Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes
Abstract
Elastic-wave propagation connects laboratory fracture with earthquakes, raising the prospect of seismic models that reuse waveform structure across physical scales. Here we show that the phase picker PNSN and the multi-task model SeismicXM organize unseen laboratory acoustic emissions around common waveform relations. Their representations agree on 512 held-out records relative to matched random networks. Four earthquake-model families also track displaced laboratory arrivals without fitting target neural weights. Receiver-function classification is accessible to frozen pretrained features, although standardized random features remain competitive. Noise correlations test the extension to continuous propagation outputs: a nonlinear SeismicXM ensemble improves on random topology, while a period-wise median remains more accurate. Waveform interventions and synthetic controls reveal that the observed agreement depends on feature calibration and the waveforms being compared. These results establish convergent waveform organization across distinct seismic training routes and show that cross-scale arrival transfer is already accessible to compact models.
Related
- Repeated evolution of convergent iridescence in closely related species of Morpho butterflies living in sympatry
- CLIVeg: Contrastive Image-Vegetation Alignment for Botany-Aware Earth Observation Representations
- Distinct drivers control trace metal distributions through the Atlantic Ocean
- Distinct functional syndromes and responses to fire history of three Mediterranean woody resprouter species
- Distinct intraseasonal pathways driving rapidly escalating heat extremes in North China and their subseasonal predictability
BibTeX
@misc{yu2026convergent,
title = {{Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes}},
author = {Ziye Yu and Yuqi Cai and Xin Liu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.37462},
eprint = {2609.37462},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37462},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes
AU - Ziye Yu
AU - Yuqi Cai
AU - Xin Liu
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.37462
UR - https://arxiv.org/abs/2609.37462
AB - Elastic-wave propagation connects laboratory fracture with earthquakes, raising the prospect of seismic models that reuse waveform structure across physical scales. Here we show that the phase picker PNSN and the multi-task model SeismicXM organize unseen laboratory acoustic emissions around common waveform relations. Their representations agree on 512 held-out records relative to matched random networks. Four earthquake-model families also track displaced laboratory arrivals without fitting target neural weights. Receiver-function classification is accessible to frozen pretrained features, although standardized random features remain competitive. Noise correlations test the extension to continuous propagation outputs: a nonlinear SeismicXM ensemble improves on random topology, while a period-wise median remains more accurate. Waveform interventions and synthetic controls reveal that the observed agreement depends on feature calibration and the waveforms being compared. These results establish convergent waveform organization across distinct seismic training routes and show that cross-scale arrival transfer is already accessible to compact models.
ER -