ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking
This provides a robust alternative to traditional subjective methods for weather and climate scientists, though it is incremental as it combines existing deep learning and tracking algorithms in a new way.
The paper tackles the problem of accurate tropical cyclone tracking by introducing ByteStorm, a data-driven framework that uses deep learning and computer vision to detect and link cyclone centers without threshold tuning, achieving high detection probabilities (85.05% ENP, 79.48% WNP) and low false alarm rates (23.26% ENP, 16.14% WNP).
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.