Interpreting the Subsurface Lithofacies at High Lithological Resolution by Integrating Information From Well‐Log Data and Rock‐Core Digital Images

Jeong, Jin-A; Park, Eungyu; Emelyanova, Irina; Pervukhina, Marina; Esteban, Lionel; Yun, Seong Taek

doi:10.1029/2019jb018204

Cited by 12 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in existing joint inversion approaches, parameters' relationships in different physical domains are usually depicted by empirical formulas or coupled generalization functions. With the framework of IFWI, we can construct a single neural network to represent physical parameters of interest in multiple domains, the multi‐physics joint inversion can be performed by optimizing this single DNR with complementary constraints from different kinds of geophysical measurements, such as seismic, well‐log(Jeong et al., 2020), gravity (Montesinos et al., 2022), electromagnetic (Blanco‐Montenegro et al., 2008; Yao et al., 2022), ground penetrating radar(Meles et al., 2011), and remote sensing (Sun, Wauthier, et al., 2020). By analyzing this single DNR, further insight into the intrinsic relationships between parameters in different domains may be discovered.…”

Section: Discussionmentioning

confidence: 99%

Implicit Seismic Full Waveform Inversion With Deep Neural Representation

et al. 2023

View full text Add to dashboard Cite

Full waveform inversion (FWI) is arguably the current state‐of‐the‐art amongst methodologies for imaging subsurface structures and physical parameters with seismic data; however, important challenges are faced in its implementation and use. Keys amongst these are (a) building a suitable initial model, from which a local minimum is unlikely to be reached, and (b) availability of tools for evaluation of uncertainty. An algorithm we refer to as implicit full waveform inversion (IFWI), designed using continuously and implicitly defined deep neural representations, appears in principle to address both of these issues. We observe in IFWI, with its random initialization and deep learning optimization, improved convergence relative to standard FWI model initialization and optimization. Models close to the global minimum, capturing relatively high‐resolution subsurface structures, are obtained. In addition, uncertainty analysis, though not solved in IFWI, is meaningfully addressed by approximating Bayesian inference with the addition of dropout neurons. Numerical experimentation with a range of 2D geological models is suggestive that IFWI exhibits a strong capacity for generalization, and is likely well‐suited for multi‐scale joint geophysical inversion.

show abstract

Section: Discussionmentioning

confidence: 99%

Implicit Seismic Full Waveform Inversion With Deep Neural Representation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Для наборов Force-2020, 2016-ml-contest, а также скважин, полученных из ресурсов WAPIMS и NLOG в работах [10,12], присутствовала литологическая зонация. Для скважин ресурсов BGS, NLOG и NOPIMS, которые использовались в работах [11,13,14], авторы получали литологическую зонацию в ручном или полуавтоматическом режиме.…”

Section: обзор задач решаемых со скважинными даннымиunclassified

Overview of Open Well Datasets

Makienko,

Safonov

2023

Proceedings of the 33rd International Conference on Computer Graphics and Vision

View full text Add to dashboard Cite

Recently, the number of studies devoted to the use of machine learning methods in geophysics has been increasing. Examples of such studies include the prediction of rock properties and separation of rock types according to quantitative characteristics. Annotated datasets are required to build machine learning based models. The purpose of this paper is to review open labeled well datasets and some research used these datasets. Datasets from competitions in machine learning for geophysical problems are analyzed, as well as other publicly available sources of open well data. The paper considers datasets containing well logging, rock images, laboratory research results, as well as labeled zonation by lithotypes.

show abstract

“…For studies that use both core and well-log derived properties for analysis, typically a core-to-log depth shift is performed to correct wireline stretch and core loss/breakage during drilling operations (Fontana et al, 2010;Jeong et al, 2020). In this study, we compared 3 different strategies: no offset, a qualitative offset, and a quantitative offset.…”

Section: Core To Log Offsetmentioning

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%

See 1 more Smart Citation

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

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

Interpreting the Subsurface Lithofacies at High Lithological Resolution by Integrating Information From Well‐Log Data and Rock‐Core Digital Images

Cited by 12 publications

References 48 publications

Implicit Seismic Full Waveform Inversion With Deep Neural Representation

Implicit Seismic Full Waveform Inversion With Deep Neural Representation

Overview of Open Well Datasets

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

Contact Info

Product

Resources

About