ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking

2025-11-28

AI Summary

Tropical cyclone (TC) automated tracking has long suffered from regional biases induced by subjective threshold selection. This paper proposes the first end-to-end, fully data-driven TC detection and tracking framework. Leveraging 850-hPa relative vorticity and sea-level pressure fields, it employs a lightweight CNN/Transformer dual-task network for joint classification and localization, integrated with the BYTE multi-object tracking algorithm to enable automatic trajectory association—eliminating reliance on manual threshold tuning. The method demonstrates strong cross-basin generalization: in the eastern and western Pacific basins, it achieves probability of detection (POD) of 85.05% and 79.48%, false alarm rate (FAR) of 23.26% and 16.14%, and interannual variability correlation coefficients of 0.75 and 0.69, respectively—outperforming state-of-the-art deterministic trackers across all metrics.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Topic discovery and tracking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may introduce biases in their skills on the geographical region of application. We present ByteStorm, an efficient data-driven framework for reconstructing TC tracks without threshold tuning. It leverages deep learning networks to detect TC centers (via classification and localization), using only relative vorticity (850 mb) and mean sea-level pressure. Then, detected centers are linked into TC tracks through the BYTE algorithm. ByteStorm is evaluated against state-of-the-art deterministic trackers in the East- and West-North Pacific basins (ENP and WNP). The proposed framework achieves superior performance in terms of Probability of Detection ($85.05%$ ENP, $79.48%$ WNP), False Alarm Rate ($23.26%$ ENP, $16.14%$ WNP), and high Inter-Annual Variability correlations ($0.75$ ENP and $0.69$ WNP). These results highlight the potential of integrating deep learning and computer vision for fast and accurate TC tracking, offering a robust alternative to traditional approaches.

Problem

• Develops a data-driven framework for tropical cyclone detection and tracking
• Addresses biases from subjective thresholds in traditional tracking methods
• Integrates deep learning and computer vision for accurate cyclone reconstruction

Innovation

• Deep learning networks detect cyclone centers using vorticity and pressure data
• BYTE algorithm links detected centers into tropical cyclone tracks
• Threshold-free framework achieves high detection probability and low false alarms