Machine Learning for the Digital Typhoon Dataset: Extensions to Multiple Basins and New Developments in Representations and Tasks

TL;DR

This paper introduces the Digital Typhoon Dataset V2 with hemispheric expansion, new tasks, and representation methods, enabling advanced machine learning research on typhoon prediction and analysis across different regions.

Contribution

The paper extends the Digital Typhoon Dataset to include southern hemisphere data and proposes new tasks and models, such as self-supervised learning and object detection, for improved typhoon analysis.

Findings

Object detection models excel for strong typhoons.

Models trained on northern data can generalize to southern hemisphere.

Self-supervised learning enhances representation quality.

Abstract

This paper presents the Digital Typhoon Dataset V2, a new version of the longest typhoon satellite image dataset for 40+ years aimed at benchmarking machine learning models for long-term spatio-temporal data. The new addition in Dataset V2 is tropical cyclone data from the southern hemisphere, in addition to the northern hemisphere data in Dataset V1. Having data from two hemispheres allows us to ask new research questions about regional differences across basins and hemispheres. We also discuss new developments in representations and tasks of the dataset. We first introduce a self-supervised learning framework for representation learning. Combined with the LSTM model, we discuss performance on intensity forecasting and extra-tropical transition forecasting tasks. We then propose new tasks, such as the typhoon center estimation task. We show that an object detection-based model performs better for stronger typhoons. Finally, we study how machine learning models can generalize across basins and hemispheres, by training the model on the northern hemisphere data and testing it on the southern hemisphere data. The dataset is publicly available at \url{http://agora.ex.nii.ac.jp/digital-typhoon/dataset/} and \url{https://github.com/kitamoto-lab/digital-typhoon/}.