Deep Learning for Hurricane Track Forecasting from Aligned Spatio-temporal Climate Datasets - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

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

Abstract

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.
Fichier principal
Vignette du fichier
workshop_nips_2018.pdf (4.45 Mo) Télécharger le fichier
MAE_simple.pdf (27.54 Ko) Télécharger le fichier
all_storms_since1979_IBTrRACKS_newcats.png (1.46 Mo) Télécharger le fichier
fusion_network.pdf (504.88 Ko) Télécharger le fichier
hermine_subplots_results.pdf (114.31 Ko) Télécharger le fichier
hermine_wiki.png (1.61 Mo) Télécharger le fichier
hurricane_schema.pdf (280.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)

Dates and versions

hal-01905408 , version 1 (25-10-2018)

Identifiers

  • HAL Id : hal-01905408 , version 1

Cite

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⟩
387 View
226 Download

Share

Gmail Facebook X LinkedIn More