Preliminary results in using Deep Learning to emulate BLOB, a nuclear interaction model

• DOI: 10.1016/j.ejmp.2020.04.005
• Publication Date: 2020-04-21T17:04:49Z
• Authors: A. Ciardiello; M. Asai; B. Caccia; G.A.P. Cirrone; M. Colonna; A. Dotti; R. Faccini; S. Giagu; A. Messina; P. Napolitani; L. Pandola; D.H. Wright; C. Mancini-Terrac...
• Keywords: SECONDARY RADIATION MEASUREMENTS; FOS: Physical sciences; Ion-therapy; [PHYS.NEXP]Physics [physics]/Nuclear Experiment [nucl-ex]; PROTON; THERAPY; Monte Carlo simulations; ION-BEAMS; PHYSICS; 03 medical and health sciences; Deep Learning; 0302 clinical medicine; Hadron-therapy; DESIGN; [INFO]Computer Science [cs]; Nuclear Experiment (nucl-ex); Nuclear Experiment; GEANT4; HE-4; [PHYS]Physics [physics]; SCANNED; Radiobiology; Computational Physics (physics.comp-ph); Physics - Medical Physics; 004; Monte Carlo simulations; Deep Learning; Nuclear reactions; Ion-therapy; Hadron-therapy; Nuclear reactions; Medical Physics (physics.med-ph); Physics - Computational Physics; Monte Carlo Method; MONTE-CARLO SIMULATIONS; RADIOTHERAPY

8 pages, 9 figures, Accepted by Physica Medica<br/>Purpose: A reliable model to simulate nuclear interactions is fundamental for Ion-therapy. We already showed how BLOB ("Boltzmann-Langevin One Body"), a model developed to simulate heavy ion interactions up to few hundreds of MeV/u, could simulate also $^{12}$C reactions in the same energy domain. However, its computation time is too long for any medical application. For this reason we present the possibility of emulating it with a Deep Learning algorithm. Methods: The BLOB final state is a Probability Density Function (PDF) of finding a nucleon in a position of the phase space. We discretised this PDF and trained a Variational Auto-Encoder (VAE) to reproduce such a discrete PDF. As a proof of concept, we developed and trained a VAE to emulate BLOB in simulating the interactions of $^{12}$C with $^{12}$C at 62 MeV/u. To have more control on the generation, we forced the VAE latent space to be organised with respect to the impact parameter ($b$) training a classifier of $b$ jointly with the VAE. Results: The distributions obtained from the VAE are similar to the input ones and the computation time needed to use the VAE as a generator is negligible. Conclusions: We show that it is possible to use a Deep Learning approach to emulate a model developed to simulate nuclear reactions in the energy range of interest for Ion-therapy. We foresee the implementation of the generation part in C++ and to interface it with the most used Monte Carlo toolkit: Geant4.<br/>