271 Geologic Energy Resources and Storage for Now and the Future (Posters)

This session seeks contributions describing research on multi-resource development efforts, non-traditional uses of fossil fuels, natural hydrogen and helium, CCUS, enhanced geothermal energy, storage of hydrogen and compressed air, and enhanced methane recovery and carbon storage in coal.

Wednesday, 22 October 2025
8:00 AM - 5:30 PM
HBGCC, Hall 1

Long-Term Groundwater Level Prediction Under Climate Change: A Nationwide Hydrogeological Monitoring Approach

Paper number: 271-11
Program: Technical Sessions
Time: 8:00 AM – 8:00 AM

Authors

Abstract

Groundwater level is one of the most critical parameters for assessing the safety of deep geological repositories for high level radioactive waste. It influences hydraulic gradients, water pressure, and redox states, all of which directly affect radionuclide migration and long term geochemical stability within the host formation. Capturing the spatial and temporal variability of groundwater levels is therefore essential for reliable site evaluation and for designing robust monitoring networks. This study introduces a predictive framework for the standardized groundwater level index (SGI) across South Korea, employing a convolutional long short term memory (ConvLSTM) neural network. The model integrates standardized precipitation indices (SPI) with different accumulation periods to represent both short and long term hydrological conditions, enabling projection of SGI patterns under future climate change scenarios extending to 2100. Model outputs reveal pronounced regional contrasts: short term drought indicators (SPI2, SPI3) dominate in most inland areas, whereas longer term indices (SPI12) exert stronger influence in an island region. These variations are consistent with differences in land use and hydrogeological settings. Scenario based predictions using Shared Socioeconomic Pathways (SSP) indicate that SSP2 4.5 and SSP5 8.5 lead to an increase in high SGI values and a reduction in low SGI occurrences over time, while SSP1 2.6 maintains distributions similar to current conditions. The findings demonstrate the value of machine learning based SGI forecasting for repository programs, offering a means to anticipate long term groundwater behavior, support site screening, and optimize monitoring strategies under changing climatic conditions.

Acknowledgements: This work was supported by Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (Ministry of Trade, Industry and Energy, MOTIE) (RS-2024-00419806). This work was supported by the Institute for Korea Spent Nuclear Fuel (iKSNF) and National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT, MSIT)(No.2021M2E1A1085186).  

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-412849

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.