Skip to main content

Research Repository

Advanced Search

MKID digital readout tuning with deep learning

Dodkins, R.; Mahashabde, S.; O’Brien, K.; Thatte, N.; Fruitwala, N.; Walter, A.B.; Meeker, S.R.; Szypryt, P.; Mazin, B.A.

MKID digital readout tuning with deep learning Thumbnail


R. Dodkins

S. Mahashabde

N. Thatte

N. Fruitwala

A.B. Walter

S.R. Meeker

P. Szypryt

B.A. Mazin


Microwave Kinetic Inductance Detector (MKID) devices offer inherent spectral resolution, simultaneous read out of thousands of pixels, and photon-limited sensitivity at optical wavelengths. Before taking observations the readout power and frequency of each pixel must be individually tuned, and if the equilibrium state of the pixels change, then the readout must be retuned. This process has previously been performed through manual inspection, and typically takes one hour per 500 resonators (20 h for a ten-kilo-pixel array). We present an algorithm based on a deep convolution neural network (CNN) architecture to determine the optimal bias power for each resonator. The bias point classifications from this CNN model, and those from alternative automated methods, are compared to those from human decisions, and the accuracy of each method is assessed. On a test feed-line dataset, the CNN achieves an accuracy of 90% within 1 dB of the designated optimal value, which is equivalent accuracy to a randomly selected human operator, and superior to the highest scoring alternative automated method by 10%. On a full ten-kilopixel array, the CNN performs the characterization in a matter of minutes — paving the way for future mega-pixel MKID arrays.


Dodkins, R., Mahashabde, S., O’Brien, K., Thatte, N., Fruitwala, N., Walter, A., …Mazin, B. (2018). MKID digital readout tuning with deep learning. Astronomy and computing, 23, 60-71.

Journal Article Type Article
Acceptance Date Mar 2, 2018
Online Publication Date Mar 13, 2018
Publication Date Apr 1, 2018
Deposit Date Apr 10, 2018
Publicly Available Date Mar 13, 2019
Journal Astronomy and computing
Print ISSN 2213-1337
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 23
Pages 60-71
Public URL


You might also like

Downloadable Citations