Machine learning-aided line intensity ratio technique applied to deuterium plasmas

Abstract

It has been demonstrated that the electron density, ne, and temperature, Te, are successfully evaluated from He I line intensity ratios coupled with machine learning (ML). In this paper, the ML-aided line intensity ratio technique is applied to deuterium (D) plasmas with 0.031 < ne (1018 m−3) < 0.67 and 2.3 < Te (eV) < 5.1 in the PISCES-A linear plasma device. Two line intensity ratios, Dα/Dγ and Dα/Dβ, are used to develop a predictive model for ne and Te separately. Reasonable agreement of both ne and Te with those from single Langmuir probe measurements is obtained at ne > 0.1 × 1018 m−3. Addition of the D2/Dα intensity ratio, where the D2 band emission intensity is integrated in a wavelength range of λ ∼ 557.4–643.0 nm, is found to improve the prediction of, in particular, ne, and Te. It is also confirmed that the technique works for D plasmas with 0.067 < ne (1018 m−3) < 6.1 and 0.8 < Te (eV) < 15 in another linear plasma device, PISCES-RF. The two training datasets from PISCES-A and PISCES-RF are combined, and unified predictive models for ne and Te give reasonable agreement with probe measurements in both devices.