An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction

Abstract This study proposes an interpretable deep learning framework to address the high-dimensional and inherently unpredictable challenges associated with oil and gas drilling and completion operations. By comparing TabNet, Tab Transformer, Hopular, and TabDDPM through computational experiments u...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin-bo He, Ke-ming Sheng, Ming-liang Du, Guan-cheng Jiang, Teng-fei Dong, Lei Guo, Bo-tao Xu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99659-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231528300216320
author Yin-bo He
Ke-ming Sheng
Ming-liang Du
Guan-cheng Jiang
Teng-fei Dong
Lei Guo
Bo-tao Xu
author_facet Yin-bo He
Ke-ming Sheng
Ming-liang Du
Guan-cheng Jiang
Teng-fei Dong
Lei Guo
Bo-tao Xu
author_sort Yin-bo He
collection DOAJ
description Abstract This study proposes an interpretable deep learning framework to address the high-dimensional and inherently unpredictable challenges associated with oil and gas drilling and completion operations. By comparing TabNet, Tab Transformer, Hopular, and TabDDPM through computational experiments under identical conditions, TabNet was selected as the optimal approach. The framework integrates Bayesian optimization (BO) with TabNet to model complex oilfield tabular datasets. Fair Cut Tree (FCT) and Synthetic Minority Over-sampling Technique (SMOTE) are incorporated to mitigate data missingness and imbalance, thereby enhancing dataset integrity and robustness. Empirical validation was conducted using 270 data entries collected from 15 distinct oil fields, specifically focusing on reservoir water sensitivity damage in natural core samples. The proposed framework exhibited superior predictive accuracy for the water sensitivity index on an independent test set, achieving a mean absolute percentage error (MAPE) of 4.4495% and a root mean square error (RMSE) of 4.05, underscoring its strong generalization capability. Moreover, this methodological approach enables a quantitative assessment of the influence of critical factors, including reservoir water salinity, initial permeability, and the mineralogical composition of rock formations, on water sensitivity predictions. This represents a significant advancement from traditional qualitative analyses to a more rigorous quantitative factor analysis, with the interpretability findings corroborating established mechanistic insights. The proposed framework offers a versatile and reliable solution for precise predictive modeling in complex drilling and completion scenarios reliant on tabular data, thereby providing a robust theoretical foundation and algorithmic support for accurate forecasting in the oil and gas industry.
format Article
id doaj-art-15335c7ebd5e4ee69984c1f7e5101830
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-15335c7ebd5e4ee69984c1f7e51018302025-08-20T02:03:30ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-99659-5An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage predictionYin-bo He0Ke-ming Sheng1Ming-liang Du2Guan-cheng Jiang3Teng-fei Dong4Lei Guo5Bo-tao Xu6National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)China Oilfield Services LimitedChina Oilfield Services LimitedAbstract This study proposes an interpretable deep learning framework to address the high-dimensional and inherently unpredictable challenges associated with oil and gas drilling and completion operations. By comparing TabNet, Tab Transformer, Hopular, and TabDDPM through computational experiments under identical conditions, TabNet was selected as the optimal approach. The framework integrates Bayesian optimization (BO) with TabNet to model complex oilfield tabular datasets. Fair Cut Tree (FCT) and Synthetic Minority Over-sampling Technique (SMOTE) are incorporated to mitigate data missingness and imbalance, thereby enhancing dataset integrity and robustness. Empirical validation was conducted using 270 data entries collected from 15 distinct oil fields, specifically focusing on reservoir water sensitivity damage in natural core samples. The proposed framework exhibited superior predictive accuracy for the water sensitivity index on an independent test set, achieving a mean absolute percentage error (MAPE) of 4.4495% and a root mean square error (RMSE) of 4.05, underscoring its strong generalization capability. Moreover, this methodological approach enables a quantitative assessment of the influence of critical factors, including reservoir water salinity, initial permeability, and the mineralogical composition of rock formations, on water sensitivity predictions. This represents a significant advancement from traditional qualitative analyses to a more rigorous quantitative factor analysis, with the interpretability findings corroborating established mechanistic insights. The proposed framework offers a versatile and reliable solution for precise predictive modeling in complex drilling and completion scenarios reliant on tabular data, thereby providing a robust theoretical foundation and algorithmic support for accurate forecasting in the oil and gas industry.https://doi.org/10.1038/s41598-025-99659-5Deep learningIntelligent drilling and completionComplex predicationTabNetTabular data modelingSensitivity damage
spellingShingle Yin-bo He
Ke-ming Sheng
Ming-liang Du
Guan-cheng Jiang
Teng-fei Dong
Lei Guo
Bo-tao Xu
An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
Scientific Reports
Deep learning
Intelligent drilling and completion
Complex predication
TabNet
Tabular data modeling
Sensitivity damage
title An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
title_full An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
title_fullStr An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
title_full_unstemmed An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
title_short An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction
title_sort interpretable deep learning framework using fct smote and bo tabnet algorithms for reservoir water sensitivity damage prediction
topic Deep learning
Intelligent drilling and completion
Complex predication
TabNet
Tabular data modeling
Sensitivity damage
url https://doi.org/10.1038/s41598-025-99659-5
work_keys_str_mv AT yinbohe aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT kemingsheng aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT mingliangdu aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT guanchengjiang aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT tengfeidong aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT leiguo aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT botaoxu aninterpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT yinbohe interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT kemingsheng interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT mingliangdu interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT guanchengjiang interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT tengfeidong interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT leiguo interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction
AT botaoxu interpretabledeeplearningframeworkusingfctsmoteandbotabnetalgorithmsforreservoirwatersensitivitydamageprediction