Cover Story：Saetchnikov A V, Tcherniavskaia E A, Saetchnikov V A, Ostendorf A. Deep-learning powered whispering gallery mode sensor based on multiplexed imaging at fixed frequency. Opto-Electron Adv 3, 200048 (2020).

Whispering gallery modes (WGMs) are standing waves occurring in circular microresonators. Due to the high sensitivity of the respective electromagnetic field distribution to the environmental conditions, WGM-based sensing is a prominent optical label-free solution for detection of various physical and chemical parameters. However, the widespread utilization of the approach has been hindered so far by the restricted applicability of the known configurations outside the laboratory conditions and their low affordability. The research group at the Applied Laser Technologies from the Ruhr University Bochum in cooperation with the researchers from the Belarusian State University reported the first realization of an affordable WGM sensor powered by deep learning and multi-resonator imaging via the fixed-frequency illumination with a cost- and energy-effective laser source. The AI-inspired processing engine enabled direct quantification of the ambient parameters where the preliminary information or follow-up sensing response interpretation procedures are redundant. The refractive index unit prediction accuracy is characterized by an absolute error at 3×10-6 level for dynamic range of the RIU variations from 0 to 2×10-3 with temporal resolution of several milliseconds and instrument-driven detection limit of 3×10-5. The reported results are expected to have a great impact on the shift of the whole sensing paradigm from the model-based to the flexible self-learning solutions.