Neural Network Emulation of Flow in Heavy-Ion Collisions at Intermediate Energies

Abstract

Applications of new techniques in machine learning are speeding up progress in research in various fields. In this work, we construct and evaluate a deep neural network (DNN) to be used within a Bayesian statistical framework as a faster and more reliable alternative to the Gaussian Process (GP) emulator of an isospin-dependent Boltzmann-Uehling-Uhlenbeck (IBUU) transport model simulator of heavy-ion reactions at intermediate beam energies. We found strong evidence of DNN being able to emulate the IBUU simulator's prediction on the strengths of protons' directed and elliptical flow very efficiently even with small training datasets and with accuracy about ten times higher than the GP. Limitations of our present work and future improvements are also discussed.

arXiv commentAdded more results and discussions. Phys. Rev. C in press

References in corpus (43)

• Recent Progress and New Challenges in Isospin Physics with Heavy-Ion Reactions
• Methods for analyzing anisotropic flow in relativistic nuclear collisions
• Optimal Ratio for Data Splitting
• Transverse momentum analysis of collective motion in relativistic nuclear collisions
• Applying Bayesian parameter estimation to relativistic heavy-ion collisions: simultaneous characterization of the initial state and quark-gluon plasma medium
• Isospin Physics in Heavy-Ion Collisions at Intermediate Energies
• Nucleon-nucleon cross sections in neutron-rich matter and isospin transport in heavy-ion reactions at intermediate energies
• Machine Learning in Nuclear Physics
• Effects of momentum-dependent symmetry potential on heavy-ion collisions induced by neutron-rich nuclei
• Nucleon Effective Masses in Neutron-Rich Matter
• Dense Nuclear Matter Equation of State from Heavy-Ion Collisions
• Constraining the Eq. of State of Super-Hadronic Matter from Heavy-Ion Collisions
• Flow systematics from SIS to SPS energies
• Determining Fundamental Properties of Matter Created in Ultrarelativistic Heavy-Ion Collisions
• Momentum dependence of the symmetry potential and nuclear reactions induced by neutron-rich nuclei at RIA
• Get on the BAND Wagon: A Bayesian Framework for Quantifying Model Uncertainties in Nuclear Dynamics
• Taming nuclear complexity with a committee of multilayer neural networks
• Directed, elliptic and higher order flow harmonics of protons, deuterons and tritons in Au+Au collisions at $\sqrt{s_{NN}}=2.4$ GeV
• Quantifying properties of hot and dense QCD matter through systematic model-to-data comparison
• Off shell behaviour of the in medium nucleon-nucleon cross section
• Elliptic flow in intermediate energy heavy ion collisions and in-medium effects
• Exploring QCD matter in extreme conditions with Machine Learning
• In-medium NN cross sections determined from stopping and collective flow in intermediate-energy heavy-ion collisions
• Elliptic flow in heavy ion collisions near the balance energy
• Towards a Deeper Understanding of How Experiments Constrain the Underlying Physics of Heavy-Ion Collisions
• Nuclear masses learned from a probabilistic neural network
• Differential flow in heavy-ion collisions at balance energies
• QCD Equation of State of Dense Nuclear Matter from a Bayesian Analysis of Heavy-Ion Collision Data
• Nuclear stopping and flow in heavy ion collisions and the in-medium NN cross section
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Accessing the in-medium effects on nucleon-nucleon elastic cross section with collective flows and nuclear stopping
• Optimizing multilayer Bayesian neural networks for evaluation of fission yields
• Bayesian quantification of strongly-interacting matter with color glass condensate initial conditions
• Self-learning Emulators and Eigenvector Continuation
• Effects of in-medium nucleon-nucleon cross section on collective flow and nuclear stopping in heavy-ion collisions in the Fermi-energy domain
• Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model
• Machine Learning for the Prediction of Converged Energies from Ab Initio Nuclear Structure Calculations
• Empirical radius formulas for canonical neutron stars from bidirectionally selecting EOS features in extended Bayesian analyses of observational data
• A novel Machine-Learning method for spin classification of neutron resonances
• Neural Network Emulation of Spontaneous Fission
• Bayesian inference of in-medium baryon-baryon scattering cross sections from HADES proton flow data
• A Neural Network Approach for Orienting Heavy-Ion Collision Events
• Computational budget optimization for Bayesian parameter estimation in heavy ion collisions

Cited by in corpus (2)

• Evolutions of in-medium baryon-baryon scattering cross sections and stiffness of dense nuclear matter from Bayesian analyses of FOPI proton flow excitation functions
• Bayesian inference of nuclear incompressibility from collective flow in mid-central Au+Au collisions at 400--1500 MeV/nucleon