Modelling V-band Atmospheric Loss with Deep Learning

Modelling atmospheric loss is fundamental to implementation of future mm-wave terrestrial and earth space communication links. Atmospheric losses have traditionally been estimated by calculating the contributions of individual weather phenomena through in-situ meteorological measurements and statistically derived models for estimating localized atmospheric water content. Collecting data for all points along the propagation path and calculating the physical effects of gases, clouds, and precipitation individually is both time consuming and impractical for large-scale use cases. In response to these present limitations, this work proposes the use of novel deep learning models for estimating atmospheric losses from tabular meteorological sensor data and doppler weather radar images. These models were validated on a multi-year propagation measurement campaign operating at 72 GHz and when combined with a natural gradient boosting algorithm to provide a unique probabilistic estimator. This new fusion deep learning and gradient boosting model can predict atmospheric loss based on current meteorological conditions along with the model’s confidence.