Neural-network methods for two-dimensional finite-source reflector design
Machine Learning: Science and Technology · 01.12.2026 · 7 (6) · 065006
DOI: 10.1088/2632-2153/aeb503 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 06.11.2026. Verfasst von Roel Hacking und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Holland High Tech -TKI HSTM.
Abstract (Originalsprache)
We address the inverse problem of designing two-dimensional reflectors that transform light from a finite, extended source into a prescribed far-field distribution. We propose a neural-network parameterization of the reflector height and develop two differentiable objective functions: (i) a direct change-of-variables loss that pushes the source distribution through the learned inverse mapping, and (ii) a mesh-based loss that maps a target-space grid back to the source, integrates over intersections, and remains continuous even when the source is discontinuous. Gradients are obtained via automatic differentiation and optimized with a robust quasi-Newton method. As a comparison, we formulate a deconvolution baseline built on a simplified finite-source approximation: a one-dimensional monotone mapping is recovered from flux balance, yielding an ordinary differential equation solved in integrating-factor form; this solver is embedded in a modified Van Cittert iteration with nonnegativity clipping and a ray-traced forward operator. Across four benchmarks—continuous and discontinuous sources, and with and without minimum-height constraints—we evaluate accuracy by the ray-traced normalized mean absolute error. Our neural-network approach converges faster and achieves consistently lower errors than the deconvolution method, and handles height constraints naturally. On our two main benchmarks the neural network reduces this error to 2 × 10 − 5 for a continuous source and 5 × 10 − 5 for a discontinuous source within a few seconds of wall-clock time on a single GPU, against 4 × 10 − 3 and 5 × 10 − 2 for the deconvolution baseline after several hundred seconds—two to three orders of magnitude lower error at two orders of magnitude less wall-clock time. We discuss how the method may be extended to rotationally symmetric and full three-dimensional settings via iterative correction schemes.
Förderung
- Holland High Tech -TKI HSTM
Zitieren
APA
Hacking, R., Kusch, L., Mitra, K., Anthonissen, M., & IJzerman, W. (2026). Neural-network methods for two-dimensional finite-source reflector design. Machine Learning: Science and Technology, 7(6), 065006. https://doi.org/10.1088/2632-2153/aeb503
Vancouver
Hacking R, Kusch L, Mitra K, Anthonissen M, IJzerman W. Neural-network methods for two-dimensional finite-source reflector design. Machine Learning: Science and Technology. 2026;7(6):065006. doi:10.1088/2632-2153/aeb503
BibTeX
@article{Hacking2026,
author = {Hacking, Roel and Kusch, Lisa and Mitra, Koondanibha and Anthonissen, Martijn and IJzerman, Wilbert},
title = {Neural-network methods for two-dimensional finite-source reflector design},
journal = {Machine Learning: Science and Technology},
year = {2026},
volume = {7},
number = {6},
pages = {065006},
doi = {10.1088/2632-2153/aeb503}
}
EUVIMED