- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In this paper, the authors propose the GCFNO for electromagnetic modeling. Motivated by local sensitivity analysis, it factorizes receiver–horizontal geometry from frequency–depth condition and couples them through a nonlinear readout. The authors provide local approximation and estimation analyses and evaluate GCFNO on synthetic 3D magnetotellurics (MT) and head EIT benchmarks.
Critical strengths
- The geometry–condition factorization is physically motivated and clearly connected to electromagnetic sensitivity.
- The paper provides useful theoretical support, including a spectral-tail local approximation bound and reference-model separation/estimation analysis.
- The experimental results were remarkable, and there were also abundant visual verifications.
Critical weaknesses
- I'm not very familiar with this field. Are the two benchmark datasets sufficient to validate the proposed method?
- The theory relies on local, small-perturbation, smoothness, and translation-invariance assumptions, so its connection to the trained global nonlinear operator is indirect.
- Ablations are insufficient for the main components, such as geometry message passing, depth aggregation, FiLM/readout, and residual design; evaluation is mostly synthetic with limited real-data/noise validation.
Questions for authors
Please see Weaknesses!
2 comments
The author has addressed my concerns, and I no longer have any further comments. Furthermore, I continue to give positive ratings.
Response to Reviewer efAd
We thank the reviewer for the constructive feedback and respond to each point below.
Weaknesses R1: MT and head EIT provide two complementary electromagnetic benchmarks with substantially different physical and computational characteristics.: MT evaluates 900 3-D volumes (630/135/135 split) on a structured 50×50 surface grid across 15 frequencies, whereas head EIT evaluates 193 subject-specific anatomies (135/29/29 split, ~76k finite-element cells) across 17 frequencies, 31 current-injection patterns, and 33 scalp electrodes. They span open-domain geophysical modeling with skin-depth attenuation and bounded, anatomically irregular biomedical modeling with boundary-electrode measurements. Together, these evaluations provide complementary evidence for the effectiveness of sensitivity-guided geometry--condition factorization across representative electromagnetic forward-modeling scenarios.
Weaknesses R2: Thanks for sharing the same concern with Reviewer 1. Proposition 1 and Proposition 4 analyze the local Fr'echet derivative under reference symmetry; they do not assume that the full nonlinear forward operator is globally linear or translation invariant. GCFNO uses this structure as an architectural inductive bias: in Eq. (13), latent feature access satisfies ∂Dd,k(η)∂di,f,k=wi(η)ad(f), separating receiver--horizontal geometry (i,η) from frequency--depth dependence (f,d), while the shared encoder Eθ and nonlinear readout Rθ learn the nonlinear material dependence end-to-end from solver responses. Appendix Fig. 10 shows that learned EIT depth weights shift from interior regions at low frequencies to boundary-adjacent regions at high frequencies, consistent with this organization. Appendix C.4 (Eqs. 47--51) further links local factor estimation to nonlinear prediction error by accounting for rank-truncation bias, estimation variance, and the second-order Taylor remainder.
Weaknesses R3: We added matched component ablations on 3-D MT using identical splits and training protocols, along with the relative degradation compared with GCFNO full:
On the fixed MT grid, the residual decoder gives the largest sequential gain (5.02% over matched GNO), and geometry message passing has the largest leave-one-out impact (+5.23% degradation when removed). Depth attention and FiLM each contribute ~0.25% on fixed-grid RMSE, while structured depth conditioning becomes more important under held-out-frequency completion, lowering macro-averaged RMSE from 1.264 (GNO freq-only) to 0.546. On input degradation (Appendix G.2, Table 8), GCFNO maintains lower error than GNO across all log-resistivity noise levels (0.01--0.10, e.g., 0.017775 vs. 0.019430 at 0.10), all coarse-grid factors (2, 4, 5), and boundary smoothing at level 0.25 (0.033771 vs. 0.034397).