Towards Neural-Network-based optical temperature sensing of Semiconductor Membrane External Cavity Laser

Abstract

A machine-learning non-contact method to determine the temperature of a laser gain medium via its laser emission with a trained few-layer neural net model is presented. The training of the feed-forward Neural Network (NN) enables the prediction of the device's properties solely from spectral data, here recorded by visible-/nearinfrared-light compact micro-spectrometers for both a diode pump laser and optically-pumped gain membrane of a semiconductor disk laser. Fiber spectrometers are used for the acquisition of large quantities of labelled intensity data, which can afterwards be used for the prediction process. Such pretrained deep NNs enable a fast, reliable and easy way to infer the temperature of a laser system such as our Membrane External Cavity Laser, at a later monitoring stage without the need of additional optical diagnostics or read-out temperature sensors. With the miniature mobile spectrometer and the remote detection ability, the temperature inference capability can be adapted for various laser diodes using transfer learning methods with pretrained models. Here, mean-square-error values for the temperature inference corresponding to sub-percent accuracy of our sensor scheme are reached, while computational cost can be saved by reducing the network depth at the here displayed cost of accuracy, as appropriate for different application scenarios.

Figures (3)

• Figure 1: (a) Sketch of the working principle. The laser signal from our employed semiconductor device is captured by spectrometers, two for the VIS and one for NIR spectral range. The captured spectra are prepared for insertion into the NN when matching the input layer structure. After training with labelled data, the few-layer NN model infers the temperature owing to a supervised learning technique. For a given input spectrum, a temperature value is deduced.
• Figure 2: a) Sketch of the measurement arrangement for the acquisition of the laser system's spectral signature. Laser light is detected after back-scattering in free-space from an arbitrary screen (here power meter sensor head) by the fiber-coupled (orange lines) mini-spectrometers' detector for individual temperature settings. Here, the close-cycle water cooling (tubes drawn in red) and thermo-electric cooling device (wiring drawn in blue) act simultaneously for temperature control of the membrane gain chip, both adjusted and monitored software-wise. b)VIS raw spectra as recorded after the 50:50 (%) splitter on the respective fiber-coupled spectrometer (fiber 2). c) NIR raw spectra as recorded after the same beam splitter on the respective fiber-coupled spectrometer (NIR). The minimum detectable wavelength is indicated by a vertical black line at $900nm$.
• Figure :