Automatic Optimization of a Parallel-Plate Avalanche Counter with Optical Readout

Abstract

An automatic optimization procedure is proposed for some operational parameters of a Parallel-Plate Avalanche Counter with Optical Readout, a detector designed for heavy-ion tracking and imaging. Exploiting differentiable programming and automatic differentiation, we model the reconstruction of the position of impinging 5.5 MeV alpha particles for different detector configurations and build an optimization cycle that minimizes an objective function. We analyze the performance improvement using this method, exploring the potential of these techniques in detector design.

Keywords

• differentiable programming
• machine learning
• detector optimization
• nuclear physics