Machine learning assisted analysis of visible spectroscopy in pulsed-power-driven plasmas

TL;DR

This paper demonstrates that machine learning models can accurately predict plasma ion density and electron temperature from visible emission spectra in pulsed-power-driven aluminum plasmas, enabling rapid analysis.

Contribution

It introduces a synthetic spectral dataset and compares multiple machine learning models, highlighting AutoGluon’s superior performance for plasma diagnostics.

Findings

AutoGluon achieves ~98% R2-score in predictions.

Simple models also perform with >90% R2-score.

The approach enables rapid, real-time plasma analysis.

Abstract

We use machine learning models to predict ion density and electron temperature from visible emission spectra, in a high energy density pulsed-power-driven aluminum plasma, generated by an exploding wire array. Radiation transport simulations, which use spectral emissivity and opacity values generated using the collisional-radiative code PrismSPECT, are used to determine the spectral intensity generated by the plasma along the spectrometer's line of sight. The spectra exhibit Al-II and Al-III lines, whose line ratios and line widths vary with the density and temperature of the plasma. These calculations provide a 2500-size synthetic dataset of 400-dimensional intensity spectra, which is used to train and compare the performance of multiple machine learning models on a 3-variable regression task. The AutoGluon model performs best, with an R2-score of roughly 98% for density and temperature predictions. Simpler models (random forest, k-nearest neighbor, and deep neural network) also exhibit high R2-scores (>90%) for density and temperature predictions. These results demonstrate the potential of machine learning in providing rapid or real-time analysis of emission spectroscopy data in pulsed-power-driven plasmas.