AI-based multivariate analysis of environmental radiation dose trends in Taiwan

Nuclear energy is considered a key low-carbon energy source for sustainable development; however, the potential risks of nuclear accidents necessitate effective environmental radiation dose monitoring. This study integrates radiation dose rate and precipitation data from 63 monitoring stations across Taiwan, incorporating spatial relationships among stations. A Variational Autoencoder architecture was employed to predict site-specific radiation dose rates using approximately 300 consecutive days of time-series data from 2024. Based on radiation observations from the preceding 10 min, the model achieved a mean absolute error below 0.0005 (μSv/h) for 7-min-ahead predictions. The results demonstrate strong predictive performance, while also indicating sensitivity to low radiation thresholds, which may induce periodic oscillations and increase prediction errors.