Machine Learning Assisted Inverse Design of Pixelated mmWave Patch Antennas

Nadeem Rather; Holger Claussen; Lester Ho

eess.SPAug 24, 2026

Machine Learning Assisted Inverse Design of Pixelated mmWave Patch Antennas

Authors: Nadeem Rather, Holger Claussen, Lester Ho

Organizations: Tyndall National Institute, Dublin, Ireland · University College Cork, Ireland

Abstract

A machine learning-assisted framework for the inverse design of pixelated millimetre-wave patch antennas targeting the 22--30 GHz band is presented. The antenna surface is represented as a 19x23 binary pixel grid on a Rogers RT/duroid 5880 substrate, where each pixel is either metal or empty, with a continuous electrical path from the feed enforced by design. An initial dataset of approximately 6,000 full-wave CST simulations was collected from structured random pixel patterns, of which only around 40% achieved a resonance with |S11| <= -10 dB anywhere in the band, resulting in an imbalanced dataset. To improve simulation efficiency, an XGBoost binary classifier was trained on this data to distinguish resonant from non-resonant patterns before simulation. Using the classifier as a pre-simulation filter, an additional 4,000 patterns were selected and simulated, raising the overall proportion of resonant designs in the combined 10,000-sample dataset from approximately 40% to 52%. A hybrid CNN-BiLSTM forward surrogate was then trained on this augmented dataset to predict the full complex S11 response across 801 frequency points, using a physics-guided composite loss that explicitly emphasises resonance dip accuracy. Finally, an inverse design model was developed that optimises in a compact 64-dimensional latent space using gradient descent to generate pixel patterns matching a desired S11 specification. The results show good agreement between the surrogate-predicted and CST-simulated |S11| responses for the generated designs and demonstrate the feasibility of automatically designing and reconfiguring antenna structures.

Figures & tables

Fig. 1: Overview of an AI-assisted inverse patch antenna design process

Fig. 2: Full pixelated patch antenna surface on Rogers RT/duroid 5880 ( $16{\times}12.5$ mm, $\varepsilon_{r}{=}2.2$ , $h{=}0.508$ mm). All 300 optimisable metal pixels are shown in black. The fixed feed line (cols. 1–11, row 10) is shown in red. Grey regions are structurally excluded.

Fig. 3: End-to-end system pipeline. An XGBoost classifier screens possible patterns to augment the CST dataset. A CNN-BiLSTM forward surrogate and a convolutional AE prior are trained on the augmented dataset. The inverse optimiser searches the 64-d AE latent space through the frozen surrogate to generate antenna patterns satisfying the target $S_{11}$ specification.

Model	Acc.	F1	AUC	Train-Val Gap
Random Forest	80.1%	0.796	0.874	14.7%
XGBoost	77.4%	0.768	0.844	4.4%
LightGBM	77.2%	0.772	0.839	3.4%
SVM	75.9%	0.761	0.827	4.1%
Logistic Reg.	71.0%	0.706	0.790	3.6%

TABLE I: Classifier benchmark on the 6K balanced dataset. Best result per model across five random seeds. Bold : best per column.

Fig. 4: CNN-BiLSTM forward surrogate architecture. The spatial encoder extracts geometric features from the binary pixel pattern, the frequency projection head reshapes them into a per-frequency sequence, and the bidirectional LSTM models inter-frequency correlations to output the full complex $S_{11}$ spectrum.

Metric	Train	Val	Test
MAE, $\|S_{11}\|_{\mathrm{dB}}$	1.305	1.547	1.548
RMSE, $\|S_{11}\|_{\mathrm{dB}}$	2.218	2.725	2.735
MAE, $f_{\mathrm{res}}$ depth (dB) *	3.213	5.844	5.742
MAE, $f_{\mathrm{res}}$ centre frequency (GHz) *	0.576	0.681	0.724

TABLE II: CNN-BiLSTM forward surrogate performance metrics

Fig. 5: Inverse-designed pixelated patch antennas and their $|S_{11}|$ responses. (a)–(d) optimised pixel patterns for target bands 26.5–27.5, 22–23, 27–28, and 25 GHz respectively. (e)–(h) corresponding surrogate-predicted (dashed) vs. CST-simulated (solid) $|S_{11}|_{\mathrm{dB}}$ responses.

Explore similar work

Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design
Oct 4, 2026Avi Epstein, Snir Nehemia, Haim Suchowski +1Physics-Informed GNNs Graph Transformer
Tel Aviv University
A Bi-Stage Framework for Automatic Development of Pixel-Based Planar Antenna Structures
Mar 4, 2026Khadijeh Askaripour, Adrian Bekasiewicz, Slawomir KozielTopology Optimization
Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, Narutowicza 11/12, 80-233 Gdansk, Poland · Department of Engineering, Reykjavik University, Menntavegur 1, 102 Reykjavik, Iceland
Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments
Aug 30, 2026M. Tsukerman, K. Grotov, D. Vovchuk +1Conditional Generative Modeling Inverse Design

Oct 4, 2026J/K move · Enter open · S save

Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design

Avi Epstein, Snir Nehemia, Haim Suchowski, Lior Wolf

Tel Aviv University

Physics-Informed GNNs Graph Transformer Inverse Design

Open paper AskPDF arXiv

Full-wave electromagnetic (EM) simulation enables accurate patch-antenna analysis but is computationally expensive for large-scale forward prediction and inverse design. We present a mesh-native, physics-augmented graph-learning framework that treats radiation-pattern prediction as signal reconstruction on an irregular surface mesh. For the forward problem, a GPS graph transformer is trained with Physics-Augmented Intermediate Supervision (PAIS), an auxiliary node-level objective that predicts complex surface currents, the physical intermediate linking geometry to radiation. PAIS improves multiple GNN backbones at no inference-time cost, while shuffled-current and non-physical controls show the gain comes from physical correspondence. Direction-conditioned decoding and a differentiable radiation-integral consistency loss further exploit this structure. On an 80,000-sample CST benchmark, GPS+PAIS reaches MSE 0.17 / PSNR 19.67, generalizes to a PCA split, and transfers zero-shot to canonical patches. For inverse design, surrogate-filtered diffusion beats nearest-neighbor retrieval by 32% relative MSE.

Abstract

Explore similar work

Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design

A Bi-Stage Framework for Automatic Development of Pixel-Based Planar Antenna Structures

Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments