Centimeter-Scale Lithology and Facies Prediction in Cored Wells Using Machine Learning

Martín, Timothy; Meyer, Ross G.; Jobe, Zane R.

doi:10.3389/feart.2021.659611

Cited by 22 publications

(12 citation statements)

References 57 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…shin et al, 2021;Jeong et al, 2020;Lauper et al, 2021;Martin et al, 2021;Pires de Lima et al, 2019;Solum et al, 2022;Zhang et al, 2021). Generally, these DNN workflows are used on well curated datasets with standardized core imagery (e.g., Martin et al, 2021). However, the core photographs in this study are more variable (e.g., various cameras, formats, resolutions, and lighting conditions).…”

Section: Core Image Datamentioning

confidence: 99%

“…This makes them particularly useful for practical predictions on real geoscience data, although this algorithm can struggle on sparse data. XGboost has been used with great success for subsurface well-log classification tasks (Bormann et al, 2020;Dev & Eden, 2019;Hall & Hall, 2017;Martin et al, 2021).…”

Section: Xgboostmentioning

confidence: 99%

“…DNNs have been used successfully for geologic image recognition and classification problems (Jeong 2020;Chawshin et al, 2021;Lauper et al, 2021;Martin et al, 2021;Meyer et al, 2020;Falivene et al, 2022). DNN regression has also been used to estimate river sediment yield (Cigizoglu & Alp, 2005).…”

Section: Deep Neural Networkmentioning

confidence: 99%

“…E934 is completely mudstone and thus was not used for the sandstone clustering workflow. shin et al, 2021;Jeong et al, 2020;Lauper et al, 2021;Martin et al, 2021;Pires de Lima et al, 2019;Solum et al, 2022;Zhang et al, 2021). Generally, these DNN workflows are used on well curated datasets with standardized core imagery (e.g., Martin et al, 2021).…”

Section: Core Image Datamentioning

confidence: 99%

“…The coreimage data underperformed compared to other data types in this study, perhaps due to this image-quality variability. Furthermore, while some studies have had success using color to predict lithology (e.g., Martin et al, 2021), color alone is not diagnostic of grain size. For example, the E997 core has dark grey mudstones but also mudstones that are light grey in color, similar to the color of sandstone in this specific core (Fig.…”

Section: Core Image Datamentioning

confidence: 99%

See 4 more Smart Citations

Digitalization of Legacy Datasets and Machine Learning Regression Yields Insights for Reservoir Property Prediction and Submarine-Fan Evolution: A Subsurface Example From the Lewis Shale, Wyoming

Martín

Tadla

Jobe

2022

The Sedimentary Record

Self Cite

View full text Add to dashboard Cite

Machine-learning algorithms have long aided in geologic property prediction from well-log data, but are primarily used to classify lithology, facies, formation, and rock types. However, more detailed properties (e.g., porosity, grain size) that are important for evaluating hydrocarbon exploration and development activities, as well as subsurface geothermal, CO2 sequestration, and hydrological studies have not been a focus of machine-learning predictions. This study focuses on improving machine-learning regression-based workflows for quantitative geological property prediction (porosity, grain size, XRF geochemistry), using a robust dataset from the Dad Sandstone Member of the Lewis Shale in the Green River Basin, Wyoming. Twelve slabbed cores collected from wells targeting turbiditic sandstones and mudstones of the Dad Sandstone member provide 1212.2 ft. of well-log and core data to test the efficacy of five machine-learning models, ranging in complexity from multivariate linear regression to deep neural networks. Our results demonstrate that gradient-boosted decision-tree models (e.g., CatBoost, XGBoost) are flexible in terms of input data completeness, do not require scaled data, and are reliably accurate, with the lowest or second lowest root mean squared error (RMSE) for every test. Deep neural networks, while used commonly for these applications, never achieved lowest error for any of the testing. We also utilize newly collected XRF geochemistry and grain-size data to constrain spatiotemporal sediment routing, sand-mud partitioning, and paleo-oceanographic redox conditions in the Green River Basin. Test-train dataset splitting traditionally uses randomized inter-well data, but a blind well testing strategy is more applicable to most geoscience applications that aim to predict properties of new, unseen well locations. We find that using inter-well training datasets are more optimistic when applied to blind wells, with a median difference of 0.58 RMSE when predicting grain size in phi units. Using these data and results, we establish a baseline workflow for applying machine-learning regression algorithms to core-based reservoir properties from well-log and core-image data. We hope that our findings and open-source code and datasets released with this paper will serve as a baseline for further research to improve geological property prediction for sustainable earth-resource modeling.

show abstract

Section: Core Image Datamentioning

confidence: 99%

Section: Xgboostmentioning

confidence: 99%

Section: Deep Neural Networkmentioning

confidence: 99%

Section: Core Image Datamentioning

confidence: 99%

Section: Core Image Datamentioning

confidence: 99%

See 3 more Smart Citations

Digitalization of Legacy Datasets and Machine Learning Regression Yields Insights for Reservoir Property Prediction and Submarine-Fan Evolution: A Subsurface Example From the Lewis Shale, Wyoming

Martín

Tadla

Jobe

2022

The Sedimentary Record

Self Cite

View full text Add to dashboard Cite

show abstract

A novel approach to classify lithology of reservoir formations using GrowNet and Deep‐Insight with physic‐based feature augmentation

Mousavi,

Hosseini‐Nasab

2024

Energy Science & Engineering

View full text Add to dashboard Cite

Manual interpretation of geophysical logging data can be a tedious and time‐consuming task in the case of the nonlinear behavior of well‐logging signals. This study aims to enhance lithology classification of reservoir formations through advanced machine learning (ML) and deep learning (DL) techniques, introducing and comparing three novel algorithms, GrowNet, Deep‐Insight, and blender, against traditional models like random forest (RF) and support vector machine (SVM). Data from the South and North Viking Graben regions, encompassing 12 lithological facies, was preprocessed through cleaning, normalization, transformation, and imputation of missing values using regression models. The data set was enhanced with physic‐based features and balanced using SMOTE and NearMiss algorithms. Deep‐Insight converted tabular data into images for a convolutional neural network (CNN), significantly improving classification accuracy compared to conventional models such as decision trees (DTs). GrowNet and blender models leveraged hybrid approaches for enhanced performance. These hybrid approaches successfully addressed data imbalance and enhanced model learning, outperforming classic methods. The GrowNet and blender models for lithology classification successfully increased the penalty score and accuracy compared to the FORCE 2020 competition. Additionally, introducing the class prediction error plot visualizes multiclass classification performance more effectively than using a confusion matrix. These novel models in multiclass classification contribute to the petroleum industry by providing more accurate and reliable lithology classification, thereby improving reservoir characterization and exploration efficiency.

show abstract

A Robust Strategy of Geophysical Logging for Predicting Payable Lithofacies to Forecast Sweet Spots Using Digital Intelligence Paradigms in a Heterogeneous Gas Field

Ashraf,

Zhang,

Thanh

et al. 2024

Nat Resour Res

View full text Add to dashboard Cite

Centimeter-Scale Lithology and Facies Prediction in Cored Wells Using Machine Learning

Cited by 22 publications

References 57 publications

Digitalization of Legacy Datasets and Machine Learning Regression Yields Insights for Reservoir Property Prediction and Submarine-Fan Evolution: A Subsurface Example From the Lewis Shale, Wyoming

Digitalization of Legacy Datasets and Machine Learning Regression Yields Insights for Reservoir Property Prediction and Submarine-Fan Evolution: A Subsurface Example From the Lewis Shale, Wyoming

A novel approach to classify lithology of reservoir formations using GrowNet and Deep‐Insight with physic‐based feature augmentation

A Robust Strategy of Geophysical Logging for Predicting Payable Lithofacies to Forecast Sweet Spots Using Digital Intelligence Paradigms in a Heterogeneous Gas Field

Contact Info

Product

Resources

About