journal article·2025-03Open access

Machine Learning Enabled LED Lighting Using Scattering Optics

Gangyi Li, Yuan Liu, Hao Liang, Xihua Wang

Advanced Optical Materials· Volume 13· Issue 9

Abstract

Abstract Illumination receives a great deal of attention as white light‐emitting diodes become energy‐efficient light sources in households and commercial buildings, on streets and highways, and at stadiums and construction sites. In general, lenses and mirrors are used to control the spatial distribution of white LED (WLED) light. Here, it is proposed to use an optical diffuser, the key device in scattering optics, to achieve a pre‐defined WLED brightness distribution by nanocrystals and machine learning. Optical diffusers are typically used to create soft light (similar brightness from any angle of view), however, here the concentration of nanocrystals in a nanocomposite film (optical diffuser) to tune its optical property at different regions is altered. Machine learning is employed to achieve the inverse design of the optical diffuser pattern controlling the WLED brightness distribution, and this design task is beyond human capacities which are carried out using the brute force approach. In the end, several pre‐defined WLED brightness distributions are demonstrated for showing the success of this efforts.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced optical system design · Optical Wireless Communication Technologies · Image Enhancement Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Electrical and Computer Engineering University of Alberta Edmonton T6G 2V4 Canada

Funding

Natural Sciences and Engineering Research Council of Canada

References (24)

Show source-provided references
1. Fischer R. F. · 2008
2. 10.1002/978111846253910.1002/9781118462539 ↗
3. 10.1364/OE.45478810.1364/OE.454788 ↗
4. 10.1038/s41467-018-04186-910.1038/s41467-018-04186-9 ↗
5. 10.1002/adom.20170043010.1002/adom.201700430 ↗
6. 10.1109/LPT.2020.304674010.1109/LPT.2020.3046740 ↗
7. 10.1115/1.404803410.1115/1.4048034 ↗
8. 10.1002/aisy.20190013210.1002/aisy.201900132 ↗
9. 10.1002/lpor.20200028710.1002/lpor.202000287 ↗
10. 10.1002/lpor.20210065810.1002/lpor.202100658 ↗
11. 10.1038/s41377-018-0060-710.1038/s41377-018-0060-7 ↗
12. 10.1021/acs.nanolett.9b0397110.1021/acs.nanolett.9b03971 ↗
13. 10.1126/sciadv.aar420610.1126/sciadv.aar4206 ↗
14. 10.1364/OE.53276110.1364/OE.532761 ↗
15. 10.1364/AO.47124310.1364/AO.471243 ↗
16. 10.1021/acs.nanolett.8b0317110.1021/acs.nanolett.8b03171 ↗
17. 10.1038/s41566-020-0685-y10.1038/s41566-020-0685-y ↗
18. 10.1038/s41467-018-07431-310.1038/s41467-018-07431-3 ↗
19. 10.1038/s41377-021-00510-z10.1038/s41377-021-00510-z ↗
20. Krizhevsky A. · Adv. Neural Inf. Process. Syst. · 2012 · 25 · 1097
21. 10.1364/AO.58.00764910.1364/AO.58.007649 ↗
22. T. S.Cohen M.Geiger J.Koehler M.Welling International Conference on Machine Learning2018.
23. 10.1029/2020MS00210910.1029/2020MS002109 ↗
24. V.Nair G.Hinton presented atProceedings of the 27th International Conference on Machine Learning (ICML‐10) Toronto Canada2010 807.