Neural network-based source biasing to speed-up challenging MCNP simulations

•Thick shields and numerous penetrations in nuclear facilities necessitate advanced variance reduction techniques for accurate.•Proposed a groundbreaking variance reduction technique employing source biasing with the assistance of a deep neural network.•The method leverages iterative neural network training to predict source contributions to a tally.•Achieved a higher Figure of Merit (FOM), than the analogous case, in a few iterations. Nuclear analysis of fusion facilities, especially in the context of ITER, is complex due to the need for precise modeling of complex geometry and radiation sources. Monte Carlo (MC) codes, such as MCNP, are used in this context due to their high precision and capability to deal with these cases. To speed up calculations, variance reduction (VR) techniques are crucial for carrying out the simulations in reasonable times. Particularly, the cases where only a small source phase space contributes significantly to the tally must be optimized by an exhaustive sampling of this phase space. This paper introduces a novel VR method for optimizing the calculation. This method obtains the histories that contribute most to the tally and uses this information for a neural network (NN) to sample the source´s phase space. Here we present a preliminary implementation of the method to study its viability in complex cases. The method's efficacy is demonstrated in a representative source-geometry configuration, significantly reducing computational time for the tally convergence. The promising results suggest applicability to more intricate ITER-like scenarios, prompting further development.