LAUSR

Abstract Nuclear technology industries have increased their interest in using data-driven methods to improve safety, reliability, and availability of assets. To do so, it is important to understand the fundamentals between the disciplines to effectively develop and deploy such systems. This survey presents an overview of the fundamentals of artificial intelligence and the state of development of learning-based methods in nuclear science and engineering to identify the risks and opportunities of applying such methods to nuclear applications. This paper focuses on applications related to three key subareas related to safety and decision-making. These are reactor health and monitoring, radiation detection, and optimization. The principles of learning-based methods in these applications are explained and recent studies are explored. Furthermore, as these methods have become more practical during the past decade, it is foreseen that the popularity of learning-based methods in nuclear science and technology will increase; consequently, understanding the benefits and barriers of implementing such methodologies can help create better research plans, and identify project risks and opportunities.