Ryan Lagerquist- April 8

Using Deep Learning to Improve Prediction and Understanding of High-impact Weather Ryan Lagerquist Wednesday, April 8th 11:00 am  https://oklahoma.zoom.us/j/822210097 Zoom password: 596031   I describe the application of convolutional neural networks (CNN), a type of deep-learning method, to high-impact weather.  CNNs are specially designed to learn directly from spatial grids, which

Start

April 8, 2020 - 11:00 am

End

April 8, 2020 - 12:30 pm

Using Deep Learning to Improve Prediction and Understanding of High-impact Weather

Ryan Lagerquist

Wednesday, April 8th

11:00 am 

https://oklahoma.zoom.us/j/822210097

Zoom password: 596031

 

I describe the application of convolutional neural networks (CNN), a type of deep-learning method, to high-impact weather.  CNNs are specially designed to learn directly from spatial grids, which improves both skill and interpretability.  Specifically, I develop and test CNNs for two tasks.  The first is tornado prediction, where two CNNs predict next-hour tornado occurrence for a given storm, using datasets similar to those used by forecasters in real-time operations.  The tornado models achieve an area under the receiver-operating-characteristic curve (AUC) of 0.94 and critical success index (CSI) of ~0.3.  This is competitive with a machine-learning model currently used in operations, which suggests that the CNNs would also be suitable for operations.  Specialized machine-learning-interpretation methods highlight the importance of a deep reflectivity core and strong mesocyclone, as well as low-level instability and wind shear in the surrounding environment.  Also, interpretation methods suggest that a rear-flank downdraft with too much precipitation and negative buoyancy can lead to tornadogenesis failure, which corroborates some previous literature.  The second task is front detection, where a CNN draws warm and cold fronts in reanalysis data.  I use the CNN-detected fronts to create a 40-year climatology over North America.  On a large scale, fronts are most common in the mid-latitude cyclone track, which migrates poleward from winter to summer, equatorward during El Niño, and poleward during La Niña.  Also, the cyclone track appears to be migrating poleward as a consequence of global warming.  These results are broadly consistent with the few pre-existing climatologies, although there are some discrepancies that should be investigated in the future.  Overall, I demonstrate that deep learning can be used to advance both the prediction and understanding of high-impact weather.