Atmospheric droplet detection and classification with self-mixing interferometry and neural networks
Applied Optics · 10.05.2026 · 65 (14) · 4797
DOI: 10.1364/ao.592122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, online erschienen am 06.05.2026. Verfasst von Robin Matha und 3 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
Self-mixing interferometry presents obvious advantages (simplicity, energy consumption, and robustness) for airborne operation. We design an experimental system able to model several atmospheric conditions in terms of water droplet sizes and use a self-mixing interferometer to probe these droplets. We design a small (embeddable) neural network and train it to classify the different types of self-mixing signals in the presence of different types of droplets in a laboratory context. Our results open the way for AI-enabled self-mixing sensors for atmospheric condition monitoring and early warnings of icing conditions. We obtain more than 93% discrimination accuracy in this laboratory setting, but further validation of the approach for airborne operation requires testing in high-speed conditions.
Zitieren
APA
Matha, R., Colas, F., Gustave, F., & Barland, S. (2026). Atmospheric droplet detection and classification with self-mixing interferometry and neural networks. Applied Optics, 65(14), 4797. https://doi.org/10.1364/ao.592122
Vancouver
Matha R, Colas F, Gustave F, Barland S. Atmospheric droplet detection and classification with self-mixing interferometry and neural networks. Applied Optics. 2026;65(14):4797. doi:10.1364/ao.592122
BibTeX
@article{Matha2026,
author = {Matha, Robin and Colas, Florent and Gustave, François and Barland, Stephane},
title = {Atmospheric droplet detection and classification with self-mixing interferometry and neural networks},
journal = {Applied Optics},
year = {2026},
volume = {65},
number = {14},
pages = {4797},
doi = {10.1364/ao.592122}
}
EUVIMED