← Back to all news
arXiv AI By Laura Laurenti, David Liu, Brian Kulis, Men-Andrin Meier, Christopher Johnson

Are Seismic Foundation Models More Than Glorified Feature Extractors?

Read the original on arXiv AI →

The paper investigates whether seismic foundation models can transcend being mere feature extractors by training a Mamba encoder‑decoder on 3 million waveform windows with varied self‑supervised objectives, quantization bottlenecks, and mixers. Experiments show that changing the training target redistributes performance across downstream tasks rather than improving it overall; adding masking improves few‑shot P‑wave picking but harms classification accuracy. The authors conclude that current models act as feature extractors, and that a learning target spanning seismic events—capturing the stochastic inter‑event timescale—is needed to achieve true foundation‑model capabilities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 4

Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability

arXiv:2606. 10069v3 Announce Type: replace Abstract: In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package.

By Wei Quan, Denise Gorse
More like this →
arXiv Machine Learning
Jun 10

Spatiotemporal Seismic Hazard Assessment Using VQ-VAE and Seismic Statistical Features

arXiv:2606. 10069v1 Announce Type: new Abstract: In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package.

By Wei Quan, Denise Gorse
More like this →
arXiv Machine Learning
Sep 23

Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising

The paper presents a framework that adapts general-purpose Vision Foundation Models (VFMs) to seismic data denoising using Parameter‑Efficient Fine‑Tuning with Low‑Rank Adaptation (LoRA). It introduces a kurtosis‑guided unsupervised test‑time adaptation module that updates only LoRA parameters to self‑calibrate for site‑specific noise without ground truth. Experiments on exploration seismic images and DAS data demonstrate that the approach matches or surpasses domain‑specific models and generalizes well to unseen cross‑site data.

By Jiahua Zhao, Umair bin Waheed, Jing Sun, Yang Cui, Nikos Savva, Eric Verschuur
fine-tuning
More like this →
arXiv Machine Learning
Jun 9

GNSS-FM: A Self-Supervised Foundation Model for Daily GNSS Displacement Time Series

arXiv:2606. 07725v1 Announce Type: cross Abstract: Displacement time series from Global Navigation Satellite Systems (GNSS) are essential for a wide range of applications, including monitoring tectonic crustal deformations and investigating the different stages of the earthquake cycle.

By Nick Teutschmann (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Laura Crocetti (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Fanny Lehmann (ETH AI Center, Switzerland), Leonardo Trentini (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Benedikt Soja (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland)
fine-tuningefficiency
More like this →
arXiv Machine Learning
Oct 12

Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment

The study investigates shortcut learning in geospatial foundation model embeddings for cross-disaster damage assessment. By holding out entire disasters during evaluation, the authors demonstrate a significant drop in mean balanced accuracy across multiple datasets, revealing that models rely on event or scene characteristics rather than transferable evidence. They further show that simple feature-level transformations, such as supervised contrastive learning or PCA, can improve generalization to unseen disasters.

By Ali Shibli, Andrea Nascetti, Yifang Ban
rag
More like this →