The UK's Sellafield nuclear facility has unveiled its AI (artificial intelligence) strategy intended to improve efficiency and safety, with the goal that by 2032 "AI will be driving safer, faster and better performance across our facilities and business functions, with established advisory systems and non-safety-critical automation".

Some of the many buildings on the Sellafield site (Image: Sellafield Ltd)

The strategy suggests that Sellafield could become a world leader in the use of AI, which "is already in use at Sellafield, having demonstrated value in a number of areas and we now need to establish an enterprise-wide AI philosophy" that will "drive us towards smarter decision-making and greater automation, ultimately increasing safety and accelerating site remediation".

AI is defined in the strategy as: "Learned, automatic analysis and processing of data to support decision-making and task automation using video, images, audio, natural language, time series and other structured or unstructured data." It includes machine learning, deep learning, computer vision and natural language processing.

Among the reasons to adopt AI more widely the strategy says it can provide greater automation "to reduce difficult, hazardous tasks currently carried out by our workforce and increase nuclear safety across our facilities" and "to establish state-of-the-art monitoring of our ponds, silos, stores and buildings to ensure future site custodians have contemporary technology and data sets" and "to enable safe and effective deployment of robotic applications across our site".

The steps to achieving the vision begin with educating and informing staff about AI and to "stoke excitement in the short term and make it normal to everyday working by 2027" and includes consulting and working closely with regulators at all stages "to enable coordinated, safe, sustainable and secure adoption of AI applications".

Examples of AI uses at Sellafield include automating retrieved waste analysis and onward package labelling which "removes people from high-risk manual sampling process, speeds up retrievals operation and provides better data for lifetime management of the package".

Another example is automation of "unmanned aerial vehicle/remotely operated vehicle image analysis" which can use "computer vision to automatically detect new defects and changes in existing defects in buildings and plant" which not only speeds up onward maintenance decision-making but can "also be combined with other data sources to provide comprehensive asset risk status".

Sellafield says its strategy will be reviewed and revised every five years and key to achieving its "ambitious" timescale" will be "ensuring our regulators join us on our journey and remain supportive".

Sellafield Ltd is the organisation responsible for the safe operation and clean-up of the Sellafield site in Cumbria, UK, as a wholly-owned subsidiary of the Nuclear Decommissioning Authority. The site - which houses more than 1000 buildings - is the largest nuclear complex in Western Europe. Sellafield's nuclear facilities include those connected with the Magnox reprocessing programme, the Sellafield mixed-oxide fuel plant, the Thermal Oxide Reprocessing Plant, and nuclear waste treatment plants. It is also home to redundant facilities from defence work in the 1950s, which included making plutonium for nuclear weapons.