Communications to Circulations: 3D Wind Field Retrieval and Real-Time Prediction Using 5G GNSS Signals and Deep Learning

2025-09-19

AI Summary

Conventional wind field observations suffer from low spatiotemporal resolution, high deployment costs, and substantial biases in numerical weather prediction (NWP) models. To address these limitations, this study proposes, for the first time, a 5G-enhanced GNSS signal strength dynamics-based approach to retrieve three-dimensional atmospheric wind fields. We develop an end-to-end deep learning framework integrating a feedforward neural network (FNN) and Transformer architecture, jointly performing GNSS feature extraction, multi-scale meteorological data fusion, and temporal modeling. The method achieves NWP-level accuracy with only ~100 GNSS stations—eliminating the need for dense observational networks—and significantly reduces hardware dependency and computational overhead. Experiments demonstrate superior wind speed and direction forecasting accuracy over ERA5 reanalysis across multiple pressure levels and forecast horizons, alongside strong spatiotemporal generalizability and system scalability—enabling high-precision meteorological forecasting, aviation safety assurance, and extreme weather early warning.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Application Domains: Mobility, Driving & Flight
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate atmospheric wind field information is crucial for various applications, including weather forecasting, aviation safety, and disaster risk reduction. However, obtaining high spatiotemporal resolution wind data remains challenging due to limitations in traditional in-situ observations and remote sensing techniques, as well as the computational expense and biases of numerical weather prediction (NWP) models. This paper introduces G-WindCast, a novel deep learning framework that leverages signal strength variations from 5G Global Navigation Satellite System (GNSS) signals to retrieve and forecast three-dimensional (3D) atmospheric wind fields. The framework utilizes Forward Neural Networks (FNN) and Transformer networks to capture complex, nonlinear, and spatiotemporal relationships between GNSS-derived features and wind dynamics. Our preliminary results demonstrate promising accuracy in both wind retrieval and short-term wind forecasting (up to 30 minutes lead time), with skill scores comparable to high-resolution NWP outputs in certain scenarios. The model exhibits robustness across different forecast horizons and pressure levels, and its predictions for wind speed and direction show superior agreement with observations compared to concurrent ERA5 reanalysis data. Furthermore, we show that the system can maintain excellent performance for localized forecasting even with a significantly reduced number of GNSS stations (e.g., around 100), highlighting its cost-effectiveness and scalability. This interdisciplinary approach underscores the transformative potential of exploiting non-traditional data sources and deep learning for advanced environmental monitoring and real-time atmospheric applications.

Problem

• Retrieving 3D wind fields from 5G GNSS signals
• Overcoming limitations of traditional wind observation methods
• Providing real-time wind forecasting using deep learning

Innovation

• Uses 5G GNSS signal strength variations
• Combines FNN and Transformer neural networks
• Achieves real-time 3D wind prediction