Eur. Phys. J. D (2013) 67: 130
https://doi.org/10.1140/epjd/e2013-40111-9

Regular Article

Applications of artificial neural networks to proton-impact ionization double differential cross sections

¹ Physics Department, Henderson State University, 1100 Henderson St, Arkadelphia, AR 71999, USA
² Department of Chemistry, University of Arkansas at Little Rock, Little Rock, AR 72204, USA

^a e-mail: harrisal@hsu.edu

Received: 28 February 2013
Received in final form: 27 April 2013
Published online: 27 June 2013

Abstract

We use artificial neural networks (ANNs) to study proton impact single ionization double differential cross sections of atoms and molecules. While widely used in other fields, to our knowledge, this is the first time that an ANN has been used to study differential cross sections for atomic collisions. ANNs are trained to learn patterns in data and make predictions for cases where no data exists. We test the validity of the ANN’s predictions by comparing them to known measurements and find that the ANN does an excellent job of predicting the known data. We then use the ANN to make predictions of cross sections where no data currently exists.