☆ 4.4 Article

Well Log Analysis and Comparison of Supervised Machine Learning Algorithms for Lithofacies Identification in Pab Formation, Lower Indus Basin

JOURNAL OF APPLIED GEOPHYSICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Geosciences, Multidisciplinary

Digital construction of geophysical well logging curves using the LSTM deep-learning network

Jing Li et al.

Summary: A complete well logging suite is frequently needed, but often unavailable or missing parts. The mudstone section is prone to wellbore collapse, causing distortion in well logs. The rapid evolution of deep-learning algorithms enables digital construction of missing well logging curves with high precision.

FRONTIERS IN EARTH SCIENCE (2023)

添加到收藏夹

Article Energy & Fuels

Lithofacies classification and sequence stratigraphic description as a guide for the prediction and distribution of carbonate reservoir quality: A case study of the Upper Cretaceous Khasib Formation (East Baghdad oilfield, central Iraq)

Mohamed Abdel-Fattah et al.

Summary: The lithofacies of the Khasib Formation in the East Baghdad oilfield have been studied using a sequence stratigraphic framework and multivariate statistical methods. This helps to define the reservoir geometry and petrophysical characteristics of the Khasib reservoirs. The highstand systems tract of the Khasib Formation shows the best reservoir characteristics in terms of thickness, porosity, and hydrocarbon saturation.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Accelerating core characterization and interpretation through deep learning with an application to legacy data sets

J. G. Solum et al.

Summary: Core descriptions are crucial for subsurface reservoir characterizations, but the traditional manual methods are time-consuming and inconsistent. By using deep learning segmentation networks trained on labeled global data sets, we can quickly infer lithofacies and structural features on core images, providing high-level digital characterizations and relieving geoscientists from repetitive tasks.

INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION (2022)

添加到收藏夹

Article Energy & Fuels

Predicting the Rock Sonic Logs While Drilling by Random Forest and Decision Tree-Based Algorithms

Hany Gamal et al.

Summary: This paper proposes machine learning models for real-time prediction of sonic logs based on drilling data, which is significant for drilling design and rock operations. The developed sonic prediction models, using decision tree and random forest algorithms, perform well in complex lithology and can save costs and time.

JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME (2022)

添加到收藏夹

Article Energy & Fuels

Lithofacies classification integrating conventional approaches and machine learning technique

Jongkook Kim

Summary: This study introduces an integrated approach for lithofacies classification using core samples, wireline logs, and machine learning. It focuses on the Eagle Ford shale and Austin Chalk formations, which present challenges for defining geological heterogeneity. The study defines four lithofacies using a combination of depositional texture, fabric, mineralogy, and other features. A convolutional neural network model is trained using common wireline logs to classify the lithofacies. This data-driven approach provides valuable insights for operators in identifying drilling locations and optimizing completion strategies.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Carbonate / siliciclastic lithofacies classification aided by well-log derivative, volatility and sequence boundary attributes combined with machine learning

David A. Wood

Summary: The study shows that derivative and volatility attributes calculated for well-log versus depth sequences can extract useful features for automated machine-learning lithofacies classification models. These attributes are valuable for wellbores with limited well log data and no cores recovered. The support vector classifier (SVC) model performs the most accurate facies class prediction, achieving a prediction accuracy of 61.2% with a dataset calibrated using core information. The addition of calculated facies boundary influence attributes further improves the SVC's facies class prediction accuracy to 77.2%.

EARTH SCIENCE INFORMATICS (2022)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Understanding Deep Learning (Still) Requires Rethinking Generalization

Chiyuan Zhang et al.

Summary: Despite traditional explanations falling short in justifying the excellent generalization of large neural networks, experiments show that state-of-the-art convolutional networks can easily adapt to random labeling during training, indicating a different mechanism contributing to their strong performance in practice.

COMMUNICATIONS OF THE ACM (2021)

添加到收藏夹

Article Engineering, Petroleum

Data Quality Considerations for Petrophysical Machine-Learning Models

Andrew McDonald et al.

Petrophysics (2021)

添加到收藏夹

Article Energy & Fuels

Petrophysical evaluation of well log data for reservoir characterization in Titas gas field, Bangladesh: a case study

Md. Shaheen Shah et al.

Summary: The petrophysical evaluation of the Titas gas field revealed the presence of three gas-bearing sub-zones in the upper sand group, indicating good reservoir quality with effective porosity ranging from 18.4-18.6% and permeability between 14.11-25.95 mD. The hydrocarbon saturation varied from 48-60%, suggesting a favorable hydrocarbon reservoir with adequate gas reserves based on commercial criteria. The assessment indicated that the Titas reservoir has a higher potential for hydrocarbon accumulation and production.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2021)

添加到收藏夹

Article Energy & Fuels

A Comparison of Machine Learning Algorithms in Predicting Lithofacies: Case Studies from Norway and Kazakhstan

Timur Merembayev et al.

Summary: The study evaluates lithofacies values using machine learning algorithms with data from Kazakhstan and Norway, with Random Forest model scoring the highest among the considered algorithms. The results are consistent with the SHapley Additive exPlanations (SHAP) framework.

ENERGIES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Imputation of missing well log data by random forest and its uncertainty analysis

Runhai Feng et al.

Summary: An innovative approach using machine learning methods is proposed to reconstruct missing well log values, with analysis of input feature importance and exploration of multicollinearity through principal component analysis for training optimization.

COMPUTERS & GEOSCIENCES (2021)

添加到收藏夹

Article Energy & Fuels

Neural network application to petrophysical and lithofacies analysis based on multi-scale data: An integrated study using conventional well log, core and borehole image data

Amer A. Shehata et al.

Summary: The study demonstrates the application of MLP technique in estimating lithofacies and petrophysical parameters for the upper unit of the ARG reservoir. The neural network showed satisfactory prediction for permeability and rock typing in wells without core data, indicating its potential for wider application in uncored wells.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Heat Maps: Perfect Maps for Quick Reading? Comparing Usability of Heat Maps with Different Levels of Generalization

Katarzyna Slomska-Przech et al.

Summary: This study compared the usability of heat maps with different levels of generalization, finding that smaller radii resulted in higher correctness of answers. Despite participants perceiving more generalized maps as easier to use, the actual performance metrics did not align with this perception.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

添加到收藏夹

Article Engineering, Marine

Prediction of Water Saturation from Well Log Data by Machine Learning Algorithms: Boosting and Super Learner

Fahimeh Hadavimoghaddam et al.

Summary: This study successfully predicted water saturation using new machine learning algorithms, avoiding the issues of traditional methods relying on resistivity log data in specific formations. Super Learner and XGBoost were found to produce the most accurate predictions, with Super Learner considered the best among all models.

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2021)

添加到收藏夹

Article Geochemistry & Geophysics

A gradient boosting decision tree algorithm combining synthetic minority oversampling technique for lithology identification

Kaibo Zhou et al.

GEOPHYSICS (2020)

添加到收藏夹

Article Energy & Fuels

An integrated petrophysical and geomechanical characterization of Sembar Shale in the Lower Indus Basin, Pakistan, using well logs and seismic data

Ghulam Mohyuddin Sohail et al.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2020)

添加到收藏夹

Article Chemistry, Multidisciplinary

Machine Learning in Electrofacies Classification and Subsurface Lithology Interpretation: A Rough Set Theory Approach

Touhid Mohammad Hossain et al.

APPLIED SCIENCES-BASEL (2020)

添加到收藏夹

Article Energy & Fuels

Characterization and probabilistic estimation of tight carbonate reservoir properties using quantitative geophysical approach: a case study from a mature gas field in the Middle Indus Basin of Pakistan

Muhammad Zahid Afzal Durrani et al.

JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY (2020)

添加到收藏夹

Article Energy & Fuels

Characterization of secondary reservoir potential via seismic inversion and attribute analysis: A case study

Aamir Ali et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2019)

添加到收藏夹

Article Engineering, Multidisciplinary

Towards Optimization of Boosting Models for Formation Lithology Identification

Yunxin Xie et al.

MATHEMATICAL PROBLEMS IN ENGINEERING (2019)

添加到收藏夹

Article Geochemistry & Geophysics

Seismic facies analysis using machine learning

Thilo Wrona et al.

GEOPHYSICS (2018)

添加到收藏夹

Article Geochemistry & Geophysics

Lithologic mapping using Random Forests applied to geophysical and remote-sensing data: A demonstration study from the Eastern Goldfields of Australia

Stephen Kuhn et al.

GEOPHYSICS (2018)

添加到收藏夹

Article Energy & Fuels

Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances

Yunxin Xie et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2018)

添加到收藏夹

Editorial Material Multidisciplinary Sciences

Classification and interaction in random forests

Danielle Denisko et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2018)

添加到收藏夹

Article Energy & Fuels

Total organic carbon content and total porosity estimation in unconventional resource play using integrated approach through seismic inversion and well logs analysis within the Talhar Shale, Pakistan

Muhammad Fahad Mahmood et al.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2018)

添加到收藏夹

Article Energy & Fuels

Comparison and sensitivity analysis of water saturation models in shaly sandstone reservoirs using well logging data

Shedid A. Shedid et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2017)

添加到收藏夹

Article Geochemistry & Geophysics

An application of seismic attributes analysis for mapping of gas bearing sand zones in the sawan gas field, Pakistan

Tahir Azeem et al.

ACTA GEODAETICA ET GEOPHYSICA (2016)

添加到收藏夹

Article Multidisciplinary Sciences

Area under Precision-Recall Curves for Weighted and Unweighted Data

Jens Keilwagen et al.

PLOS ONE (2014)

添加到收藏夹

Editorial Material Biochemical Research Methods

Heat maps

Nils Gehlenborg et al.

NATURE METHODS (2012)

添加到收藏夹

Article Engineering, Geological

A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs

A. Al-Anazi et al.

ENGINEERING GEOLOGY (2010)

添加到收藏夹

Article Geochemistry & Geophysics

Five-dimensional interpolation: Recovering from acquisition constraints

Daniel Trad

GEOPHYSICS (2009)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Comparison of four approaches to a rock facies classification problem

Martin K. Dubois et al.

COMPUTERS & GEOSCIENCES (2007)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.