Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data

TL;DR

This paper introduces a fused deep learning model that combines past storm trajectories and atmospheric reanalysis data to improve tropical cyclone track forecasting, offering fast and potentially more accurate predictions.

Contribution

The paper presents a novel neural network approach that fuses trajectory data with atmospheric images, demonstrating improved speed and accuracy over traditional models.

Findings

Deep learning model outperforms current forecast models.

Fused data approach enhances prediction accuracy.

Forecasts are generated in seconds, enabling real-time application.

Abstract

The forecast of tropical cyclone trajectories is crucial for the protection of people and property. Although forecast dynamical models can provide high-precision short-term forecasts, they are computationally demanding, and current statistical forecasting models have much room for improvement given that the database of past hurricanes is constantly growing. Machine learning methods, that can capture non-linearities and complex relations, have only been scarcely tested for this application. We propose a neural network model fusing past trajectory data and reanalysis atmospheric images (wind and pressure 3D fields). We use a moving frame of reference that follows the storm center for the 24h tracking forecast. The network is trained to estimate the longitude and latitude displacement of tropical cyclones and depressions from a large database from both hemispheres (more than 3000 storms since 1979, sampled at a 6 hour frequency). The advantage of the fused network is demonstrated and a comparison with current forecast models shows that deep learning methods could provide a valuable and complementary prediction. Moreover, our method can give a forecast for a new storm in a few seconds, which is an important asset for real-time forecasts compared to traditional forecasts.