An Hourly Short-Term Sea Fog Forecasting Model for Ningbo–Zhoushan Port Based on Dynamic Graph Neural Networks

The cargo throughput of Ningbo–Zhoushan Port ranks first in the world. Sea fog critically affects production safety and operational efficiency at the port. To refine the forecasting capabilities for sea fog in the port area, this study exploits the strengths of graph neural networks (GNNs) in handling irregularly distributed meteorological station data. Based on station locations and wind direction/speed, a dynamic graph was constructed by incorporating the advection term in atmospheric motion equations. A novel forecasting framework was developed, integrating Graph Attention Networks (GAT), Long Short-Term Memory (LSTM), and multi-step classification output, to train a sea fog forecasting model. The proposed model delivers hourly rolling 24-h sea fog forecasts for 72 stations within the port area. Operational validation in 2023 demonstrates robust performance of the model in forecasting fog occurrence. For 24-h fog occurrence forecasting, the model achieves a TS score of 0.369 (F1 = 0.539), with an average TS score of 0.190 for fixed-time forecasts. The forecasting performance shows characteristic temporal decay, achieving optimal TS score (0.441) at 1-h lead time. Furthermore, the model exhibits superior capability in predicting localized patchy fog and fog evolution, outperforming conventional machine learning approaches including Random Forest and Gaussian Naive Bayes methods.