A climatology of trapped lee waves over Britain and Ireland obtained using deep learning on high‐resolution model output

This article presents a climatology of trapped lee waves over Britain and Ireland obtained through deep learning. Several deep-learning models trained to diagnose lee-wave occurrence, amplitude, wavelength, and orientation are applied to a 31-year high-resolution hindcast dataset covering 1982–2012, from UK Climate Projections (UKCP18) data, driven by ERA-Interim reanalysis data. Building on previous work to examine lee-wave characteristics over Britain and Ireland, this study applies a new technique to a much larger dataset than has been used in the past. There is little diurnal variability observed in the occurrence and characteristics of lee waves. Spatially, most lee waves occur over hilly regions, such as the Scottish Highlands, the Lake District and the Pennines in England, and North Wales. Seasonally, lee waves occur more in the winter months than in the summer. The link between synoptic weather patterns and lee waves is quantified, with more lee waves produced and a higher likelihood of higher amplitude waves under patterns with faster synoptic wind speeds, such as the positive phase of the North Atlantic Oscillation (NAO+). The mean orientation of waves is broadly in line with the synoptic wind direction, though with a large spread in some cases. High horizontal wind speeds aloft are a necessary but not sufficient indicator of high-amplitude lee waves. When other meteorological variables are used to predict the prevalence of lee waves using a random forest, the Scorer parameter is the most important for predicting the generation of lee waves alongside horizontal wind speed: there is less importance placed on the stability. This climatology provides a novel data-driven insight into the formation and propagation of lee waves over Britain and Ireland.