Work

Machine learning-based correlation analysis of decadal cyclone intensity with sea surface temperature: data and tutorial

Year: 2026

Type: article

Abstract: The rising number of extreme climate events in the past few decades has motivated the need for a thorough consideration of tropical cyclone genesis and intensity, particularly in relation to Sea-Surface Temperature (SST). In this paper, we present an analysis of the relationship between increasing global SST and cyclone genesis using linear regression and machine learning models. We extract and curate a dataset of tropical cyclones across selected ocean basins with their associated SST over the past 40 years. We provide correlation analysis using linear regression and visualisation strategies. Our preliminary results show a positive correlation between SST and high wind speed (Category 5 Cyclones) across the South Indian Ocean and Northwest Pacific Ocean basins via linear regression and machine learning models. We provide open data with a tutorial for hands-on investigation of the relationship between the genesis and intensity of tropical cyclones. Alongside the time and position of each cyclone, we also provide the related Saffir-Simpson category, season, wind speed, and SST for 15 days before and after the tropical cyclone genesis.

Source: Stochastic Environmental Research and Risk Assessment

DOI: 10.1007/s00477-026-03251-w

Authors: Jingyang Wu, Rohitash Chandra

Institutions: UNSW Sydney, Pingla Institute

Language: English

Topic: Tropical and Extratropical Cyclones Research

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: hybrid

Estimated APC paid: $4,090