REVIEW 4 cited by
SeisLM: a Foundation Model for Seismic Waveforms
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
SeisLM: a Foundation Model for Seismic Waveforms
read the original abstract
We introduce the Seismic Language Model (SeisLM), a foundational model designed to analyze seismic waveforms -- signals generated by Earth's vibrations such as the ones originating from earthquakes. SeisLM is pretrained on a large collection of open-source seismic datasets using a self-supervised contrastive loss, akin to BERT in language modeling. This approach allows the model to learn general seismic waveform patterns from unlabeled data without being tied to specific downstream tasks. When fine-tuned, SeisLM excels in seismological tasks like event detection, phase-picking, onset time regression, and foreshock-aftershock classification. The code has been made publicly available on https://github.com/liutianlin0121/seisLM.
Forward citations
Cited by 4 Pith papers
-
GNSS-FM: A Self-Supervised Foundation Model for Daily GNSS Displacement Time Series
GNSS-FM is a self-supervised foundation model for GNSS displacement time series that outperforms task-specific baselines on 90-day forecasting and seismic step localization after pretraining on global station data.
-
IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data
Self-supervised latent prediction on raw complex ultrasound channel data reduces the labeled data needed for sound-speed estimation by roughly 3-4x in simulation, reaching 15.6 m/s error with 10,000 labels.
-
Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
SeismoGPT is a transformer autoregressive model achieving median normalized cross-correlation above 0.93 when forecasting synthetic three-component seismograms up to 240 s ahead from P- and S-wave context.
-
Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
A causal transformer trained on synthetic seismograms autoregressively continues three-component waveforms past the S-wave with median NCC of 0.93 or higher across controlled geometries.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.