Söderström P.-A.Jaworski G.Valiente Dobón J.J.Nyberg J.Agramunt J.de Angelis G.González V.2019-08-012019-08-0120190168-9002https://dx.doi.org/10.1016/j.nima.2018.11.122https://hdl.handle.net/11480/1520In 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 ? rays. Special emphasis is put on the application of artificial neural networks. The results show a systematically higher ?-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 ? 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 ?-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. © 2018eninfo:eu-repo/semantics/closedAccessBC-501ABC-537Digital pulse-shape discriminationFast-neutron detectionLiquid scintillatorNeural networksArticle91623824510.1016/j.nima.2018.11.1222-s2.0-85057630109Q1WOS:000455016800033Q3