SPAMoE: Spectrum-Aware Hybrid Operator Framework for Full-Waveform Inversion

TL;DR

SPAMoE is a spectrum-aware hybrid operator framework that improves full-waveform inversion by stabilizing frequency representation and dynamically routing frequency bands, achieving significant accuracy gains.

Contribution

The paper introduces a novel spectrum-preserving encoder and a dynamic routing mechanism for frequency bands, enhancing multi-scale geological feature modeling in FWI.

Findings

Reduces MAE by 44.4% on OpenFWI datasets.

Establishes a new architectural framework for learning-based FWI.

Demonstrates improved stability and accuracy over existing methods.

Abstract

Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill-posed. While deep learning approaches promise efficiency, existing Convolutional Neural Networks (CNNs) and single-paradigm Neural Operators (NOs) struggle with one fundamental issue: frequency entanglement of multi-scale geological features. To address this challenge, we propose Spectral-Preserving Adaptive MoE (SPAMoE), a novel spectrum-aware framework for solving inverse problems with complex multi-scale structures. Our approach introduces a Spectral-Preserving DINO Encoder that enforces a lower bound on the high-to-low frequency energy ratio of the encoded representation, mitigating high-frequency collapse and stabilizing subsequent frequency-domain modeling. Furthermore, we design a novel Spectral Decomposition and Routing mechanism that dynamically assigns frequency bands to a Mixture-of-Experts (MoE) ensemble comprising FNO, MNO, and LNO. On the ten OpenFWI sub-datasets, experiments show that SPAMoE reduces the average MAE by 44.4% relative to the best officially reported OpenFWI baseline, thereby establishing a new architectural framework for learning-based full-waveform inversion. Our code and data are available at https://github.com/zhenyuwang12366/SPAMoE