Is Seismic Forecasting Possible with Physics-based AI?
Abstract
Slow slip events within subduction zones offer a unique window into earthquake prediction. The subducting plate drives dehydration reactions in the fault, causing cyclical slip and observable surface displacements. Earthquake footprints can then be identified in these displacement series through coupling the multi-physics governing the subduction process with regional seismic activity. However, data noise and traditional filtering methods obscure the underlying mechanisms. Here, we alleviate this constraint with our physics-based attractor. By accounting for the physics of subduction paired with AI-assisted manifold detection, we are able to predict an earthquake in New Zealand's Hikurangi trench one week early. Additionally, predictability limits extend to 5-6 weeks with decadal repeatability, pointing to the fundamental determinism of the suggested mechanism through which physics-based seismic forecasting is possible.
Related
- A Likelihood‐Free Framework for Seismic Forecasting Models: Application to Incomplete ETAS Model via Simulation‐Based Inference
- FAST-ML: A Hybrid Physics-Machine Learning Framework for Tropical Cyclone Intensity Forecasting
- Fusing physics and AI enhances accuracy and diagnostic capabilities in air quality forecasting.
- Dual-constraint physics-informed LSTM-XAJ hybrid model for 10-minute flood forecasting in small-to-medium basins: A case of the Xiang River Basin, China
- PhyTGNet: A Physics‐Prior‐Guided Interpretable Forecasting Method for Thunderstorm Gusts in the Beijing–Tianjin–Hebei Region
BibTeX
@misc{keane2026seismic,
title = {{Is Seismic Forecasting Possible with Physics-based AI?}},
author = {Victoria Keane and Manolis Veveakis and Thomas Poulet},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.30861},
eprint = {2608.30861},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.30861},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Is Seismic Forecasting Possible with Physics-based AI?
AU - Victoria Keane
AU - Manolis Veveakis
AU - Thomas Poulet
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.30861
UR - https://arxiv.org/abs/2608.30861
AB - Slow slip events within subduction zones offer a unique window into earthquake prediction. The subducting plate drives dehydration reactions in the fault, causing cyclical slip and observable surface displacements. Earthquake footprints can then be identified in these displacement series through coupling the multi-physics governing the subduction process with regional seismic activity. However, data noise and traditional filtering methods obscure the underlying mechanisms. Here, we alleviate this constraint with our physics-based attractor. By accounting for the physics of subduction paired with AI-assisted manifold detection, we are able to predict an earthquake in New Zealand's Hikurangi trench one week early. Additionally, predictability limits extend to 5-6 weeks with decadal repeatability, pointing to the fundamental determinism of the suggested mechanism through which physics-based seismic forecasting is possible.
ER -