Deep learning for retrieval of the internuclear distance in a molecule from interference patterns in photoelectron momentum distributions

TL;DR

This paper demonstrates that a convolutional neural network can accurately determine the internuclear distance in a molecule from photoelectron momentum distributions, even with limited training data and focal averaging effects.

Contribution

The study introduces a neural network approach for extracting molecular internuclear distances from photoelectron data, showing high accuracy with small datasets and robustness to focal averaging.

Findings

Neural network predicts internuclear distance with less than 0.1 a.u. error.

Performance remains good under focal averaging conditions.

Small dataset suffices for accurate predictions.

Abstract

We use a convolutional neural network to retrieve the internuclear distance in the two-dimensional H$_2^{+}$ molecule ionized by a strong few-cycle laser pulse based on the photoelectron momentum distribution. We show that a neural network trained on a relatively small dataset consisting of a few thousand of images can predict the internuclear distance with an absolute error less than 0.1 a.u. We study the effect of focal averaging, and we find that the convolutional neural network trained using the focal averaged electron momentum distributions also shows a good performance in reconstructing the internuclear distance.