arXiv subjects

Timo Gahlmann

Publications and source records attributed to Timo Gahlmann.

3 recordsLinked to original sources

arXiv2025

A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes

Neural networks have been demonstrated to be able to accelerate the modeling and inverse design of optical and electromagnetic devices by serving as fast surrogates for electromagnetic solvers. Nevertheless, such neural networks can be unreliable and normally require extreme amounts of data to train. Here it is shown that these limitations can be alleviated by constraining neural-network models using prior knowledge about the governing physics. We propose a universal physics-informed neural network framework for electromagnetic scattering based on the quasinormal mode expansion of the scattering matrix. The neural networks learn the resonant structure underlying the scattering spectrum, are guaranteed to obey energy conservation and causality, and are shown to have significantly improved data efficiency for photonic-crystal slabs and all-dielectric free-form metasurfaces. Furthermore, the framework allows additional problem-specific constraints, such as losslessness, symmetries, and number of modes, to be imposed manually when they are available. The method can be applied to a wide range of optical and electromagnetic devices owing to the generality of the quasinormal mode formalism.

physics.optics↗

arXiv2025

Evaluation of machine learning techniques for conditional generative adversarial networks in inverse design

Recently, machine learning has been introduced in the inverse design of physical devices, i.e., the automatic generation of device geometries for a desired physical response. In particular, generative adversarial networks have been proposed as a promising approach for topological optimization, since such neural network models can perform free-form design and simultaneously take into account constraints imposed by the device's fabrication process. In this context, a plethora of techniques has been developed in the machine learning community. Here, we study to what extent new network architectures, such as dense residual networks, and other techniques like data augmentation, and the use of noise in the input channels of the discriminator can improve or speed up neural networks for inverse design of optical metasurfaces. We also investigate strategies for improving the convergence of the training of generative adversarial networks for inverse design, e.g., temporarily freezing the discriminator weights when the model outperforms the generator and training data blurring during the early epochs. Our results show that only some of these techniques improve inverse design models in terms of accuracy and stability, but also that a combination of them can provide more efficient and robust metasurface designs.

physics.optics↗

arXiv2022

Deep neural networks for the prediction of the optical properties and the free-form inverse design of metamaterials

Many phenomena in physics, including light, water waves, and sound, are described by wave equations. Given their coefficients, wave equations can be solved to high accuracy, but the presence of the wavelength scale often leads to large computer simulations for anything beyond the simplest geometries. The inverse problem, determining the coefficients from a field on a boundary, is even more demanding, since traditional optimization requires a large number of forward problems be solved sequentially. Here we show that the free-form inverse problem of wave equations can be solved with machine learning. First we show that deep neural networks can be used to predict the optical properties of nanostructured materials such as metasurfaces. Then we demonstrate the free-form inverse design of such nanostructures and show that constraints imposed by experimental feasibility can be taken into account. Our neural networks promise automated design in several technologies based on the wave equation.

physics.comp-ph↗