Skip to main content
U.S. flag

An official website of the United States government

Deep Learning for Extreme Weather Detection (Invited)

Presentation Date
Monday, December 11, 2017 at 8:00am
New Orleans Ernest N. Morial Convention Center - Poster Hall D-F



We will present our latest results from the application of Deep Learning methods for detecting, localizing and segmenting extreme weather patterns in climate data. We have successfully applied supervised convolutional architectures for the binary classification tasks of detecting tropical cyclones and atmospheric rivers in centered, cropped patches. We have subsequently extended our architecture to a semi-supervised formulation, which is capable of learning a unified representation of multiple weather patterns, predicting bounding boxes and object categories, and has the capability to detect novel patterns (w/ few, or no labels). We will briefly present our efforts in scaling the semi-supervised architecture to 9600 nodes of the Cori supercomputer, obtaining 15PF performance. Time permitting, we will highlight our efforts in pixel-level segmentation of weather patterns.

Funding Program Area(s)