Predicting plasmonic pole representations of complex dielectric spectra using convolutional neural networks

Abstract

Extracting spectral properties such as energy position, broadening, and spectral weight from dielectric spectra is critical for interpreting collective electronic excitations in many-body physics. Conventional approaches typically rely on nonlinear fitting procedures that can be computationally demanding and highly sensitive to initialization and fitting choices. In this work, we develop a convolutional neural-network framework for the direct inversion of dielectric spectra into their underlying plasmonic pole structures using a multipole-Padé representation. Rather than training on a constrained database of spectra associated with a specific set of materials, the network is trained entirely on synthetic spectra generated from the analytical multipole-Padé expression with randomized parameters. This enables the network to learn the general mapping between the spectra and their features in an unbiased way, without requiring large, material-specific datasets derived from real materials. We demonstrate that the synthetically trained network generalizes to complex first-principles and experimental dielectric spectra, extracting the underlying pole parameters with high accuracy in a single forward pass. This approach provides an efficient and robust alternative to conventional nonlinear fitting, enabling high-throughput, automated analysis of dielectric spectra across diverse materials and applications.

Molecular Electrodynamic Relaxation in Dielectric and Plasmonic Cavities
Gang Meng, Tao E. Li
arXiv28 Oct 2026PreprintarXiv licenceFull textPhysical chemistry Computational physicsarXiv
Robust Optical Pulling of Plasmonic, Chiral, and Dielectric Nanorods in Single and Cluster Configurations Using Hyperbolic Metamaterials
Md. Al Amin Chy, Md. Ajijul Haque Sakib Opu, Md Fujael Ahmed +2
arXiv3 Oct 2026PreprintarXiv licenceFull textOptics & photonicsarXiv
Quantum convolutional neural network for predicting nuclear charge radii
Jinzhe Wu, Jianping Zhao, Tianshuai Shang +4
arXiv11 Sep 2026PreprintarXiv licenceFull textNuclear physicsarXiv
A hybrid Fourier neural operator–convolutional surrogate for predicting geometrically necessary dislocation density in polycrystalline aluminum
Yen Fred Woguem, Brieuc Conan-Guez, Frédéric Pennerath +3
HAL4 Oct 2026PreprintCC BY-ND 4.0Full textCondensed matterHAL
Predicting Weight Windows for Duct-Streaming Shielding Geometries with a Convolutional Neural Network
Jilang Miao, Ansel Kneier, Jonathan Porrazzo
arXiv29 Oct 2026PreprintCC BY-NC-ND 4.0Full textComputational physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{leon2026predicting,
  title = {{Predicting plasmonic pole representations of complex dielectric spectra using convolutional neural networks}},
  author = {Dario A. Leon},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.11698},
  eprint = {2610.11698},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11698},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Predicting plasmonic pole representations of complex dielectric spectra using convolutional neural networks
AU  - Dario A. Leon
PY  - 2026
DA  - 2026/10/08
PB  - arXiv
DO  - 10.48550/arxiv.2610.11698
UR  - https://arxiv.org/abs/2610.11698
AB  - Extracting spectral properties such as energy position, broadening, and spectral weight from dielectric spectra is critical for interpreting collective electronic excitations in many-body physics. Conventional approaches typically rely on nonlinear fitting procedures that can be computationally demanding and highly sensitive to initialization and fitting choices. In this work, we develop a convolutional neural-network framework for the direct inversion of dielectric spectra into their underlying plasmonic pole structures using a multipole-Padé representation. Rather than training on a constrained database of spectra associated with a specific set of materials, the network is trained entirely on synthetic spectra generated from the analytical multipole-Padé expression with randomized parameters. This enables the network to learn the general mapping between the spectra and their features in an unbiased way, without requiring large, material-specific datasets derived from real materials. We demonstrate that the synthetically trained network generalizes to complex first-principles and experimental dielectric spectra, extracting the underlying pole parameters with high accuracy in a single forward pass. This approach provides an efficient and robust alternative to conventional nonlinear fitting, enabling high-throughput, automated analysis of dielectric spectra across diverse materials and applications.
ER  -

Abstract

Related

Cite