Soon Jee Seol

Soon Jee Seol

Auto-generated profile, based on publicly available information

Soon Jee Seol

Hanyang University 1 , Department of Earth Resources and Environmental Engineering, Seoul, South Korea

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2020 in Geophysics
Verified
Journal Article
Closed access
SOSeokmin Oh
Seokmin Oh
KNKyubo Noh
Kyubo Noh
SSSoon Jee Seol
Soon Jee Seol
JBJoongmoo Byun
Joongmoo Byun
Various geophysical data types have advantages for exploring the subsurface, and more reliable exploration can be realized through integration of such data. However, the imaging of physical properties based on deep learning (DL) techniques, which has received considerable attention because of its enormous potential, has generally been performed using only a single type of data. We have developed a cooperative inversion method based on supervised DL for salt delineation. Controlled-source electromagnetic (CSEM) data, which can effectively distinguish a salt body with high electrical resistivity from the surrounding medium, are used as data for cooperative inversion, with high-resolution information derived from seismic data used as the constraint. This approach can entrain seismic information into a fully convolutional network designed to invert CSEM data to reconstruct the resistivity distribution. The inversion network is trained using large synthetic data sets, including the seismic information derived from seismic data as well as CSEM data and resistivity models. A cooperative strategy for reasonable entrainment of seismic information into the inversion network is established based on analysis of the network and kernels of the convolutional layers. The performance of the proposed method is demonstrated through experiments on test data generated for resistivity models for complex salt structures. The trained cooperative inversion network shows improved salt delineation results compared to the independent inversion network, irrespective of noise levels added to the test data, due to restriction of the resistivity model to fit seismic information. Moreover, training with noise-added data decreased the effects of noise on prediction results, similar to the case of adversarial training. We develop the possibility of combining geophysical data with a constraint using DL-based techniques.

28 May 2021 in Geophysics
Verified
Journal Article
Closed access
JPJiho Park
Jiho Park
JCJihun Choi
Jihun Choi
SSSoon Jee Seol
Soon Jee Seol
JBJoongmoo Byun
Joongmoo Byun
YKYoung Kim
Young Kim
Deep-learning (DL) methods have recently been introduced for seismic signal processing. Using DL methods, many researchers have adopted these novel techniques in an attempt to construct a DL model for seismic data reconstruction. The performance of DL-based methods depends heavily on what is learned from the training data. We focus on constructing the DL model that well reflect the features of target data sets. The main goal is to integrate DL with an intuitive data analysis approach that compares similar patterns prior to the DL training stage. We have developed a two-sequential method consisting of two stages: (1) analyzing training and target data sets simultaneously for determining the target-informed training set and (2) training the DL model with this training data set to effectively interpolate the seismic data. Here, we introduce the convolutional autoencoder t-distributed stochastic neighbor embedding (CAE t-SNE) analysis that can provide the insight into the results of interpolation through the analysis of training and target data sets prior to DL model training. Our method was tested with synthetic and field data. Dense seismic gathers (e.g., common-shot gathers) were used as a labeled training data set, and relatively sparse seismic gathers (e.g., common-receiver gathers [CRGs]) were reconstructed in both cases. The reconstructed results and signal-to-noise ratios demonstrated that the training data can be efficiently selected using CAE t-SNE analysis, and the spatial aliasing of CRGs was successfully alleviated by the trained DL model with this training data, which contain target features. These results imply that the data analysis for selecting target-informed training set is very important for successful DL interpolation. In addition, our analysis method can also be applied to investigate the similarities between training and target data sets for other DL-based seismic data reconstruction tasks.

28 January 2016 in Geophysical Journal International
Verified
Journal Article
Closed access
PDF file
KNKyubo Noh
Kyubo Noh
SOSeokmin Oh
Seokmin Oh
SSSoon Jee Seol
Soon Jee Seol
KLKi Ha Lee
Ki Ha Lee
JBJoongmoo Byun
Joongmoo Byun
We present a series of processes for understanding and analysing controlled-source electromagnetic (CSEM) responses for a conductive and permeable earth. To realize the CSEM response, a new 3-D CSEM forward modelling algorithm based on an edge finite element method for both electrically conductive and magnetically permeable heterogeneities is developed. The algorithm shows highly accurate results in validation tests against a semi-analytic solution for stratified earth and an integral form of the scattered field. We describe the vector behaviour of an anomalous magnetic field originating from a conductive and permeable anomaly when the loop sources are deployed over a conductive half-space. The CSEM response of the conductive and permeable anomaly is classified into three effects originating from: conductivity perturbations, permeability perturbations and the coupling of these two effects. The separated individual results and the corresponding integral equation form of the anomalous field help to better understand the physical behaviour. We confirm the characteristic features of the CSEM response from the conductive and permeable anomaly, for example, (1) the general dominance of the induction effect in the out-of-phase response accompanied by a non-negligible magnetization effect from the magnetic anomaly in a conductive half-space and (2) the dominance of near frequency-independent magnetization effects in the in-phase response at relatively low frequencies and change in ruling part of the in-phase response into the induction effect as the frequency increases. We also demonstrate the effect of coupling mode and show that its maximum contribution is limited to a few per cent level of other two modes, induction and magnetization mode, even when the heterogeneity of our model is strong. In our synthetic survey, using examples of land-based profiling surveys of low induction number and intermediate regime, we find that the effect of magnetization can be used as an indicator of the existence of magnetic material. One important point to note from this study is the importance of accurate cancelling-out or estimation of free-space responses, which can mask the magnetic responses to imaging the varying magnetic property.

28 November 2021 in Geophysics
Verified
Journal Article
Closed access
SKSooyoon Kim
Sooyoon Kim
SSSoon Jee Seol
Soon Jee Seol
JBJoongmoo Byun
Joongmoo Byun
SOSeokmin Oh
Seokmin Oh
Diffraction images can be used for modeling reservoir heterogeneities at or below the seismic wavelength scale. However, the extraction of diffractions is challenging because their amplitude is weaker than that of overlapping reflections. Recently, deep-learning (DL) approaches have been used as a powerful tool for diffraction extraction. Most DL approaches use a classification algorithm that classifies pixels in the seismic data as diffraction, reflection, noise, or diffraction with reflection and takes whole values for the classified diffraction pixels. Thus, these DL methods cannot extract diffraction energy from pixels for which diffractions are masked by reflections. We have developed a DL-based diffraction extraction method that preserves the amplitude and phase characteristics of diffractions. Through the systematic generation of a training data set using synthetic modeling based on t-distributed stochastic neighbor embedding analysis, this technique extracts not only faint diffractions but also diffraction tails overlapped by strong reflection events. We also determine that the DL model pretrained with a basic synthetic data set can be applied to seismic field data through transfer learning. Because the diffractions extracted by our method preserve the amplitude and phase, they can be used for velocity model building and high-resolution diffraction imaging.

24 August 2021 in Geophysics
Verified
Journal Article
Closed access
MBMinkyu Bang
Minkyu Bang
SOSeokmin Oh
Seokmin Oh
KNKyubo Noh
Kyubo Noh
SSSoon Jee Seol
Soon Jee Seol
JBJoongmoo Byun
Joongmoo Byun
Conventional interpretation of airborne electromagnetic data has been conducted by solving the inverse problem. However, with recent advances in machine learning (ML) techniques, a 1D deep neural network inversion that predicts a 1D resistivity model using multifrequency vertical magnetic fields and sensor height information at one location has been applied. Nevertheless, since the final interpretation of this 1D approach relies on connecting 1D resistivity models, 1D ML interpretation has low accuracy for the estimation of an isolated anomaly, as in conventional 1D inversion. Thus, we have developed a 2D interpretation technique that can overcome the limitations of 1D interpretation and consider spatial continuity by using a recurrent neural network (RNN). We generate various 2D resistivity models, calculate the ratio of primary and induced secondary magnetic fields of the vertical direction in ppm scale using a vertical magnetic dipole source, and then train the RNN using the resistivity models and the corresponding electromagnetic (EM) responses. To verify the validity of 2D RNN inversion, we apply the trained RNN to synthetic and field data. Through application of the field data, we demonstrate that the design of the training data set is crucial to improve prediction performance in a 2D RNN inversion. In addition, we investigate changes in the RNN inversion results of field data dependent on the data preprocessing. We demonstrate that using two types of data, logarithmic transformed data and linear-scale data, having different patterns of input information can enhance the prediction performance of the EM inversion results.

17 June 2021 in Geophysics
Verified
Journal Article
Closed access
YCYonggyu Choi
Yonggyu Choi
YJYeonghwa Jo
Yeonghwa Jo
SSSoon Jee Seol
Soon Jee Seol
JBJoongmoo Byun
Joongmoo Byun
YKYoung Kim
Young Kim
The resolution of seismic data dictates the ability to identify individual features or details in a given image, and the temporal (vertical) resolution is a function of the frequency content of a signal. To improve thin-bed resolution, broadening of the frequency spectrum is required; this has been one of the major objectives in seismic data processing. Recently, many researchers have proposed and shown the applicability of machine-learning-based resolution enhancement and showed their applicability. However, because the performance of machine learning depends on what the model has learned, output from training data with features different from the target field data may be poor. Thus, we have developed a machine-learning-based spectral enhancement technique considering features of seismic field data. We used a convolutional U-Net model, which preserves the temporal connectivity and resolution of the input data, and we generated numerous synthetic input traces and their corresponding spectrally broadened traces for training the model. A priori information from field data, such as the estimated source wavelet and reflectivity distribution, was considered when generating the input data for complementing the field features. Using synthetic tests and field poststack seismic data examples, we showed that the trained model with a priori information outperforms the models trained without a priori information in terms of the accuracy of enhanced signals. In addition, our new spectral enhancing method was verified through the application to the high-cut-filtered data, and its promising features were evaluated through a comparison with well log data.