Detection of Thermal Events by Semi-Supervised Learning for Tokamak First Wall Safety

This article explores a semi-supervised object detection approach to detect thermal events on the internal wall of tokamaks. A huge amount of data is produced during an experimental campaign by the infrared (IR) viewing systems used to monitor the inner thermal shields during machine operation. The amount of data to be processed and analyzed is such that protecting the first wall is an overwhelming job. Automatizing this job with artificial intelligence (AI) is an attractive solution, but AI requires large labeled datasets that are not readily available for tokamak walls. Semi-supervised learning (SSL) is a possible solution to being able to train deep-learning models with a small amount of labeled data and a large amount of unlabeled data. SSL is explored as a possible tool to rapidly adapt a model trained on an experimental campaign A of tokamak WEST to a new experimental campaign B by using labeled data from campaign A, a little labeled data from campaign B, and a lot of unlabeled data from campaign B. Model performance is evaluated on two labeled datasets and two methods including SSL. SSL increased the mAP metric by over 6% points on the first smaller-scale database and over 4% points on the second larger-scale dataset depending on the method employed.