ARTIFICIAL NEURAL NETWORKS FOR PLASMA X-RAY SPECTROSCOPIC ANALYSIS

Modem diagnostic instrumentation produces a vast amount of data that often requires substantial analysis efforts. New methods are needed to improve the efficiency of the analysis process. Artificial neural networks have been applied to a variety of signal processing and image recognition problems. The feed-forward, back-propagation technique is well suited for the analysis of scientific laboratory data, which is viewed as a pattern-matching problem. We summarize the concepts and algorithms as implemented on a personal computer, and illustrate the method using a nonlocal thermodynamic equilibrium theoretical atomic physics model for k-shell x-ray spectroscopy of a high density, high temperature aluminum plasma. Extensions to other types of spectroscopy data analysis are discussed.