Artificial Neural Networks for Noise Removal in Data-Sparse Charged Particle Imaging Experiments.

We present the first demonstration of artificial neural networks (ANNs) for the removal of Poissonian noise in charged particle imaging measurements with very low overall counts. The approach is successfully applied to both simulated and real experimental image data relating to the detection of photoions/photoelectrons in unimolecular photochemical dynamics studies. Specific examples consider the multiphoton ionization of pyrrole and (S)-camphor. Our results reveal an extremely high level of performance, with the ANNs transforming images that are unusable for any form of quantitative analysis into statistically reliable data with an impressive similarity to benchmark references. Given the widespread use of charged particle imaging methods within the chemical dynamics community, we anticipate that the use of ANNs has significant potential impact - particularly, for example, when working in the limit of very low absorption/photoionization cross-sections, or when attempting to reliably extract subtle image features originating from phenomena such as photofragment vector correlations or photoelectron circular dichroism.