Tropical Storm Path Prediction Using Long Short-Term Memory Model, Similarity Measurement of Trajectories and Contextual Information
Year: 2023
Type: article
Abstract: Tropical Cyclones are natural and complex phenomena that threaten the life and property of human society.The accuracy of predicting their trajectories is critical to reducing the economic loss and saving human lives.When a storm occurs, context information such as wind speed and intensity, air pressure, storm direction, water surface temperature, etc. are effective in changing the direction of the storm trajectory.Accordingly, considering this information can improve the forecasting accuracy.Researchers have used various methods to predict the direction of the hurricane movements in order to achieve the highest accuracy in forecasting.Nowadays, deep learning methods have shown a potential capability in processing the complex data efficiently and accurately.In this paper, we used the Long Short-Term Memory method to predict the future path and location of the tropical cyclones in the North Atlantic Ocean by measuring the similarity of the tropical cyclone trajectories and taking into account the positional parameters and context information such as wind speed and storm direction.The obtained results show an improvement in the accuracy of the prediction compared to the lack of context information for the 3, 6, 9, and 12 hour time periods.If the context information is taken into account, the distance between the predicted trajectory path and the actual trajectory path has been reduced from 1.9 to 4.5 km.
DOI: 10.61186/jgit.11.2.1
Authors: Sahar Farmanifard, Ali Asghar Alesheikh, Mohammad Sharif, Danial Alizadeh
Institutions: K. N. Toosi University of Technology, University of Hormozgan
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: diamond
OpenAlex ID: W4394997841