AI evidence extraction

Can we trust AI-assisted technical writing in electromagnetics? characteristic mode analysis for metasurface design as a stress test

Mohamed Z. M. Hamdalla, Sayan Roy · Frontiers in Antennas and Propagation · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

2/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.3389/fanpr.2026.1808402

Methodology & findings

Study design

Narrative literature review with targeted search across peer-reviewed publications.

Main result

The study found that "CMA has become a practical tool for metasurface design because it offers an interpretable basis of current/field mechanisms that complement unit-cell parameter retrieval and brute-force optimization." The review demonstrates that characteristic mode analysis can be systematically applied across multiple metasurface design objectives including bandwidth enhancement, polarization conversion, reconfigurable intelligent surfaces, and scattering control, and that "when used with careful mode tracking, explicit reporting of solver conventions, and validation against full-wave results, CMA can help designers understand bandwidth limits, identify parasitic mechanisms, and engineer excitation to realize metasurface functions."

Research paradigm

Interpretive/Positivist hybrid - domain expert verification of AI-assisted technical writing

Author conclusions

The authors conclude: "CMA has become a practical tool for metasurface design because it offers an interpretable basis of current/field mechanisms that complement unit-cell parameter retrieval and brute-force optimization. When used with careful mode tracking, explicit reporting of solver conventions, and validation against full-wave results, CMA can help designers understand bandwidth limits, identify parasitic mechanisms, and engineer excitation to realize metasurface functions such as radiation control and polarization conversion." They further state that "Future work is likely to expand robust CMA formulations for lossy, dispersive, and strongly coupled periodic structures, and to establish community benchmarking and reporting practices that make CMA-guided metasurface designs more reproducible across solvers and laboratories."

Risk of bias

Publication bias: targeted literature scan may miss unpublished or negative results; Scope bias: review focuses on peer-reviewed applications with explicit modal reporting, potentially excluding alternative design approaches; AI drafting bias: initial automated text generation may have emphasized certain methodologies over others before expert verification; Selection bias: representative rather than exhaustive citation strategy; targeted keyword search may miss relevant applications; Confirmation bias: review emphasizes transferable design reasoning which may favor studies aligned with modal-analysis paradigm; Publication bias: review limited to peer-reviewed sources, may exclude preprints or gray literature; Author expertise bias: domain-expert editing and verification step may introduce subjective interpretation; Selection bias in literature identification: targeted scan rather than systematic review with pre-specified search protocol; Potential citation bias toward works emphasizing CMA effectiveness over limitations; No protocol for assessing quality or risk of bias in cited studies; Narrative review design lacks explicit exclusion criteria; Author expertise in the field may influence interpretation of representative examples

Limitations

The authors explicitly state: "This review is narrative rather than systematic
We conducted a targeted literature scan focused on peer-reviewed applications of CMA to metasurfaces and frequency-selective surfaces." They further note: "The cited examples are representative rather than exhaustive, and the tutorial emphasizes transferable design reasoning and reporting practices." Regarding AI-assisted drafting limitations, they identify that "The highest-risk failure modes remain (i) hallucinated or incorrect references, (ii) correct references but incorrect attribution of claims, and (iii) subtle technical inconsistencies (e.g., conflating periodic unit-cell results with finite-aperture behavior without qualification)."

Open questions raised

Future work should expand "robust CMA formulations for lossy, dispersive, and strongly coupled periodic structures, and establish community benchmarking and reporting practices that make CMA-guided metasurface designs more reproducible across solvers and laboratories." The authors identify promise in combining "CMA-based physical interpretability with global optimization tools such as genetic algorithms, covariance-matrix adaptation evolution strategies, and related learning-assisted search methods, especially for multilayer or volumetric scatterers where constructive interference among several resonances can be designed rather than guessed."
Robust CMA formulations for lossy, dispersive, and strongly coupled periodic structures
Community benchmarking and reporting practices for reproducibility across solvers and laboratories
Integration of CMA-based physical interpretability with global optimization tools (genetic algorithms, evolution strategies) for multilayer or volumetric scatterers
Improved handling of volumetric and strongly coupled metastructures where classical 2D periodic modal analysis may miss global current pathways and interlayer coupling
Need for robust CMA formulations for lossy, dispersive, and strongly coupled periodic structures

Extracted from: pdfAgreement 73%

Explore related topics

AI Manuscript Writing Academic Writing Case Study