Two-dimensional total absorption spectroscopy with conditional generative adversarial networks

We explore the use of machine learning techniques to remove the response of large volume γ-ray detectors from experimental spectra. Segmented γ-ray total absorption spectrometers (TAS) allow for the simultaneous measurement of individual γ-ray energy (Eγ) and total excitation energy (Ex). Analysis of TAS detector data is complicated by the fact that the Ex and Eγ quantities are correlated, and therefore, techniques that simply unfold using Ex and Eγ response functions independently are not as accurate. In this work, we investigate the use of conditional generative adversarial networks (cGANs) to simultaneously unfold Ex and Eγ data in TAS detectors. Specifically, we employ a textttPix2Pix cGAN, a generative modeling technique based on recent advances in deep learning, to treat rawmatrix~ matrix unfolding as an image-to-image translation problem. We present results for simulated and experimental matrices of single-γ and double-γ decay cascades. Our model demonstrates characterization capabilities within detector resolution limits for upwards of 93% of simulated test cases.