• Geophysics and Geophysical Exploration
• /
• v.26 no.2
• /
• pp.62-76
• /
• 2023

Recently, machine learning (ML) techniques have been actively applied for seismic trace interpolation. However, because most research is based on training-inference strategies that treat missing trace gather data as a 2D image with a blank area, a sufficient number of fully sampled data are required for training. This study proposes trace interpolation using ML, which uses only irregularly sampled field data, both in training and inference, by modifying the training-inference strategies of trace-based interpolation techniques. In this study, we describe a method for constructing networks that vary depending on the maximum number of consecutive gaps in seismic field data and the training method. To verify the applicability of the proposed method to field data, we applied our method to time-migrated seismic data acquired from the Vincent oilfield in the Exmouth Sub-basin area of Western Australia and compared the results with those of the conventional trace interpolation method. Both methods showed high interpolation performance, as confirmed by quantitative indicators, and the interpolation performance was uniformly good at all frequencies.

• Geophysics and Geophysical Exploration
• /
• v.26 no.2
• /
• pp.77-83
• /
• 2023

In this study, the expressions of magnetic vector and magnetic gradient tensor due to an elliptical cylinder were derived. Igneous intrusions and kimberlite structures are often shaped like elliptical cylinders with axial symmetry and different radii in the strike and perpendicular directions. The expressions of magnetic fields due to this elliptical cylinder were derived from the Poisson relation, which includes the direction of magnetization in the gravity gradient tensor. The magnetic gradient tensor due to an elliptical cylinder is derived by differentiating the magnetic fields. This method involves obtaining a total of 10 triple derivative functions acquired by differentiating the gravitational potential of the elliptical cylinder three times in each axis direction. As the order of differentiation and integration can be exchanged, the magnetic gradient tensor was derived by differentiating the gravitational potential of the elliptical cylinder three times in each direction, followed by integration in the depth direction. The remaining double integration was converted to a complex line integral along the closed boundary curve of the elliptical cylinder in the complex plane. The expressions of the magnetic field and magnetic gradient tensor derived from the complex line integral in the complex plane were shown to be perfectly consistent with those of the circular cylinder derived by the Lipschitz-Hankel integral.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.189-200
• /
• 2022

Ground subsidence on urban roads is a social issue that can lead to human and property damages. Therefore, it is crucial to detect underground cavities in advance and repair them. Underground cavity detection is mainly performed using ground penetrating radar (GPR) surveys. This process is time-consuming, as a massive amount of GPR data needs to be interpreted, and the results vary depending on the skills and subjectivity of experts. To address these problems, researchers have studied automation and quantification techniques for GPR data interpretation, and recent studies have focused on deep learning-based interpretation techniques. In this study, we described a hyperbolic event detection process based on deep learning for GPR data interpretation. To demonstrate this process, we implemented a series of algorithms introduced in the preexisting research step by step. First, a deep learning-based YOLOv3 object detection model was applied to automatically detect hyperbolic signals. Subsequently, only hyperbolic signals were extracted using the column-connection clustering (C3) algorithm. Finally, the horizontal locations of the underground cavities were determined using regression analysis. The hyperbolic event detection using the YOLOv3 object detection technique achieved 84% precision and a recall score of 92% based on AP50. The predicted horizontal locations of the four underground cavities were approximately 0.12 ~ 0.36 m away from their actual locations. Thus, we confirmed that the existing deep learning-based interpretation technique is reliable with regard to detecting the hyperbolic patterns indicating underground cavities.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.203-213
• /
• 2022

To understand an underlying geological structure via seismic imaging, the velocity information of the subsurface medium is crucial. Although the full-waveform inversion (FWI) method is considered useful for estimating subsurface velocity models, 3D FWI needs a lot-of computing power and time. Herein, we compare the calculation efficiency and accuracy of frequency-domain 2D and 3D acoustic FWIs. Thereafter, we demonstrate that the artifacts from 2D approximation can be partially suppressed via frequency-domain 2D FWI by employing diffraction angle filtering (DAF). By applying DAF, which employs only big reflection angle components, the impact of noise and out-of-plane reflections can be reduced. Additionally, it is anticipated that the DAF can create long-wavelength velocity structures for 3D FWI and migration.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.177-188
• /
• 2022

Recently, the application of distributed acoustic sensors (DAS), which can replace geophones and seismometers, has significantly increased along with interest in micro-seismic monitoring technique, which is one of the CO₂ storage monitoring techniques. A significant amount of temporally and spatially continuous data is recorded in a DAS monitoring system, thereby necessitating fast and accurate data processing techniques. Because event detection and seismic phase picking are the most basic data processing techniques, they should be performed on all data. In this study, a machine learning-based P, S wave phase picking algorithm was developed to compensate for the limitations of conventional phase picking algorithms, and it was modified using a transfer learning technique for the application of DAS data consisting of a single component with a low signal-to-noise ratio. Our model was constructed by modifying the convolution-based EQTransformer, which performs well in phase picking, to the ResUNet structure. Not only the global earthquake dataset, STEAD but also the augmented dataset was used as training datasets to enhance the prediction performance on the unseen characteristics of the target dataset. The performance of the developed algorithm was verified using K-net and KiK-net data with characteristics different from the training data. Additionally, after modifying the trained model to suit DAS data using the transfer learning technique, the performance was verified by applying it to the DAS field data measured in the Pohang Janggi basin.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.171-184
• /
• 2023

Machine learning (ML)-based cavity detection using a large amount of survey data obtained from vehicle-mounted ground penetrating radar (GPR) has been actively studied to identify underground cavities. However, only simple image processing techniques have been used for preprocessing the ML input, and many conventional seismic and GPR data processing techniques, which have been used for decades, have not been fully exploited. In this study, based on the idea that a cavity can be identified using diffraction, we applied ML-based diffraction separation to GPR data to increase the accuracy of cavity detection using the YOLO v5 model. The original ML-based seismic diffraction separation technique was modified, and the separated diffraction image was used as the input to train the cavity detection model. The performance of the proposed method was verified using public GPR data released by the Seoul Metropolitan Government. Underground cavities and objects were more accurately detected using separated diffraction images. In the future, the proposed method can be useful in various fields in which GPR surveys are used.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.185-198
• /
• 2023

In marine seismic surveys, the inevitable occurrence of trace gaps in the near offset resulting from geometrical differences between sources and receivers adversely affects subsequent seismic data processing and imaging. The absence of data in the near-offset region hinders accurate seismic imaging. Therefore, reconstructing the missing near-offset information is crucial for mitigating the influence of seismic multiples, particularly in the case of offshore surveys where the impact of multiple reflections is relatively more pronounced. Conventionally, various interpolation methods based on the Radon transform have been proposed to address the issue of the nearoffset data gap. However, these methods have several limitations, leading to the recent emergence of deep-learning (DL)-based approaches as alternatives. In this study, we conducted an in-depth analysis of two representative DL-based studies to scrutinize the challenges that future studies on near-offset interpolation must address. Furthermore, through field data experiments, we precisely analyze the limitations encountered when applying previous DL-based trace interpolation techniques to near-offset situations. Consequently, we suggest that near-offset data gaps must be approached by extrapolation rather than interpolation.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.211-228
• /
• 2023

Ground-penetrating radar (GPR) surveys are commonly used to monitor embankments, which is a nondestructive geophysical method. The results of GPR surveys can be complex, depending on the situation, and data processing and interpretation are subject to expert experiences, potentially resulting in false detection. Additionally, this process is time-intensive. Consequently, various studies have been undertaken to detect cavities in GPR survey data using deep learning methods. Deep-learning-based approaches require abundant data for training, but GPR field survey data are often scarce due to cost and other factors constaining field studies. Therefore, in this study, a deep- learning-based model was developed for embankment GPR survey cavity detection using data augmentation strategies. A dataset was constructed by collecting survey data over several years from the same embankment. A you look only once (YOLO) model, commonly used in computer vision for object detection, was employed for this purpose. By comparing and analyzing various strategies, the optimal data augmentation approach was determined. After initial model development, a stepwise process was employed, including box clustering, transfer learning, self-ensemble, and model ensemble techniques, to enhance the final model performance. The model performance was evaluated, with the results demonstrating its effectiveness in detecting cavities in embankment GPR survey data.

• Geophysics and Geophysical Exploration
• /
• v.27 no.1
• /
• pp.23-36
• /
• 2024

In this study, we analyze the structure of the Korea-Japan Joint Development Zone (JDZ) using gravity, magnetic, and seismic data. Gravity and magnetic data analysis confirmed that the Jeju Basin exhibits low anomalies compared to adjacent areas. We applied the total gradient to the Bouguer anomaly to identify basin boundaries, and computed the analytic signal from the total magnetic anomaly data to enhance the edges of the magnetic anomalies. The Taiwan-Sinzi Belt, exhibits high magnetic anomalies and crosses the center of the JDZ in the northeast-southwest direction; we presume that intrusive rocks are sporadic in the JDZ. The 3D inversion results of the gravity and magnetic data show a strong correlation between magnetic susceptibility and density (i.e. a low-density zone in the Jeju Basin and the Ho Basin, and a high magnetic susceptibility distribution in the Taiwan-Sinzi Belt). Comparison of the density and seismic profiles of the Jeju Basin shows that high densities are associated with sill, horst, and basement highs, whereas low densities are associated with basement low and grabens. These results suggest that interpretations based on seismic, gravity and magnetic data can effectively reveal the subsurface structure of the JDZ.

• Geophysics and Geophysical Exploration
• /
• v.27 no.2
• /
• pp.108-118
• /
• 2024

In this study, expressions for the magnetic field and magnetic gradient tensor due to an elliptical disk were derived. Igneous intrusions and kimberlite structures often have elliptical cylinders with axial symmetry and elliptical cross sections. An elliptical cylinder with varying cross-sectional areas was approximated using stacks of elliptical disks. The magnetic fields of elliptical disks were derived using the Poisson relation, which includes the direction of magnetization in the gravity gradient tensor, as described in a previous study (Rim, 2024). The magnetic gradient tensor due to an elliptical disk is derived by differentiating the magnetic fields, which is equivalent to obtaining ten triple-derivative functions acquired by differentiating the gravitational potential of the elliptical disk three times in each axis direction. Because it is possible to exchange the order of differentiation, the magnetic gradient tensor is derived by differentiating the gravitational potential of the elliptical disk three times, which is then converted into a complex line integral along the closed boundary curve of the elliptical disk in the complex plane. The expressions for the magnetic field and magnetic gradient tensor derived from a complex line integral in complex plane are perfectly consistent with those of the circular disk derived from the Lipschitz-Hankel integral.