Advances in Wireless Sensing and Forecasting

The field of wireless sensing and forecasting is experiencing significant growth, driven by the integration of generative artificial intelligence (GenAI) and advancements in deep learning techniques. Researchers are exploring the application of GenAI to improve wireless sensing systems, including device localization, human activity recognition, and environmental monitoring. Additionally, there is a strong focus on developing innovative forecasting models that can accurately predict solar irradiance, wind fields, and other environmental factors. These models are being designed to leverage diverse data sources, including satellite imagery, ground sensors, and 5G GNSS signals, to provide high-resolution forecasts that can support a wide range of applications, from renewable energy management to aviation safety. Noteworthy papers in this area include: SolarCAST, which presents a causally informed model for predicting future global horizontal irradiance, and MobiGPT, which introduces a foundation model for mobile data forecasting. SolarCrossFormer is also a notable work, which combines satellite images and time series from ground-based meteorological stations to improve the accuracy and resolution of day-ahead irradiance forecasts. G-WindCast is another significant contribution, which leverages 5G GNSS signals and deep learning to retrieve and forecast 3D atmospheric wind fields.

Sources

Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model

Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies

SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors

A Robust Scheduling of Cyclic Traffic for Integrated Wired and Wireless Time-Sensitive Networks

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

MobiGPT: A Foundation Model for Mobile Wireless Networks

AI-Enabled Smart Hygiene System for Real-Time Glucose Detection

S$^2$Transformer: Scalable Structured Transformers for Global Station Weather Forecasting

Built with on top of