Machine Learning in Nuclear Science and Engineering Applications

Methods of ML/AI have been introduced in nuclear reactor applications during the last decades; they contribute today to enhance the safety of the current fleet of reactors. However, these statistic techniques are becoming increasingly more practical and powerful in recent years. Hence, these current developments foretell an increase of applying Machine Learning (ML) / Artificial Intelligence (AI)-based methods to solving issues pertaining to nuclear science and technology.

The paper gives an overview of ML activities to the field of nuclear science and engineering (NS&E), from reactor-oriented applications to detection-oriented applications. The paper also covers the recent successful application of ML to identify nuclear data needs and critical issues across the nuclear data pipeline, from finding the best parameter sets for nuclear reaction codes to describe a reaction to highlighting the need of new evaluations of nuclear data.

The paper concludes that fostering collaborations between nuclear engineering researchers and experts in the ML/AI community and attracting young talent to this scientific area will be critical for a successful outcome. In this sense, Universities will play an important role updating nuclear engineering academic programs with ML/AI disciplines which ensure competent graduate and undergraduate nuclear engineers familiarized with these techniques.

¡Recibe nuestra newsletter!

    The data provided by you is processed by the Spanish Nuclear Society in accordance with EU Regulation 2016/679 on Data Protection, with the purpose of managing your requests, answering queries, administrative, statistical processing and sending SNE communications, about your activity, events, etc. The transfer of data is not foreseen (unless legally required) or international data transfers; and through the Privacy Policy you have all the rights that assist you in terms of privacy.