ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking
cs.LG, cs.AI
Submitted: 2025-11-28
Updated: 2026-03-26
Comments: 26 pages, 17 figures
Code: https://github.com/CMCC-Foundation/bytestorm
License: http://creativecommons.org/licenses/by/4.0/
The gist: Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science.
Terminology
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 and are often computationally and data-intensive, due to the management of a large number of variables. We present ByteStorm, an efficient data-driven framework for reconstructing TC tracks. 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 benchmarked with state-of-the-art deterministic trackers on the main global TC formation basins. The proposed framework achieves good tracking skills in terms of Probability of Detection and False Alarm Rate, accurately reproduces Seasonal and Inter-Annual Variability, and reconstructs reliable, smooth and coherent TC tracks. These results highlight the potential of integrating deep learning and computer vision to provide robust, computationally efficient and skillful data-driven alternatives to TC tracking.
Sources
- Decoupled Weight Decay Regularization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- TROPHY: A Topologically Robust Physics-Informed Tracking Framework for Tropical Cyclones
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks