Online Program Home
My Program

Abstract Details

Activity Number: 331 - Advances in the Analysis of Massive Space-Time Data Sets Using High Performance Computing
Type: Topic Contributed
Date/Time: Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics and the Environment
Abstract #302958 Presentation
Title: GPU Accelerated Deep Learning for Climate and Weather
Author(s): David Hall*
Companies: NVIDIA
Keywords: artificial intelligence; deep learning; weather; climate; GPUs; machine learning
Abstract:

Artificial intelligence is poised to become a central component for most technological endeavors, and weather prediction is no exception. Deep learning has emerged as a powerful mechanism for constructing software by example, which enable the construction functions too complex, subtle, or unintuitive to be designed by hand. These new tools may be applied to accelerate or augment all aspects of weather forecasting and climate prediction including: data collection, error correction, data thinning, assimilation, modeling, prediction, communication, anomaly detection, and data analysis. In this talk, I will give an overview of the subject, together with concrete examples of ongoing deep learning projects in climate and weather in which I am actively involved.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program