Enhancing Tropical Cyclone Path Forecasting with an Improved Transformer Network

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Van Thanh, Nguyen, Huynh, Nguyen Dang, Tan, Nguyen Ngoc, Minh, Nguyen Thai, Hoang, Nguyen Nam
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912357049958400
author Van Thanh, Nguyen
Huynh, Nguyen Dang
Tan, Nguyen Ngoc
Minh, Nguyen Thai
Hoang, Nguyen Nam
author_facet Van Thanh, Nguyen
Huynh, Nguyen Dang
Tan, Nguyen Ngoc
Minh, Nguyen Thai
Hoang, Nguyen Nam
contents A storm is a type of extreme weather. Therefore, forecasting the path of a storm is extremely important for protecting human life and property. However, storm forecasting is very challenging because storm trajectories frequently change. In this study, we propose an improved deep learning method using a Transformer network to predict the movement trajectory of a storm over the next 6 hours. The storm data used to train the model was obtained from the National Oceanic and Atmospheric Administration (NOAA) [1]. Simulation results show that the proposed method is more accurate than traditional methods. Moreover, the proposed method is faster and more cost-effective
format Preprint
id arxiv_https___arxiv_org_abs_2505_00495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Tropical Cyclone Path Forecasting with an Improved Transformer Network
Van Thanh, Nguyen
Huynh, Nguyen Dang
Tan, Nguyen Ngoc
Minh, Nguyen Thai
Hoang, Nguyen Nam
Machine Learning
Performance
A storm is a type of extreme weather. Therefore, forecasting the path of a storm is extremely important for protecting human life and property. However, storm forecasting is very challenging because storm trajectories frequently change. In this study, we propose an improved deep learning method using a Transformer network to predict the movement trajectory of a storm over the next 6 hours. The storm data used to train the model was obtained from the National Oceanic and Atmospheric Administration (NOAA) [1]. Simulation results show that the proposed method is more accurate than traditional methods. Moreover, the proposed method is faster and more cost-effective
title Enhancing Tropical Cyclone Path Forecasting with an Improved Transformer Network
topic Machine Learning
Performance
url https://arxiv.org/abs/2505.00495