Dong-Woo Ryu

Urban ground subsidence is often attributed to water and sewer pipe damage, but this may reflect the ease of identifying such damage rather than a single underlying cause. Many events are multifactorial, and a substantial number remain unexplained. Using only public data, this study compared spatial predisposing and temporal triggering factors for 464 subsidence cases recorded from 2019 to 2025 in Seoul, Busan, Gwangju, and Daejeon. Five spatial variables representing intrinsic susceptibility and four temporal variables, 15-day cumulative precipitation and three seasonal dummy variables, were analyzed on 200-m grids. The case-control analysis comprised 999 Monte Carlo-resampled logistic regressions and nonparametric tests against empirical null distributions to quantify each variable’s contribution. Apparent area under the curve (AUC) values for the full model were 0.747, 0.829, 0.848, and 0.815 for Seoul, Busan, Gwangju, and Daejeon, respectively. Temporal contributions differed by city: precipitation-dominated in Seoul, compound in Busan (season-leaning) and Gwangju, and season-dominated in Daejeon. Despite pipe damage being the dominant recorded cause in Daejeon, the precipitation effect was not significant and summer accounted for a large share of cases, as in the other cities, but spring had an even higher count; the winter reference category contained only one case. The spatial- only model was indistinguishable from the empirical null only in Seoul, and no spatial variable was a consistent risk factor across all cities. Independent cavity-survey data not used in model fitting showed that top-ranked grids contained significantly more cavities than expected by chance in Busan, Gwangju, and Daejeon, whereas Seoul showed no grid-level discrimination. The relative contributions of predisposing and triggering factors were therefore city-specific and not directly transferable across cities. This public-data association framework is intended for comparative screening and hypothesis generation, not causal attribution or operational warning thresholds.

Extreme precipitation is projected to intensify under climate change, yet global and regional climate model outputs are typically provided at resolutions of several to tens of kilometers, limiting their ability to represent localized precipitation structures and extremes. This study aims to develop an ensemble-learning framework for downscaling coarse precipitation fields to high-resolution fields. The proposed framework ensembles a generative adversarial network (GAN), a convolutional encoder–decoder architecture (U-Net), and a diffusion model to avoid single-model bias and to quantify downscaling uncertainty through ensemble spread. High-resolution gridded precipitation data from the Korea Meteorological Administration (KMA) serve as a reference for ensemble learning. Performance is evaluated through a reconstruction experiment in which high-resolution precipitation fields are artificially coarsened, downscaled, and compared with the original data using root mean squared error, bias, and an extreme-focused metric (the 95th percentile). The trained framework is applied to 25 km regional climate projections under Shared Socioeconomic Pathway (SSP) scenarios, generating 1 km precipitation projections for the Republic of Korea through 2100. Results show improved representation of spatial patterns and extreme statistics relative to individual models, while providing uncertainty bounds for projected extremes. Future work will extend the framework so that the downscaled precipitation data are compatible with geological data (e.g., terrain) at tens-of-meters resolution, enabling analyses of how climate risks influence geohazard risks.

Urban geological hazards have increased rapidly in metropolitan areas, with ground subsidence incidents rising five-fold from 69 cases in 2014 to 338 cases in 2018. This study presents a comprehensive quality analysis of borehole data across Seoul Metropolitan Area to enhance urban geotechnical information reliability for underground space safety. A total of 14,016 unique boreholes from 67,054 original records were systematically processed using data from Korea Public Data Portal (data.go.kr) and digital elevation model from the National Geographic Information Institute (ngii. go.kr). Data preprocessing revealed significant quality issues including layer thickness calculation errors and duplicate records, which were systematically corrected. Geotechnical analysis showed Seoul’s subsurface comprises primarily sedimentary layers (26.5%), landfill layers (19.5%), and weathered rock layers (17.5%). Altitude-based analysis confirmed distinct characteristics. High-altitude areas dominated by weathered soil and rock formations, while low-altitude areas predominantly composed of sedimentary deposits, reflecting Seoul’s complex topography from mountainous terrain to alluvial plains. Correlation analysis between Korean geotechnical classifications and Unified Soil Classification System (USCS) standards demonstrated quantitative relationships. Elevation accuracy assessment revealed 75.5% of boreholes exhibited good accuracy within 10 m difference, while 8.5% showed large errors exceeding 50 m. This comprehensive analysis provides essential baseline data for 3D geological modeling, hazard assessment, and underground development planning, supporting smart city-based integrated geospatial platforms for sustainable urban development.

As the market for renewable integration is expected to grow, there is an increasing interest in excavated rock caverns as a solution to overcome the limitations of conventional CAES that use solution-mined salt caverns. One of the major challenges is ensuring the air tightness and pressure resistance performance of lined-rock caverns (LRCs). To address this, we reviewed research on several key aspects, including air tightness, ground uplifting, structural stability of the LRC, excavation damaged zone (EDZ), and thermal-hydraulic-mechanical (T-H-M) interactions. The technical implications of the sensitivity analysis of various design factors that affect the air tightness and stability of LRCs were investigated. We reviewed the reliability-based design of the LRC using a probabilistic approach and evaluated mechanical and hydraulic effects of the EDZ. Additionally, we performed the energy balance analysis based on the T-H-M coupled analysis and determined the optimal operation strategy for the CAES.

Clays in fault zones have low electrical resistivity, making electrical resistivity tomography (ERT) effective for fault investigations. However, traditional ERT inversion methods struggle to find a unique solution and produce unstable results owing to the ill-posed nature of the problem. To address this, a workflow integrating deep-learning (DL) technology with traditional ERT inversion is proposed. First, a deep-learning model named DL-ERT inversion that maps apparent resistivity data to subsurface resistivity models is developed. To create target-oriented training data, we use approximately 150 field borehole data acquired from various survey areas in South Korea. The DL-ERT inversion algorithm is based on a U-Net structure and includes an additional network called the borehole mixer to incorporate borehole information when available. The DL-ERT inversion model is trained in three stages: base model training, borehole mixer training, and fine-tuning. Results showed that the fine-tuning model provided the highest prediction accuracy for all test datasets. Next, the prediction of the trained model is used as the initial model for the deterministic inversion method to predict the final subsurface model. The efficiency and accuracy of the proposed workflow are demonstrated in fault detection using a field data example compared with traditional deterministic inversion.

In recent years, climate change and nationally determined contribution (NDC) policies worldwide have accelerated the transition from fossil energy sources to renewable energy. Consequently, the energy storage system (ESS) sector has emerged as an area of increasing importance in this industry. In particular, compressed air energy storage (CAES), which has a long history of commercialization, is reappraised as a competitive ESS technology with the potential for long-duration and utility-scale storage. The second part of the comprehensive overview aims to provide valuable insights into the planning, design, and construction stages of the CAES system. It describes various geological storage methods for CAES, such as rock salt, aquifers, and depleted gas fields, as well as the potential issues that need to be addressed when deploying each method. Furthermore, it elucidated the isochoric and isobaric storage types and introduced an analytical model for calculating the storage energy density of CAES based on each storage type with sample configurations.

The starting point of the Energy Storage System (ESS) industry in Korea can be found in the K-ESS 2020 strategy announced in 2011. At that time, the strategy laid out government support plans for different ESS technologies, considering the various requirements on the grid. Currently, lithiumbased secondary batteries are dominant in the market. However, in the near future, as the energy mix shifts towards renewable energy sources, a diverse ESS mix will be crucial to maintaining grid stability. Compressed air energy storage (CAES) is an established technology that is now being adapted for utility-scale energy storage with a long duration, as a way to solve the grid stability issues with renewable energy. In this review, we introduce the technical timeline, status, classification, and thermodynamic characteristics of CAES.

This letter studies deep learning-based efficient ground vibration monitoring systems. In this work, artificial intelligence (AI) techniques are adopted to effectively deal with practical issues of data collection and classification. Specifically, we develop a novel energy-efficient data collection scheme by adopting deep Q-network-based reinforcement learning. Also, we propose an enhanced joint recurrent neural network (RNN) and convolutional neural network (CNN) approach for ground vibration classification. The performance of the proposed scheme is evaluated using real-world ground vibration data. The experimental results show that the proposed classification scheme outperforms the best existing scheme with CNN by more than 13% in terms of classification accuracy. It is also shown that the proposed energy management scheme can improve the accuracy of the proposed ground vibration monitoring system by 7.6% over the comparable scheme using equal power allocation.

This paper develops a reliable deep-learning framework to extract latent features from spatial properties and investigates adaptive surrogate estimation to sequester CO₂ into heterogeneous deep saline aquifers. Our deep-learning architecture includes a deep convolutional autoencoder (DCAE) and a fully-convolutional network to not only reduce computational costs but also to extract dimensionality-reduced features to conserve spatial characteristics. The workflow integrates two different spatial properties within a single convolutional system, and it also achieves accurate reconstruction performance. This approach significantly reduces the number of parameters to 4.3% of the original number required, e.g., the number of three-dimensional spatial properties needed decreases from 44,460 to 1920. The successful dimensionality reduction is accomplished by the DCAE system regarding all inputs as image channels from the initial stage of learning using the fully-convolutional network instead of fully-connected layers. The DCAE reconstructs spatial parameters such as permeability and porosity while conserving their statistical values, i.e., their mean and standard deviation, achieving R-squared values of over 0.972 with a mean absolute percentage error of their mean values of less than 1.79%. The adaptive surrogate model using the latent features extracted by DCAE, well operations, and modeling parameters is able to accurately estimate CO₂ sequestration performances. The model shows R-squared values of over 0.892 for testing data not used in training and validation. The DCAE-based surrogate estimation exploits the reliable integration of various spatial data within the fully-convolutional network and allows us to evaluate flow behavior occurring in a subsurface domain.

With the development of machine learning technology, research cases for spatial estimation through machine learning approach (MLA) in addition to the traditional geostatistical techniques are increasing. MLA has the advantage that spatial estimation is possible without stationary hypotheses of data, but it is possible for the prediction results to ignore spatial autocorrelation. In recent studies, it was considered by using a distance matrix instead of raw coordinates. Although, the performance of spatial estimation could be improved through this approach, the computational complexity of MLA increased rapidly as the number of sample points increased. In this study, we developed a method to reduce the computational complexity of MLA while considering spatial autocorrelation. Principal component analysis is applied to it for extracting spatial features and reducing dimension of inputs. To verify the proposed approach, indicator Kriging was used as a benchmark model, and each performance of MLA was compared when using raw coordinates, distance vector, and spatial features extracted from distance vector as inputs. The proposed approach improved the performance compared to previous MLA and showed similar performance compared with Kriging. We confirmed that extracted features have characteristics of rigid classification in spatial estimation; on this basis, we conclude that the model could improve performance.