FSSDataBase: a reconstructable dataset of simulated frequency-selective surface structures and scattering responses
Abstract
Data-driven design of frequency-selective surfaces (FSSs) requires reusable datasets that link structural geometry to electromagnetic response under documented simulation conditions. Here we present FSSDataBase, an openly available collection of 5,000 procedurally generated single- and multilayer FSS unit cells simulated using Ansys HFSS. The dataset covers 10-20 GHz with transverse-electric and transverse-magnetic relfection and transmission responses, including magnitude and phase, for recorded incidence angles of 0∘ and 30∘. Each record links binary structural masks and JSON-based reconstruction metadata to raw response samples and derived magnitude labels. Structural descriptors, response-distance measures and task-oriented cost functions characterize geometric and electromagnetic variation and support screening for polarization stability, angular-selective bandwidth and matched-amplitude, 180° phase-separated structure pairs. Accompanying code supports model reconstruction, data processing and configuration-driven generation of additional samples. Beyond conditional forward modelling and response-based structure retrieval, FSSDataBase has the potential to serve as a reference dataset for deep-learning-based FSS inverse design, supporting fair comparisons across network architectures under shared data splits,input conditions and evaluation protocols.
Related
- Wavelet-scattering Signatures of Fuzzy Dark Matter in Simulated 21 cm Brightness–Temperature Maps
- Signatures of Narrowband and Ultrashort-Pulse-Like Probing in Coherent Anti-Stokes Raman Scattering Using Twin Beams and Sum-Frequency Generation Readout
- Resolving the Effects of the Mixing Process on Hierarchical Structures in Polymer Nanocomposites by Bayesian Ultra-Small-Angle X-ray Scattering Analysis
- Inverse-Designed Time-Varying Multilayers for Programmable Frequency-Momentum Light Scattering
- Zero-forward Kerker scattering via synthesized complex-frequency excitation
BibTeX
@misc{kuang2026fssdatabase,
title = {{FSSDataBase: a reconstructable dataset of simulated frequency-selective surface structures and scattering responses}},
author = {Xinke Kuang and Shiyun Ma and Yuanyuan Wang and Jiang Wu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30787},
eprint = {2609.30787},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30787},
}
RIS
TY - UNPB
TI - FSSDataBase: a reconstructable dataset of simulated frequency-selective surface structures and scattering responses
AU - Xinke Kuang
AU - Shiyun Ma
AU - Yuanyuan Wang
AU - Jiang Wu
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2609.30787
UR - https://arxiv.org/abs/2609.30787
AB - Data-driven design of frequency-selective surfaces (FSSs) requires reusable datasets that link structural geometry to electromagnetic response under documented simulation conditions. Here we present FSSDataBase, an openly available collection of 5,000 procedurally generated single- and multilayer FSS unit cells simulated using Ansys HFSS. The dataset covers 10-20 GHz with transverse-electric and transverse-magnetic relfection and transmission responses, including magnitude and phase, for recorded incidence angles of 0^∘ and 30^∘. Each record links binary structural masks and JSON-based reconstruction metadata to raw response samples and derived magnitude labels. Structural descriptors, response-distance measures and task-oriented cost functions characterize geometric and electromagnetic variation and support screening for polarization stability, angular-selective bandwidth and matched-amplitude, 180° phase-separated structure pairs. Accompanying code supports model reconstruction, data processing and configuration-driven generation of additional samples. Beyond conditional forward modelling and response-based structure retrieval, FSSDataBase has the potential to serve as a reference dataset for deep-learning-based FSS inverse design, supporting fair comparisons across network architectures under shared data splits,input conditions and evaluation protocols.
ER -