ISSN :2582-9793

Forecasting Formation of a Tropical Cyclone using Reanalysis Data

Original Research (Published On: 29-Sep-2024 )
Forecasting Formation of a Tropical Cyclone using Reanalysis Data
DOI : https://dx.doi.org/10.54364/AAIML.2024.43158

Sandeep Kumar, Koushik Biswas and Ashish Kumar Pandey

Adv. Artif. Intell. Mach. Learn., 4 (3):2718-2730

Sandeep Kumar : University of Delhi

Koushik Biswas : IIIT Delhi

Ashish Kumar Pandey : IIIT Delhi

Download PDF Here

DOI: https://dx.doi.org/10.54364/AAIML.2024.43158

Article History: Received on: 15-Jul-24, Accepted on: 22-Sep-24, Published on: 29-Sep-24

Corresponding Author: Sandeep Kumar

Email: sandeep_kumar@sbs.du.ac.in

Citation: Sandeep Kumar, Koushik Biswas, Ashish Kumar Pandey. (2024). Forecasting Formation of a Tropical Cyclone using Reanalysis Data. Adv. Artif. Intell. Mach. Learn., 4 (3 ):2718-2730.


Abstract

    

The tropical cyclone formation process is one of the most complex natural phenomena which is governed by various atmospheric, oceanographic, and geographic factors that varies with time and space. Despite several years of research, accurately predicting tropical cyclone formation remains a challenging task. While the existing numerical models have inherent limitations, the machine learning models fail to capture the spatial and temporal dimensions of the causal factors behind TC formation. In this study, a deep learning model has been proposed that can forecast the formation of a tropical cyclone with a lead time of up to 60 hours with high accuracy. The model uses the high-resolution reanalysis data ERA5, and best track data IBTrACS (International Best Track Archive for Climate Stewardship) to forecast tropical cyclone formation in six ocean basins of the world. For 60 hours lead time the models achieve an accuracy in the range of 86.9% - 92.9% across the six ocean basins. The model takes about 5-15 minutes of training time depending on the ocean basin, and the amount of data used and can predict within seconds, thereby making it suitable for real-life usage. 

Statistics

   Article View: 42
   PDF Downloaded: 2