Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
A Machine-Learning Based Workflow for Predicting Overpressure in a Stiff Dolomitic Formation
Nivlet, Philippe (EXPEC Advanced Research Center, Saudi Aramco) | Yang, Yunlai (EXPEC Advanced Research Center, Saudi Aramco) | Magana-Mora, Arturo (EXPEC Advanced Research Center, Saudi Aramco) | Abughaban, Mahmoud (EXPEC Advanced Research Center, Saudi Aramco) | Abegunde, Ayodeji (Drilling Technical Department, Saudi Aramco)
Abstract Overpressure refers to the abnormally high subsurface pressure that may exceed hydrostatic pressure at a given depth. Its characterization is an important part of subsurface characterization as it allows to complete drilling operations in a safe and optimal way. In dolomitic formations, however, the prediction of such overpressure is especially challenging because of (1) the high degree of lateral variability of the formations, (2) the limited effect of overpressure on tight rocks elastic parameters, and (3) the complexity of physical processes involved to form overpressure. In addition to these factors, existing experimental models generally used to relate elastic parameters to pressure are often not well calibrated to carbonate rocks. The alternative to existing purely physical approaches is a data-driven model that leverages data from offset wells. We show that due to the complexity of the characterization question to be solved, an end-to-end machine learning based approach is deemed to fail. Instead of a fully automated approach, we show a semi-supervised workflow that integrates seismic, geological data, and overpressure observations from previously drilled wells to map overpressure regions. Attribute maps are first extracted from a 3D seismic data set in an overpressured geological formation of interest. An auto-encoder is then used to learn a more compact representation of data, resulting in a reduced number of latent attributes. Then, a hand-tailored semi-supervised approach is applied, which is a combination of clustering method (here based on DBSCAN algorithm) and Bayesian classification to determine overpressure risk degree (no risk, mild, or high risk). The approach described in this study is compared to direct end-to-end models and significantly outperforms them with an error on a blind well prediction of around 25%. The overpressure probability maps resulting from the models can be used later for the optimization of drilling processes and to reduce drilling hazards.
- Geophysics > Seismic Surveying > Seismic Interpretation (0.70)
- Geophysics > Seismic Surveying > Surface Seismic Acquisition (0.54)
- Geophysics > Seismic Surveying > Seismic Processing (0.46)
- Geophysics > Seismic Surveying > Seismic Modeling (0.46)
- Europe > Austria > Upper Austria > Molasse Basin (0.99)
- Europe > Austria > Lower Austria > Molasse Basin (0.99)
Abstract Accurate delineation of geologic facies and determination of live fluids from seismic reflection data is crucial for reservoir characterization during petroleum exploration. Facies classification or fluid identification is often done manually by an experienced interpreter, which makes this process subjective, laborious, and time-consuming. Several machine-learning models have been proposed to automate multiclass facies segmentation, but significant practical challenges (e.g., limited scope of labels for training purposes, skewed data distribution, inefficient performance evaluation metrics, etc) still remain. We present supervised and semisupervised Bayesian deep-learning methodologies to improve analysis of seismic facies depending on the scope of the labeled data. The developed networks reliably predict facies distribution using seismic reflection data and estimate the corresponding uncertainty. Therefore, they provide more consistent and meaningful information for seismic interpretation than commonly used deterministic approaches. We apply the proposed deep-learning models to field data from the North Sea to demonstrate the generalized-prediction capabilities of our methodology. In the case of sufficient availability of manually interpreted labels (or facies), the supervised learning model accurately recovers the facies distribution. When the amount of the interpreted labels is limited, we efficiently apply the semisupervised algorithm to avoid overfitting.
- North America > United States (0.93)
- Europe > United Kingdom > North Sea (0.49)
- Europe > Netherlands > North Sea (0.49)
- (2 more...)
- Geology > Geological Subdiscipline (1.00)
- Geology > Rock Type > Sedimentary Rock (0.69)
- North America > Mexico > Veracruz > Veracruz Basin (0.99)
- North America > Mexico > Gulf of Mexico > Veracruz Basin (0.99)
- Europe > United Kingdom > North Sea > Southern North Sea > Southern Gas Basin (0.99)
- (3 more...)
- Reservoir Description and Dynamics > Reservoir Characterization > Seismic processing and interpretation (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Neural networks (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
ABSTRACT Machine-learning (ML) applications in seismic exploration are growing faster than applications in other industry fields, mainly due to the large amount of acquired data for the exploration industry. The ML algorithms are constantly being implemented for almost all the steps involved in seismic processing and interpretation workflow, mainly for automation, processing time reduction, efficiency, and in some cases for improving the results. We carry out a literature-based analysis of existing ML-based seismic processing and interpretation published in SEG and EAGE literature repositories and derive a detailed overview of the main ML thrusts in different seismic applications. For each publication, we extract various metadata about ML implementations and performances. The data indicate that current ML implementations in seismic exploration are focused on individual tasks rather than a disruptive change in processing and interpretation workflows. The metadata indicate that the main targets of ML applications for seismic processing are denoising, velocity model building, and first-break picking, whereas, for seismic interpretation, they are fault detection, lithofacies classification, and geobody identification. Through the metadata available in publications, we obtain indices related to computational power efficiency, data preparation simplicity, real data test rate of the ML model, diversity of ML methods, etc., and we use them to approximate the level of efficiency, effectivity, and applicability of the current ML-based seismic processing and interpretation tasks. The indices of ML-based processing tasks indicate that current ML-based denoising and frequency extrapolation have higher efficiency, whereas ML-based quality control is more effective and applicable compared with other processing tasks. Among the interpretation tasks, ML-based impedance inversion indicates high efficiency, whereas high effectivity is depicted for fault detection. ML-based lithofacies classification, stratigraphic sequence identification, and petro/rock properties inversion exhibit high applicability among other interpretation tasks.
- North America > United States (1.00)
- Europe (1.00)
- Geology > Rock Type > Sedimentary Rock (0.68)
- Geology > Geological Subdiscipline > Geomechanics (0.66)
- Geology > Geological Subdiscipline > Stratigraphy (0.48)
- Geophysics > Seismic Surveying > Seismic Modeling > Velocity Modeling > Seismic Inversion (1.00)
- Geophysics > Seismic Surveying > Seismic Interpretation (1.00)
- Geophysics > Seismic Surveying > Passive Seismic Surveying > Microseismic Surveying (1.00)
- Geophysics > Seismic Surveying > Seismic Processing > Seismic Migration (0.92)
ABSTRACT Machine-learning (ML) applications in seismic exploration are growing faster than applications in other industry fields, mainly due to the large amount of acquired data for the exploration industry. The ML algorithms are constantly being implemented for almost all the steps involved in seismic processing and interpretation workflow, mainly for automation, processing time reduction, efficiency, and in some cases for improving the results. We carry out a literature-based analysis of existing ML-based seismic processing and interpretation published in SEG and EAGE literature repositories and derive a detailed overview of the main ML thrusts in different seismic applications. For each publication, we extract various metadata about ML implementations and performances. The data indicate that current ML implementations in seismic exploration are focused on individual tasks rather than a disruptive change in processing and interpretation workflows. The metadata indicate that the main targets of ML applications for seismic processing are denoising, velocity model building, and first-break picking, whereas, for seismic interpretation, they are fault detection, lithofacies classification, and geobody identification. Through the metadata available in publications, we obtain indices related to computational power efficiency, data preparation simplicity, real data test rate of the ML model, diversity of ML methods, etc., and we use them to approximate the level of efficiency, effectivity, and applicability of the current ML-based seismic processing and interpretation tasks. The indices of ML-based processing tasks indicate that current ML-based denoising and frequency extrapolation have higher efficiency, whereas ML-based quality control is more effective and applicable compared with other processing tasks. Among the interpretation tasks, ML-based impedance inversion indicates high efficiency, whereas high effectivity is depicted for fault detection. ML-based lithofacies classification, stratigraphic sequence identification, and petro/rock properties inversion exhibit high applicability among other interpretation tasks.
- North America > United States (1.00)
- Europe (1.00)
- Geology > Rock Type > Sedimentary Rock (0.68)
- Geology > Geological Subdiscipline > Geomechanics (0.66)
- Geology > Geological Subdiscipline > Stratigraphy (0.48)
- Geophysics > Seismic Surveying > Seismic Modeling > Velocity Modeling > Seismic Inversion (1.00)
- Geophysics > Seismic Surveying > Seismic Interpretation (1.00)
- Geophysics > Seismic Surveying > Passive Seismic Surveying > Microseismic Surveying (1.00)
- Geophysics > Seismic Surveying > Seismic Processing > Seismic Migration (0.92)
Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks
Liu, Mingliang (Aramco Research Center — Aramco Services Company, University of Wyoming) | Jervis, Michael (EXPEC ARC) | Li, Weichang (Aramco Research Center — Aramco Services Company) | Nivlet, Philippe (EXPEC ARC)
ABSTRACT Mapping of seismic and lithologic facies from 3D reflection seismic data plays a key role in depositional environment analysis and reservoir characterization during hydrocarbon exploration and development. Although a variety of machine-learning methods have been developed to speed up interpretation and improve prediction accuracy, there still exist significant challenges in 3D multiclass seismic facies classification in practice. Some of these limitations include complex data representation, limited training data with labels, imbalanced facies class distribution, and lack of rigorous performance evaluation metrics. To overcome these challenges, we have developed a supervised convolutional neural network (CNN) and a semisupervised generative adversarial network (GAN) for 3D seismic facies classification in situations with sufficient and limited well data, respectively. The proposed models can predict 3D facies distribution based on actual well log data and core analysis, or other prior geologic knowledge. Therefore, they provide a more consistent and meaningful implication to seismic interpretation than commonly used unsupervised approaches. The two deep neural networks have been tested successfully on a realistic synthetic case based on an existing reservoir and a real case study of the F3 seismic data from the Dutch sector of the North Sea. The prediction results show that, with relatively abundant well data, the supervised CNN-based learning method has a good ability in feature learning from seismic data and accurately recovering the 3D facies model, whereas the semisupervised GAN is effective in avoiding overfitting in the case of extremely limited well data. The latter seems, therefore, particularly adapted to exploration or early field development stages in which labeled data from wells are still very scarce.
- Europe > Netherlands (0.68)
- North America > United States > Texas (0.68)
- Asia > Middle East > Saudi Arabia (0.46)
- Geophysics > Seismic Surveying > Seismic Processing (1.00)
- Geophysics > Seismic Surveying > Seismic Interpretation (1.00)
- Oceania > New Zealand > North Island > Taranaki Basin (0.99)
- North America > United States > Texas > Fort Worth Basin > Barnett Shale Formation (0.99)
- North America > Mexico > Veracruz > Veracruz Basin (0.99)
- North America > Mexico > Gulf of Mexico > Veracruz Basin (0.99)