NRFormer: Nationwide Nuclear Radiation Forecasting with Spatio-Temporal Transformer
This work addresses the problem of accurate nuclear radiation prediction for individuals and governments, though it appears incremental as it builds on existing transformer-based methods with domain-specific adaptations.
The authors tackled the challenge of nationwide nuclear radiation forecasting by introducing NRFormer, a framework that integrates specialized attention modules to capture spatio-temporal dynamics, achieving superior performance against 11 baselines in experiments on two real-world datasets.
Nuclear radiation, which refers to the energy emitted from atomic nuclei during decay, poses significant risks to human health and environmental safety. Recently, advancements in monitoring technology have facilitated the effective recording of nuclear radiation levels and related factors, such as weather conditions. The abundance of monitoring data enables the development of accurate and reliable nuclear radiation forecasting models, which play a crucial role in informing decision-making for individuals and governments. However, this task is challenging due to the imbalanced distribution of monitoring stations over a wide spatial range and the non-stationary radiation variation patterns. In this study, we introduce NRFormer, a novel framework tailored for the nationwide prediction of nuclear radiation variations. By integrating a non-stationary temporal attention module, an imbalance-aware spatial attention module, and a radiation propagation prompting module, NRFormer collectively captures complex spatio-temporal dynamics of nuclear radiation. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed framework against 11 baselines.