Does High Signal-to-Noise Ratio Identify Better Training Data for Seismic Deep Learning?
Abstract
Hard signal-to-noise ratio (SNR) screening removes weak seismic records, but does retaining clearer waveforms improve learning enough to compensate for the discarded data? We test this question in phase picking and ambient-noise dispersion, first matching training counts and then restoring the full eligible dispersion pool at fixed compute. Phase-picking screening gave no consistent unfiltered-test benefit under fine-tuning or random initialization, including a control matched on distance and phase composition. Dispersion screening increased error at the original five-epoch endpoint but improved on an equally sized unscreened set after longer training. Retaining all 29,788 eligible fit paths instead of 9,929 randomly sampled paths reduced unfiltered-test error by 3.0% across three seeds at the same update budget. Full-available and strict-SNR training then had similar mean errors, 0.0405 and 0.0406 km s−1, with mixed seed-paired ordering; strict training retained a 9.9% advantage on the SNR-selected test. In two-day monitoring, SNR regulated pick streams but event recovery depended on its measurement definition. High SNR did not reliably identify better training data: gains depended on the task, training schedule, and test domain, and fixed-count comparisons omitted the benefit of retaining additional valid examples.
Related
- Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes
- Seismic Precursors to the Blatten, Switzerland Landslide Revealed by Unsupervised Machine Learning
- Physical Cross-Modal Masked Autoencoding for Seismic-to-Well Representation Learning
- A Review of Deep-learning-based Seismic Data Denoising and Its Promising Paradigm Shift to Foundation Models
- GeoFWI3D: Large-scale 3D Velocity Model Dataset for Deep Learning-assisted Seismic Imaging
BibTeX
@misc{yu2026does,
title = {{Does High Signal-to-Noise Ratio Identify Better Training Data for Seismic Deep Learning?}},
author = {Ziye Yu and Xin Liu and Yuqi Cai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.37463},
eprint = {2609.37463},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37463},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Does High Signal-to-Noise Ratio Identify Better Training Data for Seismic Deep Learning?
AU - Ziye Yu
AU - Xin Liu
AU - Yuqi Cai
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.37463
UR - https://arxiv.org/abs/2609.37463
AB - Hard signal-to-noise ratio (SNR) screening removes weak seismic records, but does retaining clearer waveforms improve learning enough to compensate for the discarded data? We test this question in phase picking and ambient-noise dispersion, first matching training counts and then restoring the full eligible dispersion pool at fixed compute. Phase-picking screening gave no consistent unfiltered-test benefit under fine-tuning or random initialization, including a control matched on distance and phase composition. Dispersion screening increased error at the original five-epoch endpoint but improved on an equally sized unscreened set after longer training. Retaining all 29,788 eligible fit paths instead of 9,929 randomly sampled paths reduced unfiltered-test error by 3.0% across three seeds at the same update budget. Full-available and strict-SNR training then had similar mean errors, 0.0405 and 0.0406 km s^−1, with mixed seed-paired ordering; strict training retained a 9.9% advantage on the SNR-selected test. In two-day monitoring, SNR regulated pick streams but event recovery depended on its measurement definition. High SNR did not reliably identify better training data: gains depended on the task, training schedule, and test domain, and fixed-count comparisons omitted the benefit of retaining additional valid examples.
ER -