Structure-dependent failure modes of neural priors in acoustic full-waveform inversion

Abstract

Frequency continuation does not improve every neural representation, and better velocity recovery need not imply better prediction of unseen waveforms. We compare a velocity grid with total-variation regularization, an adapted sinusoidal coordinate network (SIREN), and a frozen image generator with a full-grid residual in two-dimensional acoustic full-waveform inversion. All methods use the same frozen SWEEP discretization, acquisition, observations, background, and budget of 1,500 shot--model gradient evaluations. Three exposed synthetic targets represent inclined layering, curved layering, and a high-contrast curved interface drawn from a fault-labelled family. With 2-to-10 Hz continuation, the generative-residual model attains velocity RMSEs of 218.7, 108.0, and 341.9 m/s, compared with 232.5, 100.3, and 412.9 m/s for Grid+TV. Thus the latter wins on curved layering, while the former improves model RMSE by 5.9% and 17.2% on the other targets. Grid+TV nevertheless predicts held-out 10 Hz shots better on all three. SIREN is worse than the common background in every cell; continuation worsens two targets but improves one. A five-weight TV sensitivity study preserves the CurveFault model-error ranking. An equal-budget variational extension fails both recovery and interval coverage. These results establish conditional rankings, not universal superiority or an isolated spectral-bias mechanism. Full-grid residuals also prevent attributing gains uniquely to the generator. We advocate joint reporting of model recovery, unseen-shot prediction, optimization cost, and negative outcomes when auditing neural FWI.