3DTCR: A Physics-Based Generative Framework for Vortex-Following 3D Reconstruction to Improve Tropical Cyclone Intensity Forecasting

2026-03-13

AI Summary

Current numerical and AI-based weather models struggle to accurately represent the fine-scale three-dimensional structure of tropical cyclone (TC) inner cores and their intensity evolution mechanisms, limiting forecast accuracy. This study proposes 3DTCR, a novel framework that, for the first time, integrates physical constraints with generative AI to achieve vortex-following, regionally adaptive 3D reconstruction via conditional flow matching. The method incorporates latent-domain adaptation and a two-stage transfer learning strategy, enhancing computational efficiency while preserving physical consistency. Trained on six years of 3-km WRF moving-nest simulations, 3DTCR consistently outperforms ECMWF-HRES over a five-day forecast window, reducing the root-mean-square error (RMSE) of maximum 10-meter wind speed (WS10M) by 36.5% compared to FuXi inputs and substantially improving the representation of TC inner-core structure and intensity.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Tropical cyclone (TC) intensity forecasting remains challenging as current numerical and AI-based weather models fail to satisfactorily represent extreme TC structure and intensity. Although intensity time-series forecasting has achieved significant advances, it outputs intensity sequences rather than the three-dimensional inner-core fine-scale structure and physical mechanisms governing TC evolution. High-resolution numerical simulations can capture these features but remain computationally expensive and inefficient for large-scale operational applications. Here we present 3DTCR, a physics-based generative framework combining physical constraints with generative AI efficiency for 3D TC structure reconstruction. Trained on a six-year, 3-km-resolution moving-domain WRF dataset, 3DTCR enables region-adaptive vortex-following reconstruction using conditional Flow Matching(CFM), optimized via latent domain adaptation and two-stage transfer learning. The framework mitigates limitations imposed by low-resolution targets and over-smoothed forecasts, improving the representation of TC inner-core structure and intensity while maintaining track stability. Results demonstrate that 3DTCR outperforms the ECMWF high-resolution forecasting system (ECMWF-HRES) in TC intensity prediction at nearly all lead times up to 5 days and reduces the RMSE of maximum WS10M by 36.5\% relative to its FuXi inputs. These findings highlight 3DTCR as a physics-based generative framework that efficiently resolves fine-scale structures at lower computational cost, which may offer a promising avenue for improving TC intensity forecasting.

Problem

• tropical cyclone intensity forecasting
• 3D reconstruction
• inner-core structure
• physics-based modeling
• computational efficiency

Innovation

• physics-based generative model
• vortex-following reconstruction
• conditional flow matching
• latent domain adaptation
• tropical cyclone intensity forecasting