Multi-Resolution Analysis of the Convective Structure of Tropical Cyclones for Short-Term Intensity Guidance

2025-10-21

AI Summary

Predicting 24-hour intensity changes of Atlantic tropical cyclones (TCs) remains challenging due to the complexity and real-time interpretability limitations of satellite imagery. To address this, we propose a multi-resolution analysis framework based on discrete wavelet transform (DWT) that quantitatively extracts physically meaningful convective structural features of TCs across multiple spatial scales. This approach significantly enhances early identification of rapid intensification (RI) events while preserving interpretability and high-fidelity structural characterization, thereby providing deep learning models with physically constrained, structured inputs. Experimental results demonstrate that our prediction system substantially outperforms baseline models in 24-hour intensity change forecasting—particularly in both lead time and accuracy for RI detection. The framework delivers operationally viable technical support for offshore TC hazard early warning.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate tropical cyclone (TC) short-term intensity forecasting with a 24-hour lead time is essential for disaster mitigation in the Atlantic TC basin. Since most TCs evolve far from land-based observing networks, satellite imagery is critical to monitoring these storms; however, these complex and high-resolution spatial structures can be challenging to qualitatively interpret in real time by forecasters. Here we propose a concise, interpretable, and descriptive approach to quantify fine TC structures with a multi-resolution analysis (MRA) by the discrete wavelet transform, enabling data analysts to identify physically meaningful structural features that strongly correlate with rapid intensity change. Furthermore, deep-learning techniques can build on this MRA for short-term intensity guidance.

Problem

• Improving 24-hour tropical cyclone intensity forecasting accuracy
• Quantifying complex satellite storm structures for real-time interpretation
• Identifying structural features linked to rapid intensity changes

Innovation

• Multi-resolution analysis using discrete wavelet transform
• Quantifying fine tropical cyclone structural features
• Deep-learning techniques for short-term intensity guidance