Presentation
SIGN IN TO VIEW THIS PRESENTATION Sign In
Rapid Simulations of Atmospheric Data Assimilation of Hourly-Scale Phenomena with Modern Neural Networks
DescriptionAtmospheric data assimilation is essential for numerical weather prediction. Ensemble-based data assimilation connects multiple instances of atmospheric model through Kalman-filter-based algorithm, which is regarded as a challenging computing task today. In this work, we present our efforts to build a fast, low-cost, and scalable atmospheric data assimilation prototype for the new-generation Sunway supercomputer, including (1) A UNet-neural-network-based surrogate model for atmospheric dynamic simulation to generate all the background ensemble with both satisfactory accuracy and reasonable robustness; (2) Batched LETKF with an efficient eigenvalue decomposition implementation and a data staging strategy to cover the observation IO time ; (3) A framework able to flexibly deploy the components, thus available to reach the maximum resource efficiency. Experimental evaluations show that our AI-integrated ensemble data assimilation prototype can finish hour-cycle assimilation in minutes, keep linear scalability and save an order of magnitude of computing resources compared with the traditional scientific method.
Authors
Event Type
Paper
TimeThursday, 16 November 20231:30pm - 2pm MST
Location405-406-407
Artificial Intelligence/Machine Learning
Applications
Modeling and Simulation
State of the Practice
TP