Data Science Meets Nuclear - What Data Analytics, Computational Intelligence And Machine Learning Can Contribute To Nuclear Waste Management And Nuclear Verification

Data science is multidisciplinary field that deals with the study of the all aspects of data right from its generation to processing to converting it into valuable knowledge source [1-3]. While data science has a wide range of applications, to what extent have new data science methods made their way into research related to nuclear waste management and nuclear verification? And which further research questions in these nuclear fields would particularly benefit from the use of new data science methods? In this line, the presentation has two objectives: First, to highlight the state-of-the-art of data science in nuclear waste management and nuclear verification. Second, to discuss the potential use of data science in the nuclear domain. Ideas for nuclear waste management include, e.g., i) facilitating integration, analytics and visualization of data in the comparative selection process for a geological repository site, ii) creating a virtual geological repository system, iii) geological repository monitoring over its life cycle phases. In nuclear verification, data science can make a significant contribution to, e.g., to i) unattended monitoring (seals/tags, surveillance (optical, 2D/3D laser, gamma,⋯), radiation measurements,⋯), ii) perimeter monitoring (surveillance (optical, gamma, thermal,⋯), radiation measurements,⋯), and iii) wide area monitoring (using satellite imagery, geophysical monitoring, environmental sampling,⋯).[1] U. Qamar and M.S. Raza, Data Science Concepts and Techniques with Applications, Springer, Singapore, 2020, https://doi.org/10.1007/978-981-15-6133-7[2] C. Ley and S.P.A. Bordas, “What makes Data Science different? A discussion involving Statistics2.0 and Computational Sciences,” International Journal of Data Science and Analytics 6, 167-175, 2018. https://doi.org/10.1007/s41060-017-0090-x.[3] L. Cao, Data Science Thinking, The Next Scientific, Technological and Economic Revolution, Springer, Cham, 2018, https://doi.org/10.1007/978-3-319-95092-1