Machine learning methods for schlieren imaging of a plasma channel in tenuous atomic vapor

• Published in: Optics and laser technology 2023-04, Vol.159, p.108948, Article 108948
• Main Authors: Bíró, Gábor, Pocsai, Mihály, Barna, Imre F., Barnaföldi, Gergely G., Moody, Joshua T., Demeter, Gábor
• Format: Article
• Language: English
• Subjects: Machine learning; Near-resonant laser probe; Plasma diagnostic; Schlieren imaging
• ISSN: 0030-3992; 1879-2545
• DOI: 10.1016/j.optlastec.2022.108948

We investigate the usage of a schlieren imaging setup to measure the geometrical dimensions of a plasma channel in atomic vapor. Near resonant probe light is used to image the plasma channel in the tenuous vapor and machine learning techniques are tested for extracting quantitative information from the images. We build a database of simulated signals with a range of plasma parameters for training Deep Neural Networks, and demonstrate that they can estimate, from the schlieren images, reliably and with high accuracy the location, the radius and the maximum ionization fraction of the plasma channel as well as the width of the transition region between the core of the plasma channel and the unionized vapor. We test several different neural network architectures with supervised learning and show that the parameter estimations supplied by the networks are resilient with respect to slight changes of the experimental parameters that may occur in the course of a measurement. •Machine learning programs can evaluate images provided by a laser probe.•The parameters of a plasma channel can be estimated quickly and accurately.•Parameter estimation works well for measurements taken under varying circumstances.