The primary objective of radiological environmental monitoring after a radiological emergency at a nuclear facility is acquisition of background data for the determination of protective actions for the population and the comprehensive assessment of the impact on the population residing in proximity to the nuclear facility. The responsible entities engaged in the conduct of the radiological environmental monitoring encompass government organization and nuclear licensees, operating in strict adherence to the national radiological disaster prevention framework. In accordance with the national radiological disaster prevention framework, radiation environmental monitoring is executed through the deployment of emergency response organization, and recurrent exercise drills aimed at augmenting responsible capabilities. In the context of radiation environmental monitoring, it is necessary to specify measurement parameters, monitoring location, and methodological protocols for each stage, considering potential exposure pathways. In terms of equipment, it is important to utilize mobile assets such as aerial or vehicle surveys for rapid and accurate radiation environment monitoring. Radiation disaster drills are regularly conducted, and the radiation environment monitoring field is also regularly trained to enhance response capabilities. The scale of these drills may vary, ranging from exclusive participation by nuclear licensees to joint exercises conducted by governmental agencies. This iterative process of periodic drills and equipment enhancements has led to a progressive augmentation of environmental monitoring capabilities, ensuring a well-coordinated orchestration of radiation monitoring within the framework of radiation protection. Notwithstanding these achievements, challenges in public communication regarding the decision to take protective actions and the dissemination of information to the public. Considering that the purpose of radiation environmental monitoring extends beyond safeguarding public health; it also serves to alleviate public anxiety. In the future, public communication between these stakeholders should also be included in disaster drill programs to ensure proper consultation between each stakeholder during drills and to build understanding and trust in radiation environmental monitoring. This is expected to improve the quality of radiation environmental monitoring response capabilities.

The Korea Institute of Nuclear Nonproliferation and Control (KINAC) conducts outreach to promote and educate regulated entities on the export control regime’s purpose, importance, and implementation. Outreach activities help to reduce regulatory blind spots and minimize domestic and international penalties for non-compliance. The need for outreach is growing as domestic and international policies are changing rapidly, and the scope of export regulations is expanding due to increased exports of nuclear power plants. In order to explore the long-term development direction of outreach activities, we will analyze the trends of nuclear export control and the outreach activities of related organizations. Here are some key trends in nuclear export controls. In recent years, countries worldwide have been reorganizing their supply chains for critical industries, focusing on their own and friendly countries, and strengthening their trade policies in security aspects such as export control and technology protection. Following the trend of international sanctions against Russia, the Korean government has implemented domestic export control measures similar to those of the international community, such as blocking the export of strategic goods to Russia. In addition, the number of strategic goods classifications and export licenses has been increasing as Korea promotes the export of new nuclear power plants. In line with carbon neutrality, it is expected to revitalize and diversify nuclear energy-related export businesses, such as joint research on fourth-generation nuclear power plants and SMRs. Finally, the scope of exports is expanding from ‘goods’ such as existing nuclear reactors to ‘technology’-oriented transfers. The means of technology transfer are diversifying with the development of information and communication technologies such as cloud services, email, video conferencing, and large-capacity removable storage devices. Next, look at the outreach activities of nuclear export control organizations. The Korean Security Agency of Trade and Industry (KOSTI) is an organization that implements export controls on dualuse items. It puts much effort into one-on-one consulting services with companies and has established and operated various online training programs. It also actively utilizes online promotional materials such as card news and videos. The export control agencies of major countries have a common trend of expanding outreach to research institutions, providing export control guides tailored to the characteristics of each field, holding annual seminars and conferences, and operating educational programs

This study aims to classify R&D activities related to the nuclear fuel cycle using the deep learning methodology. First, R&D data of the Republic of Korea were collected from the National Science & Technology Information Service (NTIS) for the years 2021, 2022, and 2023. We use keywords such as ‘nuclear,’ ‘uranium,’ ‘plutonium,’ and ‘thorium’ to find nuclear-related R&D projects in the NTIS database. Among the numerous R&D projects found through keyword searches, overlapping and medical-related R&D projects were excluded. Finally, 495 R&D projects conducted in 2021, 430 R&D projects conducted in 2022, and 296 R&D projects conducted in 2023 were obtained for analysis. After that, Safeguards experts determine whether the R&D projects are subject to declaration under the AP. The values of the content validity index (CVI) and content validity ratio (CVR) were used to verify whether the experts’ judgments were valid. The 1,218 collected and labeled data were then divided 8:2 into training and test datasets to see if deep learning could be applied to classify nuclear fuel cycle-related R&D activities. We use the Python and TensorFlow packages, including RNN, GRU, and CNN methods. First, the collected text information was preprocessed to remove punctuation marks and then tokenized to make it suitable for deep learning. After 20 epochs of training to classify the nuclear fuel cycle-related R&D activities, the RNN model achieved 97.30% accuracy and a 5.85% error rate on the validation dataset. The GRU model achieved 96.53% accuracy and a 9.06% error rate on the validation dataset. In comparison, the CNN model achieved 94.61% accuracy and a 2.57% error rate on the validation dataset. When applying the test dataset to each model, the RNN model had a test accuracy of 83.20%, the GRU test accuracy of 82.79%, and the CNN model had a test accuracy of 85.66% for the same dataset. This study applied deep learning models to labeled data judged by various experts, and the CNN model showed the best results. In the future, this study will continue to develop an optimum deep learning model that can classify nuclear fuel cycle-related R&D activities to achieve the purpose of safeguards measures from open-source data such as papers and articles.

Safety-related items in the decommissioning Nuclear Power Plants (NPPs) can largely consider safety for workers and residents. At this time, the effects of radioactive contamination on the Systems, Structures, and Components (SSCs) are caused by the performance of work related to Decontamination and Dismantlement (D&D) activities. Classification according to dismantling activities will be important, and the decay factor of radionuclides and the impact of contaminations due to plant characteristic (thermal and electrical capacity) in estimation of exposure dose from such activities will be considered compared to other overseas NPPs. Therefore, this study will consider some factors to consider for comparison with overseas cases in estimating worker exposure dose. To assess worker exposure doses, the classification of decommissioning activities must first be made. It should be classified including large components that can be generally considered, and the contents should be similar to compare with overseas cases. In case of decommissioned NPPs with prior experience, it is possible to predict worker’s exposure with respect to plant capacity, but this does not seem to have a specific correlation when reviewing the related data. Depending on the plant capacity, the occurrence of contamination of radioactive materials may have some correlation, but it cannot be determined that it has causality with the worker’s dose when dismantling. In addition, it is expected that the effects of workers’ exposure doses will vary depending on when the highly contaminated SSCs will be dismantled from permanent shut down. Therefore, the decay correlation coefficient for this high radiation dose works should be considered. If the high radiation dose work is performed before the base year, a correlation coefficient larger than 1 value will be applied, and in the opposite case, a value less than 1 will be applied. Whether or not to perform Full System Decontamination (FSD) is also an important consideration that affects worker dose, and correlation factors should be applied. In this study, the matters to be considered when estimating worker dose for dismantling NPPs were reviewed. This suggests factors to be reflected in the work classification and dose results for comparison with overseas NPP experiences. Therefore, when doing the workers’ dose estimation, it is necessary to derive a normalized doses considering each correlation factor when comparing with overseas cases along with dose estimation for the dismantling activities.

Satellite imagery is an effective supplementary material for detecting and verifying nuclear activities and is helpful in areas where access and information are limited, such as nuclear facilities. This study aims to build training data using high-resolution KOMPSAT-3/3A satellite images to detect and identify key objects related to nuclear activities and facilities using a semantic segmentation algorithm. First, objects of interest, such as buildings, roads, and small objects, were selected, and the primary dataset was built by extracting them from the AI dataset provided by AIHub. In addition, to reflect the features of the area of interest (e.g., Yongbyon, Pyongsan), satellite images of the area were acquired, augmented, and annotated to construct an additional dataset (approximately 150,000). Finally, we conducted three stages of quality inspection to improve the accuracy of the training data. The training dataset of this study can be applied to semantic segmentation algorithms (e.g., U-Net) to detect objects of interest related to nuclear activities and facilities. Furthermore, it can be used for pixelbased object-of-interest change detection based on semantic segmentation results for multi-temporal images.

For countering nuclear proliferation, satellite imagery is being used to monitor suspicious nuclear activities in inaccessible countries or regions. Monitoring such activities involves detecting changes over time in nuclear facilities and their surroundings, and interpreting them based on prior knowledge in terms of nuclear proliferation or weaponisation. Therefore, analysts need to acquire and analyze satellite images periodically and have an understanding of nuclear fuel cycle as well as expertise in remote sensing. Meanwhile, as accessibility of satellite information has been increasing and accordingly a large amount of high-resolution satellite images is available, a lack of experts with expertise in both fields to perform satellite imagery analysis is being concerned. In this regard, the Institute of Korea Nonproliferation and Control (KINAC) has developed a prototype of semi-automatic satellite imagery analysis system that can support monitoring of potential nuclear activities to overcome the limitations of professionals and increase analysis efficiency. The system provides a satellite imagery database that can manage acquired images, and the users can load images from the database and analyze them in stages. The system includes a preprocessing module capable of resizing, correcting and matching images, a change detection module equipped with a pixel-object-based change detection algorithm for multi-temporal images, and a module that automatically generates reports with relevant information. In particular, this system continuously updates open-source information database related to potential nuclear activities and provides users with an integrated analytics platform that can support their interpretation by linking related images and textual information together. As such, the system could save time and cost in processing and interpreting satellite images by providing semi-automated analytic workflows for monitoring potential nuclear activities.