Digital typhoon dataset improves satellite storm intensity benchmarks
Digital Typhoon Dataset V3: Benchmarking for Multi-spectral Extension and Analyzing Systematic Bias in Intensity Regression
Computer Vision and Pattern Recognition
Summary
Typhoons have been tracked by satellites for almost 50 years, creating a huge amount of image data. The authors updated this dataset to include more types of satellite images, hoping to help machine learning models better predict typhoon intensity. They found that using more image channels didn’t clearly improve accuracy for estimating storm pressure. Also, some models tend to underestimate the strength of very strong typhoons, and their attempts to fix this bias didn’t fully work. This dataset is now publicly available for others to use.
What this means in practice
- •For weather forecast teams: Improve storm intensity prediction models using the long-term multispectral typhoon image dataset.
- •For climate data engineers: Develop and test machine learning workflows on a benchmark dataset of multi-channel satellite typhoon images.
Authors
Asanobu Kitamoto, Victor Le Louarn, Noelia Falczuk, Ngoc Anh Tong, Anja Veleva
Abstract
This paper presents the Digital Typhoon Dataset V3, a new version of the longest typhoon satellite image dataset spanning nearly 50 years, designed to benchmark machine learning models on long-term spatio-temporal data. The latest addition to Dataset V3 is multispectral satellite data, enabling multi-channel models. We investigate data-splitting strategies and present benchmarking results for the Northern and Southern Hemispheres. Experimental results show that, under the current dataset construction and experimental setting, multi-channel inputs do not clearly outperform single-channel inputs for pressure regression. Among the evaluated model architectures, image types, and spectral channels, ResNet-18, full-resolution images, and Channel 1 generally provide the best single-channel performance for pressure regression. Performance also differs between the WP and AU datasets by regression target, with lower RMSE on WP for pressure regression and on AU for wind regression. These results highlight the importance of considering dataset-specific and task-specific characteristics when interpreting benchmark performance. Additionally, we analyzed systematic bias in intensity regression, which leads to underestimation of intensity for strong typhoons. We tested imbalance-aware weighting strategies, including inverse-density weighting inspired by BalancedMSE, and showed that these approaches are not sufficient to remove the bias. The dataset is publicly available at http://agora.ex.nii.ac.jp/digital-typhoon/dataset/ and https://github.com/kitamoto-lab/digital-typhoon/.