, 1975, 1 (1): 38-49.

Tahmasebi P, Hezarkhani A. Artificial intelligence techniques for prediction of formation pressure from well log data [J]. Journal of Petroleum Science and Engineering, 2012, 88-89: 106-113.

Pham T D, Malallah A, Leng X, et al. Missing well log prediction using convolutional long short-term memory network [J]. GEOPHYSICS, 2020, 85 (6): D127-D138.

Wang Chunyan, Jin Peng, Gui Qihao. Interval-type fuzzy neural network-based remote sensing image segmentation method [J]. Surveying and Mapping Science, 2024,49(05):84-98.

Addison P S. Wavelet transform applications in well log signal denoising and feature extraction [J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55 (8): 4562-4571.

Chen Yuntian. Research on Logging Curve Completion and Generation Based on Machine Learning [D]. Peking University, 2020.

Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: Synthetic Minority Over-sampling Technique [J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357.

Al-Jawad A, Al-Dabbagh I, Mahmood A K. Well log completion using deep recurrent neural networks [J]. Journal of Petroleum Science and Engineering, 2021, 198: 108298.

Karimpouli S, Tahmasebi P. Physics-constrained deep learning for geophysical properties prediction [J]. Physics of The Earth and Planetary Interiors, 2020, 302: 106498.

Emerick A A, Reynolds A C. Ensemble randomized maximum likelihood method for history matching and uncertainty quantification [J]. Computational Geosciences, 2013, 17 (3): 431-450.

Song L. Cai. Research on Bridge Crack Prediction and Control Measures Based on Convolutional Neural Networks [J]. Construction Machinery, 2025, (10):266-269.

Wang Lei. Research on Prediction Method for Remaining Service Life of Hydraulic Pumps Based on Multi-source Data Fusion [D]. Xi'an University of Electronic Science and Technology, 2024.

Cai M. Research on Weld Seam Inspection of Ultrasonic Probes for Visual Recognition-Assisted Localization in Robotic Arms [J]. Laboratory Testing, 2025,3(21):54-56.

Raja I, Zhang L, Al-Dhabyani W. Digital twin applications for intelligent drilling and formation pressure monitoring [J]. Journal of Petroleum Exploration and Production Technology, 2023, 13 (5): 1234-1256.