Yongchae Cho

As demand for large‐scale seismic data interpretation tasks increases, machine learning‐based horizon autotracking methods have gained attention in the geological and geophysical fields. Although such methods have demonstrated time‐ and cost‐efficiency in large‐scale data interpretation, studies on the expansion of interpreted horizons into the reservoir characterization process are relatively limited. Hence, a reservoir characterization process that can incorporate the machine learning‐interpreted horizons and their structural uncertainties into the reservoir uncertainty assessment is necessary for an efficient reservoir modelling process. The proposed workflow consists of various modelling processes, including horizon construction where machine learning‐interpreted horizons are used instead of manually interpreted horizons, facies modelling and petrophysical modelling. The modelling algorithms are based on stochastic methods: sequential indicator simulation for facies models and Gaussian random function simulation for petrophysical properties. Each modelling process incorporates variables such as variogram parameters, facies ratios and modified porosity values. The results show promising performance in incorporating machine learning‐interpreted horizons into the uncertainty quantification process and analysing their impact by capturing the influence of structural uncertainties of horizons in the final reservoir pore volume.

We propose a machine learning-based method that estimates a three-dimensional (3D) seismic volume from irregularly placed two-dimensional (2D) seismic lines, addressing the challenges regarding the local disturbances contained within 2D lines (e.g., seismic misties and discrepant seismic characteristics across lines). To overcome these challenges, we employ the vector-quantized variational autoencoder (VQ-VAE) framework, which effectively captures global structures in data. Through appropriate data augmentation processes, the network is trained with diverse samples despite the limited availability of seismic volumes, enhancing its generality for estimating 3D structures. Specifically, numerous training samples are generated from five seismic volumes with various augmentation methods, including perspective transform along the horizontal axes, horizontal flipping, polarity reversal, and random signal-level perturbations (e.g., smooth gain functions and convolution filters). In addition, a two-stage training process, into which randomly generated convolution filters are incorporated, further strengthens the robustness to local disturbances. We validate and evaluate the trained network on unseen 3D volumes using L₁ and 3D structural similarity index measure metrics, demonstrated with numerical examples. The validation confirms that 1) the proposed method successfully reconstructs subsurface geological structures from 2D lines and 2) random filtering enhances performance for inconsistent lines. In addition, we test the applicability of the proposed method with actual 2D lines acquired from the Jeju Basin, which have various line intervals ranging from 0.5 km to 4 km. The testing results show that the network effectively manages intervals up to 2 km but struggles to estimate structures beyond straightforward horizontal layers at intervals of 4 km.

서 론 탄성파 탐사의 궁극적인 목표는 지하의 구조와 물성을 탐사를 통해 간접적으로 파악하여 석유•가스 생산이나 이 산화탄소 지중저장 등의 성공 확률을 높이는 것이다. 구조 는 주로 구조보정을 통한 영상화로 파악하거나, 물성 역산 을 통해 추정한다. 역산을 통해 추정한 물성은 암상 분류 (lithofacies classfication

Quantum computers utilize the principles of quantum mechanics to process information and have efficient computational costs compared with central-processing-unit-based computers for specific algorithms. The most general-purpose quantum computer, the quantum gate computer, uses quantum gates corresponding to gates made of transistors as computational tools. Quantum annealers, however, utilize quantum tunneling, based on the theory that particles can pass through barriers higher than the particle energy owing to the particle waveform, and it is specialized in performing mathematical optimizations. This study investigated the theoretical possibility of applying seismic exploration data processing techniques and subsurface structure imaging algorithms using quantum computers. However, this study also reveals the limitations of these methods. The results suggest that quantum computers have the potential to perform numerical modeling, seismic data preprocessing, and data enhancement in a time-efficient manner.

In this study, we analyzed the characteristics of moving vehicle-induced sources and simulated quasi-static distributed acoustic sensing (DAS) signals over an arbitrary 2D terrain using the Flamant-Boussinesq approximation. The DAS response was modeled based on strain and strain rate values, taking into account arbitrarily curved fiber optic layouts. Various vehicle movement scenarios were assessed and the effects of variables such as vehicle speed, gauge length, channel spacing, and wheel spacing were analyzed. This study is expected to contribute to the enhancement of traffic monitoring technology by providing insights into vehicle-induced source characteristics and to the advancement of intelligent transportation systems.

The shallow region of a 3D seismic data set acquired in Yeongil Bay, Pohang, exhibits various interesting features. In particular, the region exhibits bright circular seismic amplitude anomalies. These anomalies are located in a topographic low of the seismic data surrounding the structural high from the northern, southern, and eastern ends. The anomalies are confined to a temporal region of the seismic data and exhibit a concave-down appearance when viewed in cross section. Although such bright seismic amplitudes can often be a direct indicator of hydrocarbon presence, to avoid misinterpreting this feature, multiattribute analyses are applied to the data. The abnormal structural characteristics are further examined by applying a geometric attribute analysis to emphasize the coherency of the signals within the region of anomaly distribution. We also apply a physical attribute analysis to determine that these anomalies can result from changes in lithology, most likely a sandy formation, which can be inferred from a stratigraphic analysis of the Pohang Basin. Recent findings suggest the possibility of hydrocarbon presence in the study region, but we cannot rule out other possibilities without well-log data to specify the physical characteristics.