Quantifying Uncertainty for Machine Learning Based Diagnostic

TL;DR

This paper explores methods for quantifying uncertainty in deep learning predictions of electron beam diagnostics, crucial for safe and reliable deployment in particle accelerators.

Contribution

It introduces ensemble methods and quantile regression neural networks for uncertainty quantification in diagnostic predictions.

Findings

Ensemble methods improve uncertainty estimation accuracy.

Quantile regression neural networks provide reliable confidence intervals.

Enhanced uncertainty quantification aids decision-making in safety-critical systems.

Abstract

Virtual Diagnostic (VD) is a deep learning tool that can be used to predict a diagnostic output. VDs are especially useful in systems where measuring the output is invasive, limited, costly or runs the risk of damaging the output. Given a prediction, it is necessary to relay how reliable that prediction is. This is known as 'uncertainty quantification' of a prediction. In this paper, we use ensemble methods and quantile regression neural networks to explore different ways of creating and analyzing prediction's uncertainty on experimental data from the Linac Coherent Light Source at SLAC. We aim to accurately and confidently predict the current profile or longitudinal phase space images of the electron beam. The ability to make informed decisions under uncertainty is crucial for reliable deployment of deep learning tools on safety-critical systems as particle accelerators.