Artificial intelligence (AI) is regarded as one of the most disruptive technology of the century and with countless applications. What does it mean for radiation protection? This article describes the fundamentals of machine learning (ML) based methods and presents the inaugural applications in different fields of radiation protection. It is foreseen that the usage of AI will increase in radiation protection. Consequently, this article explores some of the benefits and also the potential barriers and questions, including ethical ones, that can come out. The article proposes that collaboration between radiation protection professionals and data scientist experts can accelerate and guide the development of the algorithms for effective scientific and technological outcomes.

No abstract

IAEA's (International Atomic Energy Agency) publication SSG-26 defines a methodology for calculating A1/A2 values. These values were conceived as limits for the transport of radioactive goods, to limit the public's exposure to radiation in the event of an accident. The limits ensure people involved in an accident receive an effective dose of no more than 50 mSv and a skin equivalent dose no greater than 500 mSv. The current values are based on five exposure scenarios taken from the Q-System, described in 1996. In 2013, the IAEA commissioned an international working group to improve the Q-System and calculate new limits for the transport of radioactive material. Within this working group, CERN has developed a set of models and an associated mathematical framework, and compiled them in a single piece of software. The primary purpose of the software is to compute and compare values produced by the different models under discussion. Later, the software could be distributed in a lighter version which will include the agreed upon regulatory model to determine the A1/A2 values.