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 gamma-ray detectors from experimental spectra. Segmented gamma-ray total absorption spectrometers (TAS) allow for the simultaneous measurement of individual gamma-ray energy (E-gamma) and total excitation energy (E-x). Analysis of TAS detector data is complicated by the fact that the E-x and E-gamma quantities are correlated, and therefore, techniques that simply unfold using E-x and E-gamma response functions independently are not as accurate. In this work, we investigate the use of conditional generative adversarial networks (cGANs) to simultaneously unfold E-x and E-gamma data in TAS detectors. Specifically, we employ a Pix2Pix cGAN, a generative modeling technique based on recent advances in deep learning, to treat (E-x,E- E-gamma) matrix unfolding as an image-to-image translation problem. We present results for simulated and experimental matrices of single-gamma and double-gamma decay cascades. Our model demonstrates characterization capabilities within detector resolution limits for upwards of 93% of simulated test cases.