Call for Papers - AI for Electromagnetics, Antennas, Propagation, Communication Channels and Microwave Circuits

Artificial Intelligence (AI), which encompasses not only machine learning (ML), but also optimization techniques as well as their hybrid integration, is transforming a wide range of scientific and engineering disciplines and is anticipated to have profound impact on technology development in the future. While AI in some engineering fields and data sciences has seen rapid and phenomenal development, its application in many specialized areas such as electromagnetics, antennas, propagation, communications channels, and RF and microwave circuits remains in its early stage.

To fully leverage AI’s capabilities in these important domains, substantial research and development are required. In particular, breakthroughs are needed in modelling, optimization, and synthesis that surpass the performance of traditional model-based approaches. AI is believed to offer a paradigm change for analyzing and modelling complex, nonlinear electromagnetic phenomena that are often intractable with conventional techniques.

Beyond enhancing the model accuracy, AI can enable real-time adaptability—an essential feature in dynamic and rapidly evolving communication environments. For instance, machine learning (ML) and deep learning (DL) have shown great promise in the design and optimization of antennas and RF devices, as well as in propagation modelling and parameter estimation for communication channels.

The objective of this Special Issue is to bring together cutting-edge research contributions and practical innovations that explore the application of AI techniques to electromagnetics simulation, antenna design, propagation and communication channel modelling, and RF and microwave circuit design. We welcome original research articles, comprehensive reviews, tutorials, and case studies from both academia and industry that showcase theoretical developments, experimental validation, and engineering applications.

Topics of interest include, but are not limited to:

• AI for modelling, optimization, and synthesis of antennas and arrays
• AI for design and optimization of RF and microwave circuits and systems
• AI for multiport and multiple-input-multiple output (MIMO) antenna and system design
• AI for RF channel estimation and prediction for communications
• Interpretability of AI-based models and physics-embedded AI for electromagnetic applications
• AI for modelling complex EM environments
• AI for EM scattering, radiation and imaging
• AI for electromagnetic aspects of near-field communications
• AI for electromagnetic aspects of integrated sensing and communication (ISAC)
• AI for multiphysics-based electromagnetic simulations and modelling

About JSTEAP

The IEEE Journal of Selected Topics in Electromagnetics, Antennas and Propagation (JSTEAP) is co-sponsored by the Antennas and Propagation Society (AP-S), Microwave Theory and Technology Society (MTT-S), and the Communications Society (ComSoc). The focus of JSTEAP is on contributions that bridge the gaps between electromagnetics, communications, and microwave technology and manuscripts incorporating at least two of these aspects are particularly encouraged. All types of contributions are welcome including theory, experimental results, designs, applied engineering innovations, surveys, tutorials and reviews. Each issue of JSTEAP is devoted to a specific technical topic and thus provides to JSTEAP readers a collection of up-to-date papers on that topic. These issues are expected to be valuable to the research community and become a source of valuable references.

Open and Transparent Research Exchange

JSTEAP is a fully Open Access journal and is committed to supporting open and transparent research exchange and enabling authors to embrace best practices in data and code sharing. All submitted manuscripts should contain sufficient detail to allow their research contributions and results to be verified and repeated by independent researchers.

For manuscripts with AI-related content, JSTEAP follows IEEE publication policies. In this context, we identify two main categories of submissions; to uphold open and transparent research exchange, the following guidelines apply:

1. Manuscripts describing new AI algorithms or substantive methodological advances: Public release of code and training/evaluation datasets is strongly encouraged. If full release is not possible, authors should provide sufficient algorithmic detail and complete training/evaluation protocols, together with access to datasets (public or controlled access), so that independent researchers can reproduce the results.
2. Manuscripts applying established AI methods to specific EM/antenna design or propagation modeling problems: These should emphasize verifiable outcomes rather than novelty in the AI methodology. Authors must provide enough detail to enable reproduction of the workflow and results, even if proprietary datasets cannot be released. Acceptable alternatives include: (a) detailed data specifications (e.g., size, sources, preprocessing); (b) full training and inference pipelines (hyperparameters, architectures, loss functions, hardware, compute budget, evaluation metrics); and (c) clear baseline comparisons where feasible.

Manuscripts with AI contributions outside these categories, or those seeking exceptions to these guidelines, will be considered as long as the principles of open and transparent research exchange—including verification and repeatability of results—are maintained.

Submission Guidelines

Prospective authors should submit their manuscripts following the IEEE JSTEAP guidelines. All submissions must be made through the online JSTEAP Author Portal on ScholarOne.

Official templates are available via the IEEE Template Selector for both LaTeX and MS Word. Please click on “IEEE Template Selector” and follow the instructions to access the template you need.

Authors should submit their manuscripts according to the following schedule:

Important Dates