|
Authors: |
V. M. Krasnopolsky, M. S. Fox-Rabinovitz, Y. T. Hou, S. J. Lord, A. A. Belochits
EMC/NCEP/NOAA, University of Maryland
vladimir.krasnopolsky@noaa.gov
|
Title: | Accurate and Fast Neural Network Emulations of Model Radiation for the NCEP Coupled Climate Forecast System: Climate Simulations and Seasonal Predictions |
Additional Bibliographic Information: | |
Year: | 2009 |
MMAB Contribution Number: | 277 |
Keywords: | Atmospheric radiation, climate modeling, neural networks |
Status: | draft |
Abstract: | The approach to accurate and fast calculating model physics using neural network emulations was previously developed by the authors for both long-wave and short-wave radiation parameterizations, or for the full model radiation, the most time-consuming component of model physics. It was successfully tested for a moderate resolution uncoupled NCAR CAM (Community Atmospheric Model) driven by climatological SST for a decadal climate simulation mode (Krasnopolsky et al. 2008a). In this study, the approach has been father developed and implemented into the NCEP coupled CFS (Climate Forecast System) with significantly higher resolution and time dependent CO2. The higher complexity of NCEP CFS required introducing further adjustments to the neural network emulation methodology. Validation of the approach for the NCEP CFS has been done through a decadal climate simulation and seasonal predictions. The developed highly accurate neural network emulations of long-wave and short-wave radiation parameterizations are 12 and 45 times faster than the original/control long-wave and short-wave radiation parameterizations, respectively. A detailed comparison of parallel decadal climate simulations and seasonal predictions performed with the original NCEP model radiation parameterizations and with their neural network emulations is presented. Almost identical results have been obtained for the parallel decadal simulations and seasonal prediction that justifies the practical use of efficient neural network emulations of full model radiation for climate simulations and seasonal predictions.
|
Link: | /mmab/papers/tn277/MMAB_277.pdf |
Return to index listing
Return to branch main page
|