Deep Learning for Hurricane Track Forecasting from Aligned Spatio-temporal Climate Datasets

Sophie Giffard-Roisin (1) , Mo Yang (2) , Guillaume Charpiat (3) , Balázs Kégl (2) , Claire Monteleoni (1)

1 University of Colorado [Boulder]
2 LAL - Laboratoire de l'Accélérateur Linéaire
3 TAU - TAckling the Underspecified

The forecast of hurricane trajectories is crucial for the protection of people and property, but machine learning techniques have been scarce for this so far. We propose a neural network fusing past trajectory data and reanalysis atmospheric images (wind and pressure 3D fields). We used 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 hurricanes 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 fusion network is demonstrated and a comparison with current forecast models shows that deep methods could provide a valuable and complementary prediction.

Domaines: Apprentissage [cs.LG]; Climatologie; Traitement des images [eess.IV]; Météorologie; Intelligence artificielle [cs.AI]

Sophie Giffard-Roisin, Mo Yang, Guillaume Charpiat, Balázs Kégl, Claire Monteleoni. Deep Learning for Hurricane Track Forecasting from Aligned Spatio-temporal Climate Datasets. Modeling and decision-making in the spatiotemporal domain NIPS workhop, Dec 2018, Montréal, Canada. ⟨hal-01905408⟩