FECSG-ML: Feature Engineering for Nuclear Reaction Cross Sections Generation Using Machine Learning

Abstract

In the field of nuclear science, obtaining and utilizing nuclear data, including nuclear reaction data, nuclear structure information, and radioactive decay data, is crucial. Neutron-induced nuclear reactions, particularly nuclear cross sections data, are essential for various applications, including reactor design. The EXFOR database is the only international repository for storing nuclear reaction experimental measurement information and data. However, experimental measurement data are often scarce, subject to discrepancies, or even errors, requiring human evaluation. This process can be prone to biases and significant uncertainties. To address these challenges, this study proposes a novel framework, Feature Engineering for Nuclear Reaction Cross Section Generation using Machine Learning (FECSG-ML), which employs machine learning methods to generate nuclear cross sections data, serving as a substitute for evaluating nuclear databases. Given the limited size of the EXFOR database, training a model solely on EXFOR data could lead to underfitting. Therefore, the proposed approach utilizes transfer learning, initially pre-training the model using the ENDF/B-VIII.0 dataset and subsequently fine-tuning it with the EXFOR database. This approach ensures high accuracy where real data are available and enables the learning of characteristics of the evaluation dataset where real data are lacking. Moreover, machine learning techniques are employed to transform discrete nuclear cross sections data into a continuous format, accommodating various isotopes and predicting multiple sets of cross sections data. The framework integrates various machine learning methods and utilizes ensemble learning for result optimization. Experimental results demonstrate that the regression curves generated by the FECSG-ML model align well with EXFOR data points, outperforming the ENDF/B-VIII.0 evaluation database. Furthermore, the nuclear cross sections data generated by the FECSG-ML model are applied in the OpenMC Monte Carlo simulation program to simulate pin fuel assemblies and CANDU bundle reactors, confirming the effectiveness of the model. This study underscores the importance of accurate and reliable nuclear cross sections data and provides a method for substituting the evaluation of nuclear databases.