On-chip Fourier-transform spectrometers and machine learning : a new route to smart photonic sensors

Herrero-Bermello, Alaine and Li, Jiangfeng and Khazaei, Mohammad and Grinberg, Yuri and Vellasco, Aitor V. and Vachon, Martin and Cheben, Pavel and Stankovic, Lina and Stankovic, Vladimir and Xu, Dan-Xia and Schmid, Jens H. and Alonso-Ramos, Carlos (2019) On-chip Fourier-transform spectrometers and machine learning : a new route to smart photonic sensors. Optics Letters. ISSN 0146-9592 (In Press)

[img] Text (Herrero-Bermello-etal-OL2019-On-chip-Fourier-transform-spectrometers-and-machine-learning)
Herrero_Bermello_etal_OL2019_On_chip_Fourier_transform_spectrometers_and_machine_learning.pdf
Accepted Author Manuscript
Restricted to Repository staff only until 4 November 2020.

Download (1MB) | Request a copy from the Strathclyde author

    Abstract

    Miniaturized silicon photonics spectrometers capable of detecting specific absorption features have great potential for mass market applications in medicine, environmental monitoring, and hazard detection. However, state-of-the-art silicon spectrometers are limited by fabrication imperfections and environmental conditions, especially temperature variations, since uncontrolled temperature drifts of only 0.1 °C distort the retrieved spectrum precluding the detection and classification of the absorption features. Here, we present a new strategy that exploits the robustness of machine learning algorithms to signal imperfections, enabling recognition of specific absorption features in a wide range of environmental conditions. We combine on-chip spatial heterodyne Fourier-transform spectrometers and supervised learning to classify different input spectra in the presence of fabrication errors, without temperature stabilization or monitoring. We experimentally show differentiation of four different input spectra under an uncontrolled 10 °C range of temperatures, about 100x increase in operational range, with a success rate up to 82.5% using state-of-the-art support vector machines and artificial neural networks.