Skip to main content
U.S. flag

An official website of the United States government

Emulating RRTMG Radiation with Deep Neural Networks for the Accelerated Model for Climate and Energy

Presentation Date
Wednesday, December 13, 2017 at 1:40pm
Location
New Orleans Ernest N. Morial Convention Center - Poster Hall D-F
Authors

Author

Abstract

The RRTMG radiation scheme in the Accelerated Model for Climate and Energy Multi-scale Model Framework (ACME-MMF), is a bottleneck and consumes approximately $50\%$ of the computational time. To simulate a case using RRTMG radiation scheme in ACME-MMF with high throughput and high resolution will therefore require a speed-up of this calculation while retaining physical fidelity. In this study, RRTMG radiation is emulated with Deep Neural Networks (DNNs). \\

The first step towards this goal is to run a case with ACME-MMF and generate input data sets for the DNNs. A principal component analysis of these input data sets are carried out. Artificial data sets are created using the previous data sets to cover a wider space. These artificial data sets are used in a standalone RRTMG radiation scheme to generate outputs in a cost effective manner. These input-output pairs are used to train multiple architectures DNNs(1). Another DNN(2) is trained using the inputs to predict the error. A reverse emulation is trained to map the output to input. An error controlled code is developed with the two DNNs (1 and 2) and will determine when/if the original parameterization needs to be used.