Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
workflow
Paleokarst caves recognition from seismic response simulation to convolutional neural network detection
Zhu, Donglin (BGP Inc., Colorado School of Mines) | Guo, Rui (BGP Inc.) | Li, Xiangwen (BGP Inc.) | Li, Lei (BGP Inc.) | Zhan, Shifan (BGP Inc.) | Tao, Chunfeng (BGP Inc.) | Gao, Yingnan (BGP Inc.)
ABSTRACT Paleokarst systems, found in carbonate rock formations worldwide, have potential for creating vast reservoirs and facilitating hydrocarbon migration. Thus, studying these systems is essential for the exploration and development of carbonate reservoirs. An approach using convolutional neural networks (CNNs) is introduced to automatically and precisely identify cave features within 3D seismic data. An efficient technique is outlined for generating ample amounts of 3D training data, which is comprised of synthetic seismic data and labels for cave features contained in the seismic data, as a solution to bypass the labeling task for training the CNN. This workflow uses point-spread functions to simulate the cave response in the seismic data and allows us to easily generate realistic and diverse synthetic training data sets with different geologic structures and cave features. By training a CNN with these synthetic data sets, it can effectively learn to detect cave features in field seismic volumes. Upon evaluation using multiple examples, this approach outperforms earlier techniques like seismic attributes and other CNN-based paleokarst characterization methods.
- Geophysics > Seismic Surveying > Seismic Processing (1.00)
- Geophysics > Seismic Surveying > Seismic Modeling (1.00)
- Geophysics > Seismic Surveying > Seismic Interpretation (0.89)
- Geophysics > Seismic Surveying > Surface Seismic Acquisition (0.88)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (24 more...)
ABSTRACT Wind energy is considered to be of great importance for promoting energy transition and achieving net-zero carbon emission. Reliable modeling and monitoring of the near-subsurface geology are crucial for successful wind farm selection, construction, operation, and maintenance. For optimal characterization of shallow seafloor sediments, 2D ultrahigh-resolution (UHR) seismic survey and 1D cone-penetration testing (CPT) often are acquired, processed, interpreted, and integrated for building 3D ground models of essential geotechnical parameters such as friction. Such a task faces multiple challenges, such as limited CPT availability, strong noise contamination in UHR seismic data, and heavy manual efforts for completing the traditional workflows, particularly acoustic impedance inversion. This study accelerates the integration by a semisupervised learning workflow with three highlights. First, it enables geotechnical parameter estimation directly from UHR seismic data without impedance inversion. The second comes from the use of a pretrained feature engine to reduce the risk of overfitting while mapping massive UHR seismic data with sparse CPT measurements through deep learning. More importantly, it allows incorporating other geologic/geophysical information, such as a predefined structural model, to further constrain the machine learning and boost its generalization capability. Its values are validated through applications to the Dutch wind farm zone for estimating four geotechnical parameters, including cone-tip resistance, sleeve friction, pore-water pressure, and the derived friction ratio, in two example scenarios: (1)ย UHR seismic data only and (2)ย UHR seismic data and an 11-layer structural model. The results verify the feasibility of data-driven geotechnical parameter estimation. In addition to the two demonstrated scenarios, our workflow can be further customized for embedding more constraints, e.g.,ย prestack seismic and elastic/static property models, given their availability in a wind farm of interest.
- Geophysics > Seismic Surveying > Seismic Interpretation (1.00)
- Geophysics > Seismic Surveying > Seismic Modeling > Velocity Modeling (0.46)
- Geophysics > Seismic Surveying > Seismic Processing > Seismic Migration (0.34)
ABSTRACT Fault mapping is one of the main tasks of 3D seismic interpretation, and seismic discontinuity attributes are often used to support fault mapping in vertical sections and time slices. The most commonly used fault mapping procedure involves three passes/generations. First, the approximate positions of faults (generation I) on some vertical sections are interpreted manually. Second, the generation I faults are projected on some time slices, and the individual fault traces (generation II) are picked on time slices. Finally, the generation II faults are projected onto the vertical sections and the fault sticks (generation III) are picked in the vertical sections. To speed up the fault mapping process, we use the seismic discontinuity attribute as input to automatically extract the generation III faults in the vertical sections under the generation I and II fault mapping conditions. A quality control (QC) step is essential to improve the accuracy of the automatically generated fault sticks. To reduce the time required for QC, we propose to output the fault sticks on the seismic vertical sections defined by the interpreters. The workflow is applied to a real seismic survey to demonstrate its effectiveness.
Multiple-frequency attribute blending via adaptive uniform manifold approximation and projection and its application on hydrocarbon reservoir delineation
Liu, Naihao (Xiโan Jiaotong University) | Zhang, Zezhou (Xiโan Jiaotong University) | Zhang, Haoran (Xiโan Jiaotong University) | Wang, Zhiguo (Xiโan Jiaotong University) | Gao, Jinghuai (Xiโan Jiaotong University) | Liu, Rongchang (PetroChina Research Institute of Petroleum Exploration and Development (RIPED)) | Zhang, Nan (Yumen Oilfield Company)
ABSTRACT Multifrequency attribute blending is a highly effective tool for characterizing hydrocarbon reservoirs. It begins by extracting multifrequency attributes of seismic data based on time-frequency transformation. Subsequently, a blending algorithm is used to fuse the extracted multifrequency components, thereby obtaining the interpretation results of the interested reservoirs. The red-green-blue (RGB) algorithm is commonly used to fuse the multifrequency components. However, it should be noted that the RGB blending algorithm can only fuse three frequency components, i.e.,ย the low-, middle-, and high-frequency components. Moreover, it can occasionally introduce ambiguities, making it difficult to interpret areas that appear white or yellow. To address these issues, we develop a workflow for multiple-frequency component analysis to delineate hydrocarbon reservoirs. First, we apply the generalized S-transform to obtain the multiple-frequency components of seismic data. Then, the correlation analysis is developed and implemented to select the sensitive frequency components. Finally, we use the uniform manifold approximation and projection, a nonlinear dimension reduction algorithm, to blend the extracted multiple-frequency components and obtain reservoir interpretation results. We apply the suggested workflow to synthetic data and a 3D field data volume to evaluate its effectiveness. Our mathematical analysis demonstrates that the suggested workflow can effectively fuse multiple-frequency components to accurately characterize hydrocarbon reservoirs.
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (1.00)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Sandstone (0.46)
- Oceania > New Zealand > South Island > South Pacific Ocean > Canterbury Basin (0.99)
- Asia > China > Shanxi > Ordos Basin (0.99)
- Asia > China > Shaanxi > Ordos Basin (0.99)
- (5 more...)
ABSTRACT Seismic processing often involves suppressing multiples that are an inherent component of collected seismic data. Elaborate multiple prediction and subtraction schemes such as surface-related multiple removal have become standard in industry workflows. In cases of limited spatial sampling, low signal-to-noise ratio, or conservative subtraction of the predicted multiples, the processed data frequently suffer from residual multiples. To tackle these artifacts in the postmigration domain, practitioners often rely on Radon transform-based algorithms. However, such traditional approaches are both time-consuming and parameter dependent, making them relatively complex. In this work, we present a deep learning-based alternative that provides competitive results, while reducing the complexity of its usage, and, hence simplifying its applicability. Our proposed model demonstrates excellent performance when applied to complex field data, despite it being exclusively trained on synthetic data. Furthermore, extensive experiments show that our method can preserve the inherent characteristics of the data, avoiding undesired oversmoothed results, while removing the multiples from seismic offset or angle gathers. Finally, we conduct an in-depth analysis of the model, where we pinpoint the effects of the main hyperparameters on real data inference, and we probabilistically assess its performance from a Bayesian perspective. In this study, we put particular emphasis on helping the user reveal the inner workings of the neural network and attempt to unbox the model.
- Geophysics > Seismic Surveying > Seismic Processing (1.00)
- Geophysics > Seismic Surveying > Seismic Modeling > Velocity Modeling (0.46)
- North America > United States > Montana > Target Field (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > ร sgard Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Svarte Formation (0.99)
- (18 more...)
ABSTRACT Rockfalls pose a threat to human infrastructure below cliffs. Sensitive and reactive alarm systems are needed for rail traffic safety because small rockfalls () impacting the railroad may cause train derailment. We develop a seismic processing workflow for rockfall early warning, powered by dense arrays deployed along the track. The method is evaluated by dropping rocks from a controlled height and triggering rockfalls on a cliff. We indicate that seismic arrays are highly sensitive to small impacts and are able to detect them, locate them, and estimate their magnitude. The detection can be performed in near real-time with a simple algorithm because small-scale rockfalls produce impulsive waveforms near the impact. Precise localization with matched field processing is able to track the trajectory of a rockfall. Impacts against the steel rails may be recognized by their source signature. The seismic amplitudes are related to the rockfall volume by the Hertz law, which may be used to estimate their volume. These results indicate the potential of seismic-driven near real-time rockfall alarm systems.
- Geophysics > Seismic Surveying > Seismic Processing (1.00)
- Geophysics > Seismic Surveying > Passive Seismic Surveying (0.69)
Paleokarst caves recognition from seismic response simulation to convolutional neural network detection
Zhu, Donglin (BGP Inc., Colorado School of Mines) | Guo, Rui (BGP Inc.) | Li, Xiangwen (BGP Inc.) | Li, Lei (BGP Inc.) | Zhan, Shifan (BGP Inc.) | Tao, Chunfeng (BGP Inc.) | Gao, Yingnan (BGP Inc.)
ABSTRACT Paleokarst systems, found in carbonate rock formations worldwide, have potential for creating vast reservoirs and facilitating hydrocarbon migration. Thus, studying these systems is essential for the exploration and development of carbonate reservoirs. An approach using convolutional neural networks (CNNs) is introduced to automatically and precisely identify cave features within 3D seismic data. An efficient technique is outlined for generating ample amounts of 3D training data, which is comprised of synthetic seismic data and labels for cave features contained in the seismic data, as a solution to bypass the labeling task for training the CNN. This workflow uses point-spread functions to simulate the cave response in the seismic data and allows us to easily generate realistic and diverse synthetic training data sets with different geologic structures and cave features. By training a CNN with these synthetic data sets, it can effectively learn to detect cave features in field seismic volumes. Upon evaluation using multiple examples, this approach outperforms earlier techniques like seismic attributes and other CNN-based paleokarst characterization methods.
- Geophysics > Seismic Surveying > Seismic Processing (1.00)
- Geophysics > Seismic Surveying > Seismic Modeling (1.00)
- Geophysics > Seismic Surveying > Seismic Interpretation (0.89)
- Geophysics > Seismic Surveying > Surface Seismic Acquisition (0.88)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (24 more...)
Multiple-frequency attribute blending via adaptive uniform manifold approximation and projection and its application on hydrocarbon reservoir delineation
Liu, Naihao (Xiโan Jiaotong University) | Zhang, Zezhou (Xiโan Jiaotong University) | Zhang, Haoran (Xiโan Jiaotong University) | Wang, Zhiguo (Xiโan Jiaotong University) | Gao, Jinghuai (Xiโan Jiaotong University) | Liu, Rongchang (PetroChina Research Institute of Petroleum Exploration and Development (RIPED)) | Zhang, Nan (Yumen Oilfield Company)
ABSTRACT Multifrequency attribute blending is a highly effective tool for characterizing hydrocarbon reservoirs. It begins by extracting multifrequency attributes of seismic data based on time-frequency transformation. Subsequently, a blending algorithm is used to fuse the extracted multifrequency components, thereby obtaining the interpretation results of the interested reservoirs. The red-green-blue (RGB) algorithm is commonly used to fuse the multifrequency components. However, it should be noted that the RGB blending algorithm can only fuse three frequency components, i.e.,ย the low-, middle-, and high-frequency components. Moreover, it can occasionally introduce ambiguities, making it difficult to interpret areas that appear white or yellow. To address these issues, we develop a workflow for multiple-frequency component analysis to delineate hydrocarbon reservoirs. First, we apply the generalized S-transform to obtain the multiple-frequency components of seismic data. Then, the correlation analysis is developed and implemented to select the sensitive frequency components. Finally, we use the uniform manifold approximation and projection, a nonlinear dimension reduction algorithm, to blend the extracted multiple-frequency components and obtain reservoir interpretation results. We apply the suggested workflow to synthetic data and a 3D field data volume to evaluate its effectiveness. Our mathematical analysis demonstrates that the suggested workflow can effectively fuse multiple-frequency components to accurately characterize hydrocarbon reservoirs.
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (1.00)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Sandstone (0.46)
- Oceania > New Zealand > South Island > South Pacific Ocean > Canterbury Basin (0.99)
- Asia > China > Shanxi > Ordos Basin (0.99)
- Asia > China > Shaanxi > Ordos Basin (0.99)
- (5 more...)
Robust quantitative estimation of the seismic attenuation from shallow geotechnical borehole VSP data
Nasr, Maher (Institut National de la Recherche Scientifique) | Giroux, Bernard (Institut National de la Recherche Scientifique) | Fabien-Ouellet, Gabriel (รcole Polytechnique Montrรฉal) | Vergniault, Christophe (รlectricitรฉ De France) | Simon, Cyril (รlectricitรฉ De France)
ABSTRACT Estimating seismic attenuation from shallow geotechnical borehole surveys can be a delicate task. Measured data are often collected within the source near-field domain and the classic inverse-distance correction of the geometric spreading (GS) is inappropriate at this scale. We develop a novel approach based on a 3D full-waveform modeling to substitute the inverse-distance correction. It consists of scaling the picked amplitudes using their counterparts obtained from an elastic simulation carried out under conditions mimicking the data acquisition. The seismic attenuation may be inferred from the corrected amplitudes using either a piecewise regression or a ray-based inversion. Numerical experiments involving P- and S-wave synthetic data indicate that our correction better compensates for the GS effect than the inverse-distance correction. For a synthetic example with 5% noise, the Q-factor values derived from amplitude corrected via the proposed approach have a relative error of approximately 10% compared with 40% for the traditional correction. We investigate the effect of the velocity and density uncertainty upon the calculated correction terms and show that our approach is unbiased and stable. Finally, the robustness of our workflow is assessed on a real case study involving a P-wave data set acquired in a geotechnical borehole.
- North America > United States (0.68)
- North America > Canada > Quebec (0.28)
- Geology > Geological Subdiscipline (0.67)
- Geology > Structural Geology > Tectonics > Plate Tectonics > Earthquake (0.47)
- Geology > Rock Type > Sedimentary Rock (0.46)
Abstract In unconventional reservoirs, spacing and stacking directly influence the hydrocarbon resources available to be drained by a given lateral. Hypothetically, these available resources, rock properties and stimulation effectiveness will drive the well performance (i.e., Estimated Ultimate Recovery (EUR)). Characterization of the effectively contacted volume is an important element in understanding the well performance and the depletion efficiency of the intended development. This paper will present a simple but novel way of characterizing a well's drainage volume and demonstrates how this characterization can be applied to improve the understanding of expected well recovery, primary depletion efficiency (i.e., recovery factor), and their relationship with petrophysics and geology. The methodology is proposed as a method to help lead to optimum development and resource economic value for the operator. The proposed method uses the concept of no flow boundaries driven by frac geometry established between wells to define a drainage polygon surrounding neighboring laterals. Incorporating supplementary datasets allows further characterization (i.e., well-log to obtain fluid-in-place distribution). The method provides insights which can be tied back to the well performance. For example, the method shows the importance of geology and petrophysics, reflected through the Original Oil in Place (OOIP) within the drainage volume, driving the well's EUR and recovery factor. Significance/Novelty: Improved reservoir drainage volume and well performance characterization can significantly impact the optimum development plan, maximizing both the exploitation efficiency and value for operators.
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (24 more...)