|
|
Soderstrom, P. A. et al, Agramunt, J., Egea, J., Gadea, A., & Huyuk, T. (2019). Neutron detection and gamma-ray suppression using artificial neural networks with the liquid scintillators BC-501A and BC-537. Nucl. Instrum. Methods Phys. Res. A, 916, 238–245.
Abstract: In this work we present a comparison between the two liquid scintillators BC-501A and BC-537 in terms of their performance regarding the pulse-shape discrimination between neutrons and gamma rays. Special emphasis is put on the application of artificial neural networks. The results show a systematically higher gamma-ray rejection ratio for BC-501A compared to BC-537 applying the commonly used charge comparison method. Using the artificial neural network approach the discrimination quality was improved to more than 95% rejection efficiency of gamma rays over the energy range 150 to 1000 keV for both BC-501A and BC-537. However, due to the larger light output of BC-501A compared to BC-537, neutrons could be identified in BC-501A using artificial neural networks down to a recoil proton energy of 800 keV compared to a recoil deuteron energy of 1200 keV for BC-537. We conclude that using artificial neural networks it is possible to obtain the same gamma-ray rejection quality from both BC-501A and BC-537 for neutrons above a low-energy threshold. This threshold is, however, lower for BC-501A, which is important for nuclear structure spectroscopy experiments of rare reaction channels where low-energy interactions dominates.
|
|
|
|
Villanueva-Domingo, P., & Villaescusa-Navarro, F. (2021). Removing Astrophysics in 21 cm Maps with Neural Networks. Astrophys. J., 907(1), 44–14pp.
Abstract: Measuring temperature fluctuations in the 21 cm signal from the epoch of reionization and the cosmic dawn is one of the most promising ways to study the universe at high redshifts. Unfortunately, the 21 cm signal is affected by both cosmology and astrophysics processes in a nontrivial manner. We run a suite of 1000 numerical simulations with different values of the main astrophysical parameters. From these simulations we produce tens of thousands of 21 cm maps at redshifts 10 <= z <= 20. We train a convolutional neural network to remove the effects of astrophysics from the 21 cm maps and output maps of the underlying matter field. We show that our model is able to generate 2D matter fields not only that resemble the true ones visually but whose statistical properties agree with the true ones within a few percent down to scales 2 Mpc(-1). We demonstrate that our neural network retains astrophysical information that can be used to constrain the value of the astrophysical parameters. Finally, we use saliency maps to try to understand which features of the 21 cm maps the network is using in order to determine the value of the astrophysical parameters.
|
|
