A paper inspired by the Cost Action CA21128-PROBONO has recently published by Serkan Akkoyun, Cafer Mert Yeşilkanat, Tuncay Bayram in Nucl. Instrum. Methods Phys. Res., Sect. B,Volume 549, April 2024, 165293
https://doi.org/10.1016/j.nimb.2024.165293
Machine learning predictions for cross-sections of 43,44Sc radioisotope production by alpha-induced reactions on Ca target
Serkan Akkoyun, Cafer Mert Yeşilkanat, Tuncay Bayram
Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms
Volume 549, April 2024, 165293
https://doi.org/10.1016/j.nimb.2024.165293
Abstract:
43,44Sc radioisotopes are an alternative to 18F in positron emission tomography. 43,44Sc radioisotopes, which can be generated at low costs by irradiating inexpensive natural Ca with alpha particles, can be produced, and distributed in a central cyclotron facility due to their relatively long half-lives. Since there is limited experimental data on the cross-sections in the literature, in this study, cross-section predictions of the production of 43,44Sc radioisotopes with alpha particles on Ca target were carried out with different machine learning approaches. In order to improve the results, the feature engineering method was applied to the variables of the cross-section predictions. Moreover, predictions have been improved with Stacked Ensemble Learning (SEL) approaches, a complex methodology that leverages the predictive capabilities of multiple underlying models to build a higher-level metamodel. We found that the best results were obtained with Bayesian Regularized Neural Network, Support Vector Regression and Stacked Ensemble Learning methods.