# Parametric simulation dataset of a 2.4 GHz patch antenna with slot for AI-based S11 prediction

## TL;DR

This paper introduces a large dataset of simulated 2.4 GHz patch antenna designs for training AI models to predict antenna performance.

## Contribution

The dataset provides 55,000 simulation samples for AI-based S11 prediction and antenna design optimization.

## Key findings

- The dataset includes S11 values across varied geometric configurations for 2.4 GHz antennas.
- It supports machine learning in RF engineering tasks like impedance matching and bandwidth enhancement.
- Future releases will add experimental validation and impedance data for improved AI modeling.

## Abstract

This dataset comprises over 55,000 simulation samples of a microstrip patch antenna engineered for operation near the 2.4 GHz frequency band—a key spectrum for wireless communication and IoT applications. Each sample records S11 reflection coefficient values (in decibels), mapping the return loss across a broad range of geometric configurations. Data were generated over a one-month period using parameter sweeps and variation studies with CST Microwave Studio, ensuring comprehensive coverage of design possibilities. The resulting dataset serves as a substantial resource for developing and benchmarking machine learning models in antenna performance prediction, design automation, and optimization tasks including impedance matching, bandwidth enhancement, and geometric optimization in RF and microwave engineering. To promote generalizability and practical relevance for the research community, future dataset releases will incorporate experimental validation and expand target parameters to include antenna impedance, thereby improving the robustness and utility for advanced AI-driven modeling and optimization.