Smart on-chip Fourier-transform spectrometers harnessing machine learning algorithms

Alaine Herrero-Bermello, Jiangfeng Li, Mohammad Khazaei, Yuri Grinberg, Aitor Villafranca-Velasco, Martin Vachon, Pavel Cheben, Lina Stankovic, Vladimir Stankovic, Dan-Xia Xu, Jens H. Schmid, Carlos A. Alonso-Ramos

Research output: Contribution to conferenceAbstractpeer-review

19 Downloads (Pure)


Miniaturized silicon photonics spectrometers have great potential for mass market applications like medicine and hazard detection. However, the performance of state-of-the-art silicon spectrometers is limited by fabrication imperfections and temperature variations. In this work, we present a fundamentally new strategy that combines machine learning algorithms and on-chip spatial heterodyne Fourier-transform spectroscopy to identify specific absorption features operated under a wide range of temperatures in the presence of fabrication imperfections. We experimentally show differentiation of four different input spectra with unknown temperature variations as large as 10 °C. This is about 100x increase in operational range, compared to state-of-the-art retrieval techniques.
Original languageEnglish
Number of pages1
Publication statusPublished - 6 Feb 2020
EventSPIE Photonics West OPTO - San Francisco, United States
Duration: 1 Feb 20206 Feb 2020


ConferenceSPIE Photonics West OPTO
Country/TerritoryUnited States
CitySan Francisco
Internet address


  • silicon
  • spectrometers
  • machine learning


Dive into the research topics of 'Smart on-chip Fourier-transform spectrometers harnessing machine learning algorithms'. Together they form a unique fingerprint.

Cite this