Next Article in Journal
Accurate Road User Position Estimation for V2I Using Point Clouds from Mobile Mapping Systems
Next Article in Special Issue
In-Situ Measurements in Reconfigurable Phased-Array Transmitters
Previous Article in Journal
HRSRD: A High-Resolution SAR Road Dataset and MSDA-LinkNet for Road Extraction with Multi-Scale Deformable Attention
Previous Article in Special Issue
In Situ Assessment of EMF Exposure Across Urban Districts of Samsun, Türkiye
 
 
Article
Peer-Review Record

Physics-Informed and Interpretable Machine-Learning-Assisted Design of Electromagnetic Absorbers for Radar Cross-Section Reduction in Electronic Systems

Electronics 2026, 15(6), 1237; https://doi.org/10.3390/electronics15061237
by Tiancai Zhang 1,2, Yi Yang 1,* and Tao Hong 3,4,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Electronics 2026, 15(6), 1237; https://doi.org/10.3390/electronics15061237
Submission received: 12 February 2026 / Revised: 2 March 2026 / Accepted: 4 March 2026 / Published: 16 March 2026
(This article belongs to the Special Issue Innovations in Electromagnetic Field Measurements and Applications)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors   This paper deals with the design of electromagnetic absorbers for radar cross-section reduction. A learning model is developed to establish transparent relationships between absorber parameters and reflection-related performance. The predicted results are verified through experiments. The paper can be considered for publication after some revisions. My main comments are the following.   1) The topic has already been widely studied. The novelty should be better clarified.   2) A photograph and a block diagram of the experimental setup should be included.   3) The physical properties of electromagnetic absorbers are influenced by environmental conditions such as humidity and temperature. Did the authors investigate the impact of these factors on the predicted results? The authors should provide a comment or clarification on this point.   4) The authors should evaluate the applicability of the proposed model and design approach over a wide range of temperatures and relative humidity levels. Furthermore, the predicted results should be experimentally validated under different environmental conditions to confirm their reliability.   5) It is unclear whether all analytical expressions in the manuscript were originally derived by the authors. If any expressions were taken from or based on existing literature, the relevant sources should be properly acknowledged and cited.   6) The measurement uncertainty or at least instrument accuracy need to be supplemented. This aspect should be addressed to ensure the credibility and reliability of the experimental data.   7) The differences between the theoretical and experimental results should be explained more thoroughly. Possible sources of discrepancy need to be identified and discussed in detail.   8) It is recommended to use the same font type in all figures.

Author Response

Please refer to the attachment for a detailed response.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The article addresses the current and important issue of designing electromagnetic absorbers using machine learning methods supported by physical knowledge. The authors accurately identify the difficulties resulting from strongly nonlinear relationships between electromagnetic, geometric, and material parameters, as well as the limitations of the classical trial-and-error approach. The work is well structured and logically presented. It covers the construction of a unified data set and physical descriptors, the construction of an XGBoost model, SHAP interpretability analysis leading to the derivation of quantitative design rules, and experimental validation. The literature is up-to-date, comprehensive, and correctly cited. While reading the work, I had a few minor comments that, in my opinion, could help the authors present the results of their work in a more accessible way.

  1. Abbreviations such as ML, EM, and SHAP should be expanded when they first appear in the text. In particular, failure to expand the abbreviation SHAP when it is first used may make it difficult for readers outside the field to understand the article.
  2. The chapter titles are quite long and complex, which sometimes makes it difficult to navigate the structure of the work. The authors could consider shortening them or partially adapting them to the classic IMRaD structure, which would improve the clarity of the article.
  3. The paper contains a large number of abbreviations and physical symbols. In accordance with MDPI guidelines, it would be advisable to add a "Nomenclature" section containing a list of symbols and abbreviations used in the article.
  4. I noticed some minor editorial shortcomings, including:
    • editorial text left ("Type of the Paper"),
    • subtitles located as the last line of the page,
    • insufficient separation between drawings and text,
    • minor typos and formatting inconsistencies.

          Careful technical editing prior to publication is recommended.

  1. The authors mention the possibility of extending the proposed framework to other classes of materials. Please clarify whether any preliminary validation has been performed on other data. Is this statement based on any tests or is it theoretical in nature?
  2. The conclusions section lacks a clearly formulated paragraph on limitations of the work and future research directions.

Author Response

Please refer to the attachment for a detailed response.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors addressed all of my original comments and now I can recommend the manuscript for publication.

Back to TopTop