When Less Is More: Simplicity Beats Complexity for Physics-Constrained InSAR Phase Unwrapping

TL;DR

This study demonstrates that simple convolutional neural networks outperform complex attention-based models in physics-constrained InSAR phase unwrapping, emphasizing the importance of simplicity and physical consistency.

Contribution

The paper provides the first large-scale ablation study showing that simpler U-Net architectures outperform complex attention models in geophysical phase unwrapping tasks.

Findings

Vanilla U-Net outperforms attention-based models in R^2 and RMSE.

Attention models introduce unphysical high-frequency artifacts.

U-Net achieves faster inference suitable for operational early-warning systems.

Abstract

Operational phase unwrapping is the primary computational bottleneck in InSAR-based volcanic and seismic monitoring. We challenge the industry trend of adopting high-complexity computer vision architectures, such as attention mechanisms, without validating their suitability for physics-constrained geophysical regression. We present the first large-scale architectural ablation study on a global LiCSAR benchmark (20 frames, 39,724 patches, 651M pixels). Our results reveal a significant "complexity penalty": a vanilla U-Net (7.76M parameters) achieves $R^2=0.834$ and RMSE $= 1.01$ cm, outperforming 11.37M-parameter attention-based models by 34% in $R^2$ and 51% in RMSE. Power Spectral Density (PSD) analysis provides the physical justification: while attention excels at capturing sharp semantic edges in natural images, it injects unphysical high-frequency artifacts ($>0.3$ cycles/pixel) into geophysical fields, violating the fundamental smoothness constraints of elastic surface deformation. With a 2.92ms inference latency (a $2.5\times$ speedup), the vanilla U-Net is the only candidate to comfortably meet the sub-100ms requirement for operational early-warning systems. This work bridges the "publication-to-practice" gap by proving that convolutional locality outperforms modern complexity for smooth-field regression, advocating for physics-informed simplicity in ML4RS. Code available at https://github.com/prabhjotschugh/When-Less-is-More-InSAR-Phase-Unwrapping