Convolutional neural networks as aid in core lithofacies classification

Lima, Rafael Pires de; Suriamin, Fnu; Marfurt, Kurt J.; Pranter, Matthew J.

doi:10.1190/int-2018-0245.1

Cited by 48 publications

(18 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As with WaveNet, this allows the network to consider context above and below the individual labels when making predictions-however, the sequences could not be as long, since image data is two orders of magnitude larger memory size than CCL per unit depth. Other researchers have used CNN models on carbonate core image data with success (Pires de Lima et al, 2019).…”

Section: Deep Ten For Use With Image Datamentioning

confidence: 99%

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

2021

View full text Add to dashboard Cite

Machine-learning algorithms have been used by geoscientists to infer geologic and physical properties from hydrocarbon exploration and development wells for more than 40 years. These techniques historically utilize digital well-log information, which, like any remotely sensed measurement, have resolution limitations. Core is the only subsurface data that is true to geologic scale and heterogeneity. However, core description and analysis are time-intensive, and therefore most core data are not utilized to their full potential. Quadrant 204 on the United Kingdom Continental Shelf has publicly available open-source core and well log data. This study utilizes this dataset and machine-learning models to predict lithology and facies at the centimeter scale. We selected 12 wells from the Q204 region with well-log and core data from the Schiehallion, Foinaven, Loyal, and Alligin hydrocarbon fields. We interpreted training data from 659 m of core at the sub-centimeter scale, utilizing a lithology-based labeling scheme (five classes) and a depositional-process-based facies labeling scheme (six classes). Utilizing a “color-channel-log” (CCL) that summarizes the core image at each depth interval, our best performing trained model predicts the correct lithology with 69% accuracy (i.e., the predicted lithology output from the model is the same as the interpreted lithology) and predicts individual lithology classes of sandstone and mudstone with over 80% accuracy. The CCL data require less compute power than core image data and generate more accurate results. While the process-based facies labels better characterize turbidites and hybrid-event-bed stratigraphy, the machine-learning based predictions were not as accurate as compared to lithology. In all cases, the standard well-log data cannot accurately predict lithology or facies at the centimeter level. The machine-learning workflow developed for this study can unlock warehouses full of high-resolution data in a multitude of geological settings. The workflow can be applied to other geographic areas and deposit types where large quantities of photographed core material are available. This research establishes an open-source, python-based machine-learning workflow to analyze open-source core image data in a scalable, reproducible way. We anticipate that this study will serve as a baseline for future research and analysis of borehole and core data.

show abstract

Section: Deep Ten For Use With Image Datamentioning

confidence: 99%

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

2021

View full text Add to dashboard Cite

show abstract

“…Using several hundred feet of labeled core from a Mississippian limestone in Oklahoma (data from Suriamin andPranter, 2018 andPires de Lima et al, 2019), we selected a small sample of 285 images from five distinct lithofacies to be classified by the retrained CNN models. Pires de Lima et al (2019) describes how a sliding window is used to generate CNN input data, cropping small sections from a standard core image. We used 10% of the data as the test set and achieved an accuracy of 1.0 using the retrained MobileNetV2 and an accuracy of 0.97 using the retrained InceptionV3 (Table 1).…”

Section: Cnn-assisted Core Descriptionmentioning

confidence: 99%

Untitled

2019

TSR

View full text Add to dashboard Cite

This publication is the result of more than 3 decades of sequence stratigraphy research and application. The objective is to emphasize the most important aspects of Sequence Stratigraphy-a method to guide geologic interpretation of stratigraphic data (seismic profiles, well-logs, cores and outcrops) across scales (from local to regional and global) and depositional environments (from continental to deep marine).The stratigraphic concept of a depositional sequence was introduced to the scientific literature by Peter Vail and his colleagues in the late 70s, building on the shoulders of giants like Chamberlain, Sloss and Wheeler. Since then, several papers compared and contrasted the original sequence-stratigraphic school published in the AAPG Memoir 26 in 1977 with other approaches to subdivide the geologic record, as well as, debating the model validity and impact on the community. At its core, the "model" is really a stratigraphic interpretation method, which was never explicitly documented in the literature. The objective of this book is to present the sequence stratigraphic method in its current form in an attempt to clarify its usage and application in diverse geologic data and depositional environments. This publication is the result of more than 3 decades of sequence stratigraphy research and application. The objective is to emphasize the most important aspects of Sequence Stratigraphy-a method to guide geologic interpretation of stratigraphic data (seismic profiles, well-logs, cores and outcrops) across scales (from local to regional and global) and depositional environments (from continental to deep marine). This book in an 11 x 17 format is designed to be easily used for teaching or self-learning experiences. In the second edition of the "Atlas", the book was divided in 2 separately bound volumes-Exercises and Solutions-to make it easier to use the publication as text book for sequence stratigraphy courses in universities. Also, a new exercise was added and several of the existing exercises went through major updating and editing. Catalog #55020 • Softcover

show abstract

“…The list of studies using transfer learning for the classification of geoscience images is also expanding. Examples include Pires de Lima et al [24], who used transfer learning for the classification of lithofacies using pictures of core data. In contrast to some of the examples cited, Baraboshkin et al [25] reported inferior performance when using transfer learning than when training a CNN model with randomly initialized weights.…”

Section: Introductionmentioning

confidence: 99%

Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification

Lima

Duarte

2021

Geosciences

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNN) are currently the most widely used tool for the classification of images, especially if such images have large within- and small between- group variance. Thus, one of the main factors driving the development of CNN models is the creation of large, labelled computer vision datasets, some containing millions of images. Thanks to transfer learning, a technique that modifies a model trained on a primary task to execute a secondary task, the adaptation of CNN models trained on such large datasets has rapidly gained popularity in many fields of science, geosciences included. However, the trade-off between two main components of the transfer learning methodology for geoscience images is still unclear: the difference between the datasets used in the primary and secondary tasks; and the amount of available data for the primary task itself. We evaluate the performance of CNN models pretrained with different types of image datasets—specifically, dermatology, histology, and raw food—that are fine-tuned to the task of petrographic thin-section image classification. Results show that CNN models pretrained on ImageNet achieve higher accuracy due to the larger number of samples, as well as a larger variability in the samples in ImageNet compared to the other datasets evaluated.

show abstract

Convolutional neural networks as aid in core lithofacies classification

Cited by 48 publications

References 44 publications

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

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

Untitled

Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification

Contact Info

Product

Resources

About