Predicting Tropical Cyclone-Induced Sea Surface Temperature Responses Using Machine Learning - Research Letter - 2023GL104171 - model prediction and feature importance

Aug 5, 2026

Upload by Anda

This research letter constructs a random-forest machine learning model to predict the spatiotemporal evolution of sea surface temperature (SST) cooling induced by northwest Pacific tropical cyclones, driven by the “wind pump” effect. The model uses 12 predictors describing tropical cyclone characteristics and pre-storm ocean conditions, and it reproduces the observed spatial structure, temporal development, and cross-case variance across different storm intensity groups. A companion model quantifies feature scores, identifying which predictors most strongly control the magnitude of maximum SST cooling. Results highlight that tropical cyclone intensity, translation speed and size, and pre-storm mixed layer depth and SST are dominant, varying with the considered cooling area, and these findings inform prediction of ocean primary production responses.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

1. Introduction

Tropical cyclone ocean heat extraction and SST cooling

Momentum injection and vertical mixing

Observational evidence and SST feedback

Links to chlorophyll-a changes

RESEARCH LETTER 10.1029/2023GL104171 Key Points: • A machine learning-based model is built to predict the spatiotemporal evolution of the tropical cyclone-induced sea surface temperature response • The model well predicts the spatial structure and temporal evolution of the observed response and captures the observed cross-case variance • Feature scores are computed to assess the relative importance of the predictors in determining the magnitude of the SST response Supporting Information: Supporting Information may be found in the online version of this article. Correspondence to: D. Tang and W. Mei, [lingzistdl@126.com](lingzistdl@126.com); [wmei@email.unc.edu](wmei@email.unc.edu) [Citation:](Citation:) Cui, H., Tang, D., Mei, W., Liu, H., Sui, Y., & Gu, X. (2023). Predicting tropical cyclone-induced sea surface temperature responses using machine learning. Geophysical Research Letters, 50, e2023GL104171. [https://doi](https://doi). org/10.1029/2023GL104171 Received 18 APR 2023 Accepted 27 AUG 2023 © 2023. The Authors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. Predicting Tropical Cyclone-Induced Sea Surface Temperature Responses Using Machine Learning Hongxing Cui1,2 , Danling Tang1 , Wei Mei3 , Hongbin Liu1,2 , Yi Sui1,4 , and Xiaowei Gu5 1Guangdong Remote Sensing Center for Marine Ecology and Environment, Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), Guangzhou, China, 2Department of Ocean Science, Hong Kong University of Science and Technology, Hong Kong, China, 3Department of Earth, Marine and Environmental Sciences, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA, 4Department of Oceanography, Dalhousie University, Halifax, NS, Canada, 5School of Computing, University of Kent, Canterbury, UK Abstract This study proposes to construct a model using random forest method, an efficient machine learning-based method, to predict the spatial structure and temporal evolution of the sea surface temperature (SST) cooling induced by northwest Pacific tropical cyclones (TCs), a process of the so-called wind pump. The predictors in use include 12 predictors related to TC characteristics and pre-storm ocean conditions. The model is shown to skillfully predict the spatiotemporal evolutions of the cold wake generated by TCs of different intensity groups, and capture the cross-case variance in the observed SST response. Another model is further built based on the same method to assess the relative importance of the 12 predictors in determining the magnitude of the maximum cooling. Computations of feature scores of those predictors show that TC intensity, translation speed and size, and pre-storm mixed layer depth and SST dominate, depending on the area where the cooling is considered. Plain Language Summary While many studies have been devoted to understanding the processes and mechanisms underlying the sea surface temperature (SST) cooling induced by tropical cyclones (TCs), few studies have attempted to predict the spatial and temporal evolution of the sea surface temperature (SST) cooling triggered by TCs. In this study, we proposed to achieve this goal by building a model using an efficient and robust machine learning-based method. The constructed model uses 12 predictors associated with TC characteristics (e.g., intensity, and translation speed) and pre-storm ocean states (e.g., mixed layer depth) . The model performs well in producing the TC-induced spatial structure and temporal evolution of the cold wake and can capture most of the variance in the observed SST response. We quantified the relative importance of the 12 predictors, and found that TC intensity, translation speed and size, and pre-storm mixed layer depth and SST dominate in deciding the magnitude of the SST response. The result

FAQs

What does the study aim to predict for tropical cyclones?

It predicts the spatial structure and temporal evolution of the SST cooling response induced by northwest Pacific tropical cyclones, driven by the wind pump effect.

Which method is used in the main predictive model?

The study builds a model using random forest, an efficient and robust machine learning approach.

How are the predictors evaluated in the study?

Feature scores are computed with a companion model based on the same method to assess the relative importance of the 12 predictors in determining the SST response magnitude.

Aug 5, 2026

Upload by Anda