TJ7.4 Automated Detection of Fronts Using a Deep Learning Algorithm

Wednesday, 10 January 2018: 11:30 AM
Ballroom A (ACC) (Austin, Texas)
Kenneth E. Kunkel, Cooperative Institute for Climate and Satellites, Asheville, NC; and J. C. Biard and E. Racah

A deeper understanding of climate model simulations and the future effects of global warming on extreme weather can be attained through direct analyses of the phenomena that produce weather. Such analyses require these phenomena to be identified in automatic, unbiased, and comprehensive ways. Atmospheric fronts are centrally important weather phenomena because of the variety of significant weather events, such as thunderstorms, directly associated with them. In current operational meteorology, fronts are identified and drawn visually based on the approximate spatial coincidence of a number of quasi-linear localized features - a trough (relative minimum) in air pressure in combination with gradients in air temperature and/or humidity and a shift in wind, and are categorized as cold, warm, stationary, or occluded, with each type exhibiting somewhat different characteristics. Fronts are extended in space with one dimension much larger than the other (often represented by complex curved lines), which poses a significant challenge for automated approaches. We addressed this challenge by using a Deep Learning Convolutional Neural Network (CNN) to automatically identify and classify fronts. The CNN was trained using a “truth” dataset of front locations identified by National Weather Service meteorologists as part of operational 3-hourly surface analyses. The input to the CNN is a set of 5 gridded fields of surface atmospheric variables, including 2m temperature, 2m specific humidity, surface pressure, and the two components of the 10m horizontal wind velocity vector at 3-hr resolution. The output is a set of feature maps containing the per - grid cell probabilities for the presence of the 4 front types.

The CNN was trained on a subset of the data and then used to produce front probabilities for each 3-hr time snapshot over a 14-year period covering the continental United States and some adjacent areas. The total frequencies of fronts derived from the CNN outputs matches very well with the truth dataset. There is a slight underestimate in total numbers in the CNN results but the spatial pattern is a close match. The categorization of front types by CNN is best for cold and occluded and worst for warm. These initial results from our ongoing development highlight the great promise of this technology.

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner