Spatiotemporal estimation of groundwater and surface water conditions by integrating deep learning and physics-based watershed models
Water Research X · 2024-05 · 23 · 100228
DOI: 10.1016/j.wroa.2024.100228 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water Research X, 2024-05. Verfasst von Soobin Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Disposal Safety Evaluation R&D Division, Korea Atomic Energy Research Institute (KAERI), 111, Daedeok-daero 989 beon-gil, Yuseong-gu, Daejeon 34057, …. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 124 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ministry of Environment, Korea Institute of Geoscience and Mineral Resources, Korea Environmental Industry and Technology Institute.
Abstract (Originalsprache)
The impacts of climate change on hydrology underscore the urgency of understanding watershed hydrological patterns for sustainable water resource management. The conventional physics-based fully distributed hydrological models are limited due to computational demands, particularly in the case of large-scale watersheds. Deep learning (DL) offers a promising solution for handling large datasets and extracting intricate data relationships. Here, we propose a DL modeling framework, incorporating convolutional neural networks (CNNs) to efficiently replicate physics-based model outputs at high spatial resolution. The goal was to estimate groundwater head and surface water depth in the Sabgyo Stream Watershed, South Korea. The model datasets consisted of input variables, including elevation, land cover, soil type, evapotranspiration, rainfall, and initial hydrological conditions. The initial conditions and target data were obtained from the fully distributed hydrological model HydroGeoSphere (HGS), whereas the other inputs were actual measurements in the field. By optimizing the training sample size, input design, CNN structure, and hyperparameters, we found that CNNs with residual architectures (ResNets) yielded superior performance. The optimal DL model reduces computation time by 45 times compared to the HGS model for monthly hydrological estimations over five years (RMSE 2.35 and 0.29 m for groundwater and surface water, respectively). In addition, our DL framework explored the predictive capabilities of hydrological responses to future climate scenarios. Although the proposed model is cost-effective for hydrological simulations, further enhancements are needed to improve the accuracy of long-term predictions. Ultimately, the proposed DL framework has the potential to facilitate decision-making, particularly in large-scale and complex watersheds.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Disposal Safety Evaluation R&D Division, Korea Atomic Energy Research Institute (KAERI), 111, Daedeok-daero 989 beon-gil, Yuseong-gu, Daejeon 34057, Republic of Korea.
- Korea Institute of Geoscience and Mineral Resources, 124 Gwahak-ro, Yuseong-gu, Daejeon 34132, Republic of Korea.
- Aquanty, Inc., 600 Weber St. N., Unit B, Waterloo, ON N2V 1K4, Canada.
- Department of Earth and Environmental Sciences, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada.
- Department of Environmental Engineering, Pusan National University, Busandaehak-ro 63 beon-gil 2, Geumjeong-gu, Busan 46241, South Korea.
- School of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulju-gun, Ulsan 44919, Republic of Korea.
Förderung
- Ministry of Environment
- Korea Institute of Geoscience and Mineral Resources
- Korea Environmental Industry and Technology Institute
- National Research Foundation of Korea
Zitieren
APA
Kim, S., Lee, E., Hwang, H. T., Pyo, J., Yun, D., Baek, S. S., & Cho, K. H. (2024). Spatiotemporal estimation of groundwater and surface water conditions by integrating deep learning and physics-based watershed models. Water Research X, 23, 100228. https://doi.org/10.1016/j.wroa.2024.100228
Vancouver
Kim S, Lee E, Hwang HT, Pyo J, Yun D, Baek SS, et al. Spatiotemporal estimation of groundwater and surface water conditions by integrating deep learning and physics-based watershed models. Water Research X. 2024;23:100228. doi:10.1016/j.wroa.2024.100228
BibTeX
@article{Kim2024,
author = {Kim, Soobin and Lee, Eunhee and Hwang, Hyoun-Tae and Pyo, JongCheol and Yun, Daeun and Baek, Sang-Soo and Cho, Kyung Hwa},
title = {Spatiotemporal estimation of groundwater and surface water conditions by integrating deep learning and physics-based watershed models},
journal = {Water Research X},
year = {2024},
volume = {23},
pages = {100228},
doi = {10.1016/j.wroa.2024.100228}
}
EUVIMED