Enhancing Tropical Cyclone Path Forecasting with an Improved Transformer Network

TL;DR

This paper introduces an improved Transformer-based deep learning model for more accurate, faster, and cost-effective tropical cyclone path forecasting over a 6-hour horizon, utilizing NOAA storm data.

Contribution

The study presents a novel Transformer network architecture specifically optimized for storm trajectory prediction, outperforming traditional methods in accuracy and efficiency.

Findings

Higher forecasting accuracy than traditional methods

Faster prediction process

More cost-effective approach

Abstract

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