@article{scholars16434, year = {2022}, publisher = {Elsevier Ltd}, title = {Generation of cross section for neutron induced nuclear reaction on iridium and tantalum isotope using machine learning technique}, journal = {Applied Radiation and Isotopes}, volume = {187}, note = {cited By 0}, doi = {10.1016/j.apradiso.2022.110306}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85132228257&doi=10.1016\%2fj.apradiso.2022.110306&partnerID=40&md5=eb80b0ae70f27663a406b039a2f81917}, author = {Hamid, M. A. B. and Beh, H. G. and Shahrol Nidzam, N. N. and Chew, X. Y. and Ayub, S.}, abstract = {In this work, we proposed a new approach in generating nuclear data using machine learning techniques. This paper focused on generation of nuclear cross section for neutron induced-nuclear reaction on iridium isotopes (Ir-191) and tantalum isotopes (Ta-181) target, specifically 191Ir (n,p)191Os and 181Ta (n, 2n)180Ta using random forest algorithms. The input consists of experimental datasets obtained from EXOR and simulated datasets from TALYS 1.9. We found that the regression curve generated by our model is in good agreement with the evaluated nuclear data library ENDF/B-VII.0, which is set as the benchmark. This shows a potential in building a machine learning model for generating nuclear cross section data for both well studied and understudied nuclear reaction. {\^A}{\copyright} 2022 Elsevier Ltd}, keywords = {Decision trees; Iridium; Learning systems; Machine learning; Nuclear reactions; Tantalum, ENDF/B-VII.0; In-buildings; Machine learning techniques; New approaches; Nuclear cross sections; Nuclear data; Nuclear data library; Random forest algorithm; Regression curve; Simulated datasets, Isotopes, iridium; tantalum; isotope, Article; computer simulation; decision tree; human; machine learning; mathematical parameters; neutron; neutron radiation; random forest; simulation; machine learning, Iridium; Isotopes; Machine Learning; Neutrons; Tantalum}, issn = {09698043} }