High-order spectral deconvolution of complex x-ray distributions using machine learning
Open Access
- 1 October 2026
- journal article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (5) , 055034
Abstract
High-repetition-rate (HRR) (10 Hz) laser–plasma experiments require rapid and reliable reconstruction of x-ray spectra from scintillator-based linear absorption spectrometer measurements. The inverse problem is intrinsically ill-posed and complicated by practical detector non-idealities such as digitisation, saturation, and noise. In this work, we present a machine learning-based reconstruction framework that enables rapid spectral inference under realistic detector conditions, without a priori assumptions on spectral shape during inference. The approach separates spectral shape from flux, allowing an ensemble of neural networks to infer spectral shape from normalised detector measurements, while flux is recovered in a subsequent step. Training data comprises a collection of physically interpretable, multi-component spectra formed from mixtures of Boltzmann and skewed Gaussian components, enabling generalisation beyond simple parametric forms. Models are trained on synthetic data incorporating detector non-idealities. Comparison is performed with existing multi-parameter deconvolution method, demonstrating comparable performance in the presence of detector non-idealities, with approximately two orders of magnitude faster inference. A comprehensive evaluation is performed examining the role of training distribution, measurement-space data augmentation, and detector response. Results demonstrate robust reconstruction across diverse spectral morphologies and flux levels, with millisecond-level inference times suitable for HRR experiments.Keywords
This publication has 20 references indexed in Scilit:
- Calorimeter with Bayesian unfolding of spectra of high-flux broadband x raysReview of Scientific Instruments, 2022
- Deconvolution of multi-Boltzmann x-ray distribution from linear absorption spectrometer via analytical parameter reductionReview of Scientific Instruments, 2021
- Compact spectroscopy of keV to MeV X-rays from a laser wakefield acceleratorScientific Reports, 2021
- Development of a deep learning based automated data analysis for step-filter x-ray spectrometers in support of high-repetition rate short-pulse laser-driven acceleration experimentsReview of Scientific Instruments, 2021
- A spectrometer for ultrashort gamma-ray pulses with photon energies greater than 10 MeVReview of Scientific Instruments, 2018
- High-energy differential-filtering photon spectrometer for ultraintense laser-matter interactionsReview of Scientific Instruments, 2018
- Novel scintillator-based x-ray spectrometer for use on high repetition laser plasma interaction experimentsReview of Scientific Instruments, 2018
- Measuring fast electron spectra and laser absorption in relativistic laser-solid interactions using differential bremsstrahlung photon detectorsReview of Scientific Instruments, 2013
- A Bremsstrahlung spectrometer using k-edge and differential filters with image plate dosimetersReview of Scientific Instruments, 2008
- A practical method for estimating high-energy X-ray spectra using the iterative perturbation principle proposed by WaggenerRadiation Physics and Chemistry, 2003