Physics-Informed Residual Neural Ordinary Differential Equations for Enhanced Tropical Cyclone Intensity Forecasting
This work addresses the problem of accurate storm hazard mitigation for meteorologists and communities, representing a strong specific gain in forecasting.
The paper tackles tropical cyclone intensity forecasting by introducing a Physics-Informed Residual Neural ODE model, which achieves a 25.2% reduction in RMSE and a 19.5% increase in R2 compared to a neural network baseline on the SHIPS dataset.
Accurate tropical cyclone (TC) intensity prediction is crucial for mitigating storm hazards, yet its complex dynamics pose challenges to traditional methods. Here, we introduce a Physics-Informed Residual Neural Ordinary Differential Equation (PIR-NODE) model to precisely forecast TC intensity evolution. This model leverages the powerful non-linear fitting capabilities of deep learning, integrates residual connections to enhance model depth and training stability, and explicitly models the continuous temporal evolution of TC intensity using Neural ODEs. Experimental results in the SHIPS dataset demonstrate that the PIR-NODE model achieves a significant improvement in 24-hour intensity prediction accuracy compared to traditional statistical models and benchmark deep learning methods, with a 25. 2\% reduction in the root mean square error (RMSE) and a 19.5\% increase in R-square (R2) relative to a baseline of neural network. Crucially, the residual structure effectively preserves initial state information, and the model exhibits robust generalization capabilities. This study details the PIR-NODE model architecture, physics-informed integration strategies, and comprehensive experimental validation, revealing the substantial potential of deep learning techniques in predicting complex geophysical systems and laying the foundation for future refined TC forecasting research.