Well log data generation and imputation using sequence based generative adversarial networks

Abstract Well log analysis is significant for hydrocarbon exploration, providing detailed insights into subsurface geological formations. However, gaps and inaccuracies in well log data, often due to equipment limitations, operational challenges, and harsh subsurface conditions, can introduce signif...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdulrahman Al-Fakih, A. Koeshidayatullah, Tapan Mukerji, Sadam Al-Azani, SanLinn I. Kaka
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-95709-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849734829210337280
author Abdulrahman Al-Fakih
A. Koeshidayatullah
Tapan Mukerji
Sadam Al-Azani
SanLinn I. Kaka
author_facet Abdulrahman Al-Fakih
A. Koeshidayatullah
Tapan Mukerji
Sadam Al-Azani
SanLinn I. Kaka
author_sort Abdulrahman Al-Fakih
collection DOAJ
description Abstract Well log analysis is significant for hydrocarbon exploration, providing detailed insights into subsurface geological formations. However, gaps and inaccuracies in well log data, often due to equipment limitations, operational challenges, and harsh subsurface conditions, can introduce significant uncertainties in reservoir evaluation. Addressing these challenges requires effective methods for both synthetic data generation and precise imputation of missing data, ensuring data completeness and reliability. This study introduces a novel framework utilizing sequence-based generative adversarial networks (GANs) specifically designed for well log data generation and imputation. The framework integrates two distinct sequence-based GAN models: time series GAN (TSGAN) for generating synthetic well log data and sequence GAN (SeqGAN) for imputing missing data. Both models were tested on a dataset from the North Sea, Netherlands region. For the imputation task, the input comprises logs with missing values and the output is the corresponding imputed logs; for the synthetic data generation task, the input is complete real logs and the output is synthetic logs that mimic the statistical properties of the original data. All log measurements are normalized to a 0-1 range using min-max scaling, and error metrics are reported in these normalized units. Different sections of 5, 10, and 50 data points were used. Experimental results demonstrate that this approach achieves superior accuracy in filling data gaps compared to other deep learning models for spatial series analysis. The imputation method yielded $$\hbox {R}^{2}$$ values of 0.92, 0.86, and 0.57, with corresponding mean absolute percentage error (MAPE) values of 8.320, 0.005, and 166.6, and mean absolute error (MAE) values of 0.012, 0.002, and 0.03, respectively. The synthetic generation yielded $$\hbox {R}^{2}$$ of 0.92, MAE, of 0.35, and MRLE of 0.01. These results set a new benchmark for data integrity and utility in geosciences, particularly in well log data analysis.
format Article
id doaj-art-d89919d83878451b8b041482da65d05b
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d89919d83878451b8b041482da65d05b2025-08-20T03:07:41ZengNature PortfolioScientific Reports2045-23222025-03-0115112110.1038/s41598-025-95709-0Well log data generation and imputation using sequence based generative adversarial networksAbdulrahman Al-Fakih0A. Koeshidayatullah1Tapan Mukerji2Sadam Al-Azani3SanLinn I. Kaka4College of Petroleum Engineering and Geosciences, King Fahd University of Petroleum MineralsCollege of Petroleum Engineering and Geosciences, King Fahd University of Petroleum MineralsDepartments of Energy Science & Engineering, Earth & Planetary Sciences, and Geophysics, Stanford UniversitySDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum and MineralsCollege of Petroleum Engineering and Geosciences, King Fahd University of Petroleum MineralsAbstract Well log analysis is significant for hydrocarbon exploration, providing detailed insights into subsurface geological formations. However, gaps and inaccuracies in well log data, often due to equipment limitations, operational challenges, and harsh subsurface conditions, can introduce significant uncertainties in reservoir evaluation. Addressing these challenges requires effective methods for both synthetic data generation and precise imputation of missing data, ensuring data completeness and reliability. This study introduces a novel framework utilizing sequence-based generative adversarial networks (GANs) specifically designed for well log data generation and imputation. The framework integrates two distinct sequence-based GAN models: time series GAN (TSGAN) for generating synthetic well log data and sequence GAN (SeqGAN) for imputing missing data. Both models were tested on a dataset from the North Sea, Netherlands region. For the imputation task, the input comprises logs with missing values and the output is the corresponding imputed logs; for the synthetic data generation task, the input is complete real logs and the output is synthetic logs that mimic the statistical properties of the original data. All log measurements are normalized to a 0-1 range using min-max scaling, and error metrics are reported in these normalized units. Different sections of 5, 10, and 50 data points were used. Experimental results demonstrate that this approach achieves superior accuracy in filling data gaps compared to other deep learning models for spatial series analysis. The imputation method yielded $$\hbox {R}^{2}$$ values of 0.92, 0.86, and 0.57, with corresponding mean absolute percentage error (MAPE) values of 8.320, 0.005, and 166.6, and mean absolute error (MAE) values of 0.012, 0.002, and 0.03, respectively. The synthetic generation yielded $$\hbox {R}^{2}$$ of 0.92, MAE, of 0.35, and MRLE of 0.01. These results set a new benchmark for data integrity and utility in geosciences, particularly in well log data analysis.https://doi.org/10.1038/s41598-025-95709-0Generative adversarial networks modelsTime series modelsSequence GAN modelsWell log data imputationSynthetic well log data generation
spellingShingle Abdulrahman Al-Fakih
A. Koeshidayatullah
Tapan Mukerji
Sadam Al-Azani
SanLinn I. Kaka
Well log data generation and imputation using sequence based generative adversarial networks
Scientific Reports
Generative adversarial networks models
Time series models
Sequence GAN models
Well log data imputation
Synthetic well log data generation
title Well log data generation and imputation using sequence based generative adversarial networks
title_full Well log data generation and imputation using sequence based generative adversarial networks
title_fullStr Well log data generation and imputation using sequence based generative adversarial networks
title_full_unstemmed Well log data generation and imputation using sequence based generative adversarial networks
title_short Well log data generation and imputation using sequence based generative adversarial networks
title_sort well log data generation and imputation using sequence based generative adversarial networks
topic Generative adversarial networks models
Time series models
Sequence GAN models
Well log data imputation
Synthetic well log data generation
url https://doi.org/10.1038/s41598-025-95709-0
work_keys_str_mv AT abdulrahmanalfakih welllogdatagenerationandimputationusingsequencebasedgenerativeadversarialnetworks
AT akoeshidayatullah welllogdatagenerationandimputationusingsequencebasedgenerativeadversarialnetworks
AT tapanmukerji welllogdatagenerationandimputationusingsequencebasedgenerativeadversarialnetworks
AT sadamalazani welllogdatagenerationandimputationusingsequencebasedgenerativeadversarialnetworks
AT sanlinnikaka welllogdatagenerationandimputationusingsequencebasedgenerativeadversarialnetworks