A hybrid Machine Learning unmixing method for automatic analysis of [formula omitted]-spectra with spectral variability.

Automatic identification and quantification of γ -emitting radionuclides, taking into account spectral deformations due to γ -interactions in radioactive source surroundings, is a challenging task in the nuclear field. In that context, this paper presents a Machine Learning approach based on autoencoder that can learn a model for the spectral signatures of γ -emitters with variability. Training and test datasets were obtained by means of simulated γ -spectra computed with the Geant4 simulation code according to increasing material thicknesses (steel, lead). A novel hybrid unmixing algorithm combining a pretrained autoencoder is studied for joint estimation of spectral signatures and counting in the case of mixtures of four radionuclides (57Co, 60Co, 133Ba, 137Cs). The investigations were carried out to account for spectral deformations due to attenuation, Compton scattering and fluorescence at high and low statistics. This study demonstrates the validity of this novel hybrid approach combining Machine Learning and Maximum Likelihood for the automatic full-spectrum analysis of γ -spectra. • Hybrid γ -spectra unmixing algorithm combining Machine Learning and Maximum Likelihood. • Modeling of spectral signature deformations by autoencoder with limited data. • Geant4 simulations of spectral deformations due to physical effects. • Full-spectrum unmixing using autoencoder as a generative model of γ -spectra. • Joint estimation of spectral signatures and mixing weights for all radionuclides. [ABSTRACT FROM AUTHOR]