Weather Estimation for Integrated Sensing and Communication

TL;DR

This paper demonstrates that 6G base stations can be repurposed for accurate weather sensing using deep learning, enabling cost-effective and widespread weather monitoring as a new service in future networks.

Contribution

It introduces a novel approach to utilize 6G infrastructure for weather sensing through neural networks, expanding ISAC capabilities beyond object detection.

Findings

Achieved over 99% accuracy in classifying weather conditions.

Estimated precipitation rate and wind speed with errors of 1.2 mm/h and 1.5 km/h.

Validated the approach with a multi-week experimental campaign.

Abstract

One of the key features of sixth-generation (6G) mobile communications will be integrated sensing and communication (ISAC). While the main goal of ISAC in standardization efforts is to detect objects, the byproducts of radar operations can be used to enable new services in 6G, such as weather sensing. Even though weather radars are the most prominent technology for weather detection and monitoring, they are expensive and usually neglect areas in close vicinity. To this end, we propose reusing the dense deployment of 6G base stations for weather sensing purposes by detecting and estimating weather conditions. We implement both a classifier and a regressor as a convolutional neural network trained across measurements with varying precipitation rates and wind speeds. We implement our approach in an ISAC proof-of-concept and conduct a multi-week experiment campaign. Experimental results show that we are able to jointly and accurately classify weather conditions with accuracies of 99.38% and 98.99% for precipitation rate and wind speed, respectively. For estimation, we obtain errors of 1.2 mm/h and 1.5 km/h, for precipitation rate and wind speed, respectively. These findings indicate that weather sensing services can be reliably deployed in 6G ISAC networks, broadening their service portfolio and boosting their market value.