Machine learning modeling of the stopping power experimental data

C.C. MONTANARI; F. BIVORT HAIEK; A.M.P. MENDEZ; D. M. MITNIK

Lisbon

Conferencia; The 22nd INTERNATIONAL CONFERENCE ON ION BEAM MODIFICATION OF MATERIALS (IBMM 2022); 2022

Universidade de Lisboa, Lisbon, Portugal

The International Atomic Energy Agency (IAEA) stopping power database [1] is a valuable public resource, which is continuously updated [2], making available compilations of the experimentalmeasurements published over the last nine decades [3] to the global scientific community. The purpose of this work is to apply machine learning methods to predict the electronic stopping power cross section based on this important compilation of data. The experimental data compiled from published articles by diverse authors is not standardized. The data is presented in distinct units and formats, including the mix of stopping cross sections per atom, per molecule, per mass and also energy loss per unit path length. We devoted a significant effort in the reorganization of the database, unifying units, and arranging the data in a standard (csv) format, enabling to obtain the information easily and quickly.Considering that the database contains several dozen of thousands input values, purging manually this data requires also a considerable amount of work.To this purpose, we developed a machine learning method to clean up the existing compilation of experimental data, based on an unsupervised clustering technique (DBSCAN) which identifies outliervalues, and determines which data to keep in cases of overlapping, taking into account the year of production. The refined data is used to train a deep neural network, able to accurately reproduce theinput experimental results, and to predict new results in cases which have never been seen in the training procedure (the test set). In this opportunity, the code ESPNN (Electronic Stopping Power with NeuralNetwork), performing all these tasks will be presented, and the results discussed.