WaveDINO: Learning-Based Atmospheric Correction of Unwrapped InSAR Interferograms Validated by GNSS: Results at Laguna del Maule and Campi Flegrei Volcanoes

2026-06-15

AI Summary

This study addresses the persistent challenges in InSAR observations caused by atmospheric delays, seasonal surface changes, and decorrelation, which existing correction methods struggle to mitigate without introducing artifacts or biases. To overcome these limitations, the authors propose a learning-based, multi-scale wavelet denoising framework that innovatively integrates features from a frozen-parameter DINOv2 vision foundation model with topographic information. A hybrid training strategy is employed, combining physically simulated magmatic deformation signals with real atmospheric noise to preserve authentic atmospheric statistics while providing reliable supervisory targets. Validation on the Laguna del Maule volcanic field in Chile and the Campi Flegrei caldera in Italy demonstrates that the proposed method significantly outperforms current approaches, including numerical weather models, achieving GNSS cross-validated mean squared error reductions of approximately 3% and 19%, respectively.

Abstract

Interferometric Synthetic Aperture Radar (InSAR) enables effective monitoring of volcanic deformation; however, the observed signals are often corrupted by atmospheric phase delays, seasonal surface changes, and decorrelation effects. Existing atmospheric correction methods, such as numerical weather model-based methods, can reduce these effects but do not consistently remove atmospheric artefacts and may introduce residual biases. To address these limitations, we propose a novel learning-based method for denoising unwrapped InSAR interferograms, using a hybrid training strategy that combines physically motivated synthetic deformation with real atmospheric noise. Specifically, we introduce WaveDINO, a wavelet-based multi-scale denoising framework conditioned on frozen DINOv3 foundation-model features and terrain information. Training uses synthetic magma-source deformation superimposed on short-term interferograms to expose the network to realistic atmospheric statistics while retaining known ground truth. Performance is evaluated on both controlled synthetic data and long-term real interferograms from Laguna del Maule (Chile) and Campi Flegrei (Italy), with independent GNSS measurements used for validation. WaveDINO consistently outperforms competing models, improving agreement with GNSS measurements, and reducing mean GNSS misfit by approximately 3% and 19% at two sites, respectively, while surpassing weather-model-based corrections.

Problem

• Atmospheric correction
• InSAR
• Volcanic deformation
• Atmospheric phase delay
• Interferogram denoising

Innovation

• WaveDINO
• learning-based atmospheric correction
• InSAR denoising
• foundation model conditioning
• multi-scale wavelet denoising