Conventional microwave engineering education relies heavily on analytical methods, canonical circuit topologies, and intuition-driven design, which have proven effective at microwave frequencies. However, as systems increasingly operate in the millimeter-wave and terahertz regimes, parasitic effects, process-dependent electromagnetic interactions, and ultra-wideband performance requirements challenge both topology/layout-constrained traditional design methodologies and existing teaching paradigms. This paper proposes a pedagogical shift in microwave and RFIC (Radio Frequency Integrated Circuit) engineering and education by introducing machine-learning (ML) and data-driven electromagnetic synthesis as a complementary design framework for microwave circuits such as power dividers and combiners, couplers, and baluns. Rather than emphasizing predefined topologies, the proposed approach enables topology-agnostic, performance-oriented exploration of the design space, allowing students to directly engage with electromagnetic behavior through specification-driven synthesis. By integrating machine-learning-based inverse design and multi-objective optimization into the curriculum, the framework enhances physical intuition, encourages design creativity, and better aligns microwave education with emerging industrial practices in high-frequency and ultra-wideband system design.
Fig. 4 : The continuum; three methods for synthesizing microwave circuit layouts from electrical specifications
Method
Requires Dataset
Algorithms
Advantages
Disadvantages
Evolutionary Optimization (EA)
No
NSGA-II, CMA-ES, DE, PSO
Directly optimizes performance using EM simulations without reliance on pre-trained models or datasets.
Sensitive to the initial solution (random or template-based). Runtime scales poorly with EM simulation cost. Performance is highly dependent on the score function definition.
Gradient-Free Local Search
No
DFO-TR (continuous), Tabu Search (discrete)
Rapid optimization of a single layout with strong local improvement.
Limited exploration capability. Scales poorly with increasing pixel count and is highly sensitive to the initial design.
Bayesian Optimization (BO)
Optional
GP-BO, Batch BO, Multi-fidelity BO
Constructs a probabilistic surrogate of the simulator, enabling sample-efficient optimization and reuse of learned information.
Performance degrades in high-dimensional spaces and is sensitive to acquisition strategy selection.
Reinforcement Learning
Optional
PPO, TRPO, DQN
Learns a policy that directly optimizes expected performance without explicit S-parameter matching.
Requires large training budgets and careful tuning of reward formulation and hyperparameters.
Neural Surrogate Models
Yes
CNN, DNN, other neural networks
Enables fast inference once trained and significantly reduces reliance on EM simulations.
Requires large datasets and often generalizes poorly across structure families or fabrication technologies.
Surrogate Model + EA Hybrid
Yes
Surrogate models + EA (NSGA-II, CMA-ES, PSO)
Combines fast surrogate-driven optimization with periodic EM-based validation.
Limited by surrogate accuracy and training data coverage; extrapolation is unreliable.
TABLE I : Comparison of Machine-Learning and Optimization Methods for Microwave Passive Circuit Synthesis
Traditional microwave filter design typically relies on iterative parameter tuning and predefined topologies, which limits design space and increases development time. This study uses a deep learning approach combining convolutional neural networks with genetic algorithms to automate pixelated microwave filter synthesis. To validate the approach experimentally, both S-parameter and spatial electric-field measurements were analyzed. The synthesized low-pass filter demonstrated excellent agreement between simulated and measured performance, achieving a 7 GHz passband with over 20 dB suppression beyond 9.5 GHz. Electro-optical measurements, for the first time, revealed electric field patterns that resemble coupled transmission-lines or stub structures, providing insight into the emergent characteristics of AI-generated designs.
Han Zhou, Richard Bannister, Caspar Pierce +9
Chalmers University of Technology, Gothenburg, Sweden · Advanced Technology Institute, University of Surrey, Guildford, UK · National Physical Laboratory, Teddington, UK.
Inverse design of RF and electromagnetic (EM) circuits is challenging because the relationship between circuit layout and electrical response is non-unique, and full-wave simulation is computationally expensive. This paper presents K-TRAIL, a simulator-guided generative framework for automated EM/RF circuit synthesis. K-TRAIL combines diffusion-based layout generation with derivative-free ensemble Kalman guidance, allowing feedback from a black-box EM simulator to refine candidate layouts during generation without requiring adjoint sensitivities or differentiable solver models. The framework supports both synthesis from prescribed S-parameter responses and synthesis directly from RF performance constraints. Experiments on multi-layer RFIC structures show that simulator-guided generation improves agreement with target responses and can identify structurally distinct layouts that satisfy circuit-level design requirements. The proposed approach provides a practical path toward generative, verification-aware RF circuit design while retaining the flexibility to explore diverse layout topologies.
Piyush Saha, Evan Newell, Hanna O'Leary +2
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR 97331 USA · Department of Electrical and Computer Engineering, Yale University, New Haven, CT 06511 USA
Future wireless systems are expected to transform the surrounding space from a passive propagation medium into a smart electromagnetic environment, where engineered surfaces control wave propagation, support wireless sensing, and create programmable electromagnetic fingerprints. A key challenge in realizing this vision is the inverse design of metasurfaces for tailored electromagnetic propagation. While forward analysis evaluates the response of a known geometry, the inverse task starts from a prescribed scattering signature and seeks a physically realizable structure that produces it. This inverse task is inherently nonlinear and often high-dimensional, while candidate solutions may be non-unique and provide no direct indication of practical realizability. Here, we introduce a conditional diffusion framework for inverse design of dielectric resonator metasurfaces from target angular scattering patterns. Trained on T-matrix simulated geometry-response pairs, the model learns a conditional distribution of geometries instead of a deterministic mapping, enabling multiple candidate designs for the ill-posed inverse problem. The best generated metasurface achieves a mean percentage error of 1.39%, outperforming CMA-ES optimization (4.1% after 10 h) while requiring only about one minute for after-training inference. The model also produces lower error distributions than deterministic neural baselines for out-of-distribution spectra, highlighting the potential of diffusion models for efficient metasurface design.