TorchGDM: A GPU-Accelerated Python Toolkit for Multi-Scale Electromagnetic Scattering with Automatic Differentiation
arXiv:2505.09545 · doi:10.21468/SciPostPhysCodeb.60
Abstract
We present "torchGDM", a numerical framework for nano-optical simulations based on the Green's Dyadic Method (GDM). This toolkit combines a hybrid approach, allowing for both fully discretized nano-structures and structures approximated by sets of effective electric and magnetic dipoles. It supports simulations in three dimensions and for infinitely long, two-dimensional structures. This capability is particularly suited for multi-scale modeling, enabling accurate near-field calculations within or around a discretized structure embedded in a complex environment of scatterers represented by effective models. Importantly, torchGDM is entirely implemented in PyTorch, a well-optimized and GPU-enabled automatic differentiation framework. This allows for the efficient calculation of exact derivatives of any simulated observable with respect to various inputs, including positions, wavelengths or permittivity, but also intermediate parameters like Green's tensor components, which can be interesting for physics informed deep learning applications. We anticipate that this toolkit will be valuable for applications merging nano-photonics and machine learning, as well as for solving nano-photonic optimization and inverse problems, such as the global design and characterization of metasurfaces, where optical interactions between structures are critical.
24 pages, 16 figures
References in corpus (40)
- MNPBEM - A Matlab toolbox for the simulation of plasmonic nanoparticles
- Strong magnetic response of submicron Silicon particles in the infrared
- An electromagnetic multipole expansion beyond the long-wavelength approximation
- Inverse design of photonic crystals through automatic differentiation
- Data-Driven Design for Metamaterials and Multiscale Systems: A Review
- Simulating electron energy loss spectroscopy with the MNPBEM toolbox
- Plasmonics simulations with the MNPBEM toolbox: Consideration of substrates and layer structures
- Artificial Neural Network with Physical Dynamic Metasurface Layer for Optimal Sensing
- Magneto-electric point scattering theory for metamaterial scatterers
- RETICOLO software for grating analysis
- Fundamental limitations of Huygens metasurfaces for optical beam shaping
- Spatial coherence in complex photonic and plasmonic systems
- Generalization of the coupled dipole method to periodic structures
- SMUTHI: A python package for the simulation of light scattering by multiple particles near or between planar interfaces
- A newcomer's guide to deep learning for inverse design in nano-photonics
- pyGDM -- A python toolkit for full-field electro-dynamical simulations and evolutionary optimization of nanostructures
- Describing meta-atoms using the exact higher-order polarizability tensors
- The local density of optical states of a metasurface
- Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
- Global polarizability matrix method for efficient modeling of light scattering by dense ensembles of non-spherical particles in stratified media
- pyGDM -- new functionalities and major improvements to the python toolkit for nano-optics full-field simulations
- User Guide for the Discrete Dipole Approximation Code DDSCAT 7.0
- Brewster quasi bound states in the continuum in all-dielectric metasurfaces from single magnetic-dipole resonance meta-atoms
- Decay Rate of Magnetic Dipoles near Non-magnetic Nanostructures
- Designing Collective Non-local Responses of Metasurfaces
- Nanoparticle lattices with bases: Fourier modal method and dipole approximation
- Nanophotonic resonance modes with the nanobem toolbox
- Inverse Design of All-dielectric Metasurfaces with Bound States in the Continuum
- T-matrix representation of optical scattering response: Suggestion for a data format
- Polarizabilities of complex individual dielectric or plasmonic nanostructures
- Multiple scattering of light in nanoparticle assemblies: user guide for the TERMS program
- Designing Multi-functional Metamaterials
- Inverse-designed dispersive time-varying nanostructures
- Inverse Design of Unitary Transmission Matrices in Silicon Photonic Coupled Waveguide Arrays using a Neural Adjoint Model
- A framework to compute resonances arising from multiple scattering
- FDTD Modeling of Periodic Structures: A Review
- A flexible framework for large-scale FDTD simulations: open-source inverse design for 3D nanostructures
- Meent: Differentiable Electromagnetic Simulator for Machine Learning
- Electromagnetic Multipole Theory for Two-dimensional Photonics
- Generalizing the exact multipole expansion: Density of multipole modes in complex photonic nanostructures