pith. sign in

arxiv: 2604.07421 · v3 · pith:RKJWQVODnew · submitted 2026-04-08 · 💻 cs.LG

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

Zhenyu Wang , Peiyuan Li , Yongxiang Shi , Ruoyu Wu , Chenfei Liao , Lei Zhang This is my paper

Pith reviewed 2026-05-10 17:30 UTC · model grok-4.3

classification 💻 cs.LG
keywords full-waveform inversionmixture of expertsneural operatorsspectral methodsdeep learninginverse problemsvelocity model reconstruction
0
0 comments X

The pith

SPAMoE uses spectrum-aware routing to cut errors in learning-based full-waveform inversion by 44 percent.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper aims to show that frequency entanglement of multi-scale features limits existing CNNs and single neural operators in full-waveform inversion. SPAMoE counters this with a Spectral-Preserving DINO Encoder that protects high-frequency energy and a routing system that sends separate frequency bands to an ensemble of specialized operators. On ten OpenFWI sub-datasets the method lowers average mean absolute error by 44.4 percent versus the strongest prior baseline. If correct, the result supplies a concrete new route to faster, more accurate subsurface velocity models from seismic data.

Core claim

SPAMoE combines a Spectral-Preserving DINO Encoder, which enforces a lower bound on the high-to-low frequency energy ratio, with a Spectral Decomposition and Routing mechanism that dynamically assigns bands to a Mixture-of-Experts ensemble of FNO, MNO, and LNO operators, thereby reducing reconstruction error on standard full-waveform inversion benchmarks.

What carries the argument

The Spectral Decomposition and Routing mechanism that assigns frequency bands to an MoE ensemble of Fourier, multi-wavelet, and local neural operators, backed by the energy-ratio constraint in the DINO encoder.

If this is right

  • Average MAE across the ten OpenFWI sub-datasets drops 44.4 percent relative to the strongest reported baseline.
  • Multi-scale geological structures become easier to resolve because high-frequency collapse is prevented before operator application.
  • The same hybrid routing pattern can be applied to other inverse problems that involve entangled frequency content.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The routing logic could be ported to other wave-based inverse tasks such as medical ultrasound tomography.
  • Real-time seismic monitoring pipelines might adopt the MoE decomposition to handle streaming data with changing frequency content.
  • Field-data experiments would be needed to check whether the synthetic gains hold when noise statistics differ from the OpenFWI training distribution.

Load-bearing premise

Frequency entanglement is the dominant bottleneck in prior CNNs and single-paradigm operators, and separating bands through the proposed encoder and MoE routing will reliably improve results across varied geological settings.

What would settle it

A controlled test on a new synthetic or field dataset in which SPAMoE fails to beat the best OpenFWI baseline by a comparable margin or in which the encoded high-frequency energy ratio drops below the claimed bound.

Figures

Figures reproduced from arXiv: 2604.07421 by Chenfei Liao, Lei Zhang, Peiyuan Li, Ruoyu Wu, Yongxiang Shi, Zhenyu Wang.

Figure 1
Figure 1. Figure 1: Schematic illustration of seismic full-waveform Inver￾sion (FWI). and traveltime tomography in characterizing complex geolog￾ical structures. However, conventional physics-constrained iterative inversion methods have long been limited by cycle￾skipping, high computational cost, and strong sensitivity to the initial model, which is particularly pronounced in high￾resolution and structurally complex scenario… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the SPAMoE framework. (a) The Spectral-Preserving DINO Encoder projects time-receiver domain seismic obser [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of subsurface velocity maps predicted by SPAMoE and the FNO baseline. Top row: ground-truth velocity maps; middle row: SPAMoE predictions; bottom row: FNO predic￾tions. better), while PSNR measures reconstruction fidelity in deci￾bels (higher is better). Following the OpenFWI practice of re￾porting the best-performing checkpoint, we evaluate the met￾rics at each epoch during training and report … view at source ↗
Figure 4
Figure 4. Figure 4: Spectral visualizations of ablation study. [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparison of pipe flow velocity fields on the Pipe Flows dataset. From left to right, each column shows the ground-truth velocity field, the prediction of our model, and the cor￾responding absolute error.Each row corresponds to a different test sample. 5 Conclusion In this paper, we proposed SPAMoE, a unified framework for full-waveform inversion. By integrating a Spectral- [PITH_FULL_IMAGE:f… view at source ↗
Figure 6
Figure 6. Figure 6: Additional qualitative results of our framework on OpenFWI. Each column corresponds to one of the ten OpenFWI sub-datasets, [PITH_FULL_IMAGE:figures/full_fig_p016_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Total 12 columns show 4 samples per sub-dataset (from left to right: FlatVel-A, CurveFault-A, CurveVel-A). Rows from top to [PITH_FULL_IMAGE:figures/full_fig_p017_7.png] view at source ↗
read the original 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

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes SPAMoE, a spectrum-aware hybrid operator framework for full-waveform inversion (FWI). It introduces a Spectral-Preserving DINO Encoder that enforces a lower bound on the high-to-low frequency energy ratio of encoded representations to mitigate high-frequency collapse, along with a Spectral Decomposition and Routing mechanism that dynamically assigns frequency bands to a Mixture-of-Experts ensemble consisting of FNO, MNO, and LNO operators. Experiments on the ten OpenFWI sub-datasets report that SPAMoE reduces average MAE by 44.4% relative to the best officially reported baseline, positioning the method as a new architectural framework for learning-based FWI. Code and data are released.

Significance. If the performance gains prove robust and attributable to the spectrum-aware components (rather than capacity increases or baseline differences), the work could meaningfully advance learning-based FWI by targeting frequency entanglement in multi-scale geological structures. The open-sourcing of code and data is a clear strength for reproducibility and follow-on work.

major comments (3)
  1. [Abstract] Abstract: The central claim of a 44.4% average MAE reduction on the ten OpenFWI sub-datasets is stated without details on baseline implementations, data splits, statistical significance, variance across runs, or ablation controls. This makes it impossible to determine whether the improvement stems from the proposed Spectral-Preserving DINO Encoder and frequency-band routing or from other factors.
  2. [Spectral-Preserving DINO Encoder] Spectral-Preserving DINO Encoder section: The lower-bound enforcement on the high-to-low frequency energy ratio is claimed to prevent representational collapse, but no ablation removing or varying this term is described, nor is there analysis showing that the ratio is actively constrained rather than trivially satisfied. Without this, the term's contribution to the headline result cannot be isolated.
  3. [Experiments] Experiments section: No expert-utilization statistics, routing histograms, or per-band allocation analysis are provided to verify that the Spectral Decomposition and Routing mechanism meaningfully distributes frequency bands across the FNO/MNO/LNO experts instead of collapsing to a single dominant operator. This directly affects whether the hybrid MoE design is load-bearing for the reported gains.
minor comments (2)
  1. [Abstract] The title refers to a 'Spectrum-Aware Hybrid Operator Framework' while the abstract defines SPAMoE as 'Spectral-Preserving Adaptive MoE'; a brief note reconciling the two phrasings would improve clarity.
  2. [Abstract] The abstract mentions 'frequency entanglement of multi-scale geological features' as the core limitation of prior CNNs and single-paradigm NOs; a short literature pointer or equation illustrating this entanglement would help readers unfamiliar with FWI.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We address each major comment point by point below, providing our responses and indicating the revisions we will make to the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim of a 44.4% average MAE reduction on the ten OpenFWI sub-datasets is stated without details on baseline implementations, data splits, statistical significance, variance across runs, or ablation controls. This makes it impossible to determine whether the improvement stems from the proposed Spectral-Preserving DINO Encoder and frequency-band routing or from other factors.

    Authors: We agree that the abstract is concise and would benefit from additional context for clarity. The reported 44.4% MAE reduction is computed against the best officially reported baselines from the OpenFWI benchmark, with complete details on data splits, baseline implementations, and experimental protocols provided in the Experiments section. We will revise the abstract to explicitly note the use of officially reported OpenFWI baselines and to direct readers to the Experiments section for implementation details, data splits, ablation studies, and any available statistical analysis. We will also add results from multiple runs with standard deviations to the revised Experiments section to address variance and robustness. revision: partial

  2. Referee: [Spectral-Preserving DINO Encoder] Spectral-Preserving DINO Encoder section: The lower-bound enforcement on the high-to-low frequency energy ratio is claimed to prevent representational collapse, but no ablation removing or varying this term is described, nor is there analysis showing that the ratio is actively constrained rather than trivially satisfied. Without this, the term's contribution to the headline result cannot be isolated.

    Authors: We acknowledge that an explicit ablation and constraint analysis would better isolate the contribution of the spectral-preserving term. The current manuscript motivates the lower-bound enforcement theoretically in the Spectral-Preserving DINO Encoder section and demonstrates its effect indirectly via performance gains. In the revised version, we will add an ablation study that removes or varies the lower-bound term, along with analysis (e.g., plots of the high-to-low frequency energy ratio during training) to confirm that the ratio is actively constrained rather than trivially satisfied. revision: yes

  3. Referee: [Experiments] Experiments section: No expert-utilization statistics, routing histograms, or per-band allocation analysis are provided to verify that the Spectral Decomposition and Routing mechanism meaningfully distributes frequency bands across the FNO/MNO/LNO experts instead of collapsing to a single dominant operator. This directly affects whether the hybrid MoE design is load-bearing for the reported gains.

    Authors: We agree that verifying the dynamic routing behavior is essential to substantiate the hybrid MoE design. While the manuscript describes the Spectral Decomposition and Routing mechanism and reports overall performance improvements, we will expand the Experiments section to include expert-utilization statistics, routing histograms, and per-band allocation analysis. These additions will demonstrate that frequency bands are meaningfully distributed across the FNO, MNO, and LNO experts rather than collapsing to a dominant operator. revision: yes

Circularity Check

0 steps flagged

No significant circularity: empirical gains measured on external OpenFWI benchmarks

full rationale

The paper proposes SPAMoE with a Spectral-Preserving DINO Encoder enforcing a high-to-low frequency energy ratio lower bound and a frequency-band MoE routing across FNO/MNO/LNO experts. Its headline result is the 44.4% average MAE reduction on the ten OpenFWI sub-datasets relative to the best reported baseline. No derivation chain, equations, or self-citations are shown that reduce this performance gain or the architectural choices to quantities defined inside the model by construction. The improvements are presented as experimental outcomes against independent external data, not as tautological predictions or renamed fitted inputs. The framework is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 2 invented entities

The framework rests on standard neural-operator approximation assumptions plus two paper-specific architectural inventions whose effectiveness is shown empirically rather than derived from first principles.

free parameters (1)
  • frequency-band thresholds and routing gates
    Parameters that control decomposition and expert assignment; learned or tuned during training and central to the claimed frequency handling.
axioms (2)
  • domain assumption Neural operators can approximate solutions to the wave equation in FWI
    Standard background assumption in the neural-operator literature for seismic inversion.
  • ad hoc to paper Enforcing a lower bound on high-to-low frequency energy ratio prevents representational collapse
    Introduced specifically for the Spectral-Preserving DINO Encoder.
invented entities (2)
  • Spectral-Preserving DINO Encoder no independent evidence
    purpose: Enforces spectral energy ratio lower bound during encoding
    New architectural component proposed to address high-frequency loss.
  • Spectral Decomposition and Routing mechanism no independent evidence
    purpose: Dynamically assigns frequency bands to MoE experts
    Novel routing layer that enables the hybrid operator ensemble.

pith-pipeline@v0.9.0 · 5544 in / 1613 out tokens · 108611 ms · 2026-05-10T17:30:14.015825+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.