Authors
Tarik Siddik
Published in
Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine. Volume 240. Pages 113083. Nov 05, 2026. Epub Nov 05, 2026.
Abstract
This study evaluates the application of Artificial Neural Networks (ANNs) as a data-driven tool for estimating neutron-induced reaction cross-sections for gallium and arsenic isotopes. Specifically, the model was applied to the 69Ga(n,p)69mZn, 69Ga(n,2n)68Ga, 71Ga(n,p)71Zn, 71Ga(n,2n)70Ga, 75As(n,2n)74As, and 75As(n,p)75Ge reactions. The ANN model's performance was evaluated by comparing its numerical approximations with experimental data from the EXFOR database and with benchmarks from the nuclear reaction codes EMPIRE-3.2 Malta and TALYS 1.9 in their standard configurations. The results demonstrate that the ANN model exhibits a high degree of statistical alignment with the experimental datasets, yielding lower residual errors than the evaluated theoretical codes within the training energy ranges. These findings suggest that the ANN serves as an effective complementary tool for data evaluation and interpolation, providing a precise statistical representation of experimental trends that can supplement traditional phenomenological modeling in nuclear science and technology.
PMID:
43035067
Bibliographic data and abstract were imported from PubMed on 16 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 6
- Comments 0