Permafrost augmented simulation and forecast using hybrid modeling through spectral neural networks
Abstract
Purpose - Global warming is impacting several crucial Earth systems, including the permafrost. This study investigates the possibility of performing fast and reliable simulation and forecasting of permafrost behavior, addressing a critical gap in the existing literature related to high computation times and energy costs of the simulations. Methodology - A numerical cryohydrogeological study on water and energy transfer in a forested, continuous permafrost site has been conducted using parallel high-performance computing to simulate the permafrost dynamics. The numerical results reasonably replicate the measured soil temperature profiles and the dynamics of infiltrated waters. This work uses a spectral network to achieve a fast, reliable, and stable surrogate model for the simulations to forecast over long periods of time. The surrogate is also enhanced by assimilating experimental data through the development of a hybrid modeling framework. Findings - The proposed approach improves the physical simulation while maintaining the stability of the dynamic model over long periods of time. The results reveal that the proposed hybrid modeling remains stable in integration and forecasting. The final hybrid solution demonstrates a significant improvement in simulation accuracy when tested against a test set of measurements. Predictions of the permafrost behavior in the coming decade are later made based on the CMIP6 climate change scenarios. Originality - This research offers a novel perspective on permafrost modeling that extends the current understanding of its behavior under different climate change scenarios. It shows a higher-than-expected temperature increase of the permafrost. Moreover, the stable forecasting of climate change effects is demonstrated.
Related
- Structured Neural Modeling of Daily Arctic Sea-Ice Concentration Evolution: Physical-Trajectory-Driven Learning and Forecast-Domain Adaptation
- Spectral Element Extension for Direct Simulation of Rotational Ground Motions
- Three-dimensional numerical simulation of ambient seismic noise for arbitrary surface source distributions: application to the study of horizontal-to-vertical spectral ratios and their variability
- Forward Modeling of Spectral-Line Polarization for Weak Magnetic-Field Imaging
- Thermal-state transition pathways and spatial differentiation of permafrost in Northeast China
BibTeX
@misc{ghnatios2026permafrost,
title = {{Permafrost augmented simulation and forecast using hybrid modeling through spectral neural networks}},
author = {Chady Ghnatios and Thibault Xavier and Anatoly S. Prokushkin and Laurent Orgogozo and Francisco Chinesta},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24665},
eprint = {2610.24665},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24665},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Permafrost augmented simulation and forecast using hybrid modeling through spectral neural networks
AU - Chady Ghnatios
AU - Thibault Xavier
AU - Anatoly S. Prokushkin
AU - Laurent Orgogozo
AU - Francisco Chinesta
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.24665
UR - https://arxiv.org/abs/2610.24665
AB - Purpose - Global warming is impacting several crucial Earth systems, including the permafrost. This study investigates the possibility of performing fast and reliable simulation and forecasting of permafrost behavior, addressing a critical gap in the existing literature related to high computation times and energy costs of the simulations. Methodology - A numerical cryohydrogeological study on water and energy transfer in a forested, continuous permafrost site has been conducted using parallel high-performance computing to simulate the permafrost dynamics. The numerical results reasonably replicate the measured soil temperature profiles and the dynamics of infiltrated waters. This work uses a spectral network to achieve a fast, reliable, and stable surrogate model for the simulations to forecast over long periods of time. The surrogate is also enhanced by assimilating experimental data through the development of a hybrid modeling framework. Findings - The proposed approach improves the physical simulation while maintaining the stability of the dynamic model over long periods of time. The results reveal that the proposed hybrid modeling remains stable in integration and forecasting. The final hybrid solution demonstrates a significant improvement in simulation accuracy when tested against a test set of measurements. Predictions of the permafrost behavior in the coming decade are later made based on the CMIP6 climate change scenarios. Originality - This research offers a novel perspective on permafrost modeling that extends the current understanding of its behavior under different climate change scenarios. It shows a higher-than-expected temperature increase of the permafrost. Moreover, the stable forecasting of climate change effects is demonstrated.
ER -