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

TL;DR

This paper introduces a parameter-efficient method to adapt pre-trained vision models for seismic data denoising, enabling robust, domain-generalized noise suppression without extensive retraining.

Contribution

It proposes a novel framework using Low-Rank Adaptation and unsupervised test-time calibration to effectively adapt vision foundation models for seismic denoising tasks.

Findings

Framework matches or outperforms domain-specific models.

Demonstrates strong generalization across different seismic datasets.

Effective noise suppression without requiring ground truth labels.

Abstract

The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data from dense geophone deployments, distributed acoustic sensing (DAS) arrays, and large-scale 2D and 3D surveys. This expansion makes complex noise suppression increasingly challenging, especially when signal fidelity must be preserved. Conventional supervised deep learning methods are often task-specific, require large paired datasets, and can suffer from domain shift under new acquisition conditions. Foundation models offer a promising alternative, but pre-training seismic foundation models from scratch requires massive domain-specific data and substantial computation. We propose an efficient framework that repurposes general-purpose Vision Foundation Models (VFMs) for geophysical tasks through Parameter-Efficient Fine-Tuning. The architecture uses a pre-trained VFM, a DINOv3 encoder, adapted with Low-Rank Adaptation (LoRA) to enable effective feature adaptation with few additional parameters. To improve robustness under unseen field conditions without ground truth, we introduce a kurtosis-guided unsupervised test-time adaptation module that updates only LoRA parameters during inference. This module self-calibrates the model to site-specific noise by identifying information-rich regions via kurtosis and performing self-training without labeled data. Experiments on public exploration seismic images and DAS vertical seismic profiling data from the Utah FORGE site show that the framework matches or outperforms domain-specific models. Tests on unseen cross-site data from a land survey in China and the Gro{\ss} Sch\"onebeck geothermal site in Germany further demonstrate strong generalization and effective signal-noise separation. These results highlight the potential of adapting pre-trained VFMs to data-intensive problems in exploration seismology.