Prediction of Exotic (n,2n) Cross Sections Using a Regression Tree Machine Learning Algorithm

The XGBoost machine learning algorithm for regression was used to predict (n,2n) microscopic cross sections by training models on physical parameters describing various target nuclei and their corresponding evaluated (n,2n) cross sections sourced from ENDF/B-VIII. Research was concentrated on nuclides with nucleon numbers 30 (Formula presented.) A (Formula presented.) 208. Machine learning predictions were compared to library evaluations from ENDF/B-VIII, JENDL-5, JEFF-3.3, CENDL-3.2, and TENDL-2021. Predictions for many nuclides were found to be in agreement with existing evaluated cross sections, with (Formula presented.) 0.95, with respect to at least one library evaluation found for 73.5 ± 1.0% of nuclides in ENDF/B-VIII. Predictions were subsequently made on a wide range of exotic nuclides and compared to evaluations from the TENDL-2021 and JENDL-5 libraries.