Poster

PUBDB-2025-05559

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Physics-Informed Inverse Design of Optical Coatings using a Differentiable Transfer Matrix Method

Chattopadhyay, U. (Corresponding author)Extern* ; Carstens, F. ; Steinecke, M. ; Wienke, A. ; Hartl, I.DESY* ; Ay, N. ; Heyl, C.DESY* ; Tuennermann, H.DESY*

2025

Abstract: We tackle the challenging inverse design of optical coatings using an artificial intelligence (AI) framework for optical thin-film coating design. Our approach is based on a physics-informed autoencoder with a differentiable physics decoder. Unlike data-driven approaches, our model embeds Maxwell’s equations directly through an analytical forward model, enabling end-to-end, gradient-based optimization from target optical properties to physical layer structures, without requiring any prior design examples. We demonstrate our method by designing a complex broadband mirror with a target reflectivity reaching >99% and a precise group delay dispersion of −200 fs$^2$ over the 940–1120 nm wavelength range. The AI-generated designreaches performance characteristics competitive with state-of-the-art commercial software, demonstrating a powerful and generalizable framework for solving physics-based inverse design problems.

---

Contributing Institute(s):

1. Laser Forschung und Entwicklung (FS-LA)
2. Photonics Research and Development (FS-PRI)

Research Program(s):

1. 631 - Matter – Dynamics, Mechanisms and Control (POF4-631) (POF4-631)
2. HIDSS-0002 - DASHH: Data Science in Hamburg - Helmholtz Graduate School for the Structure of Matter (2019_IVF-HIDSS-0002) (2019_IVF-HIDSS-0002)

Experiment(s):

1. No specific instrument

Appears in the scientific report 2025

---