DocumentCode :
2494598
Title :
Development of neural network convection parameterizations for numerical climate and weather prediction models using cloud resolving model simulations
Author :
Krasnopolsky, Vladimir M. ; Fox-Rabinovitz, Michael S. ; Belochitski, Alexei A.
Author_Institution :
Nat. Centers for Environ. Prediction, Univ. of Maryland, Camp Spring, MD, USA
fYear :
2010
fDate :
18-23 July 2010
Firstpage :
1
Lastpage :
8
Abstract :
A novel approach based on the neural network (NN) technique is formulated and used for development of a NN ensemble stochastic convection parameterization for numerical climate and weather prediction models. This fast parameterization is built based on data from Cloud Resolving Model (CRM) simulations initialized with TOGA-COARE data. CRM emulated data are averaged and projected onto the General Circulation Model (GCM) space of atmospheric states to implicitly define a stochastic convection parameterization. This parameterization is comprised as an ensemble of neural networks. The developed NNs are trained and tested. The inherent uncertainty of the stochastic convection parameterization derived in such a way is estimated. The major challenges of development of stochastic NN parameterizations are discussed based on our initial results.
Keywords :
geophysics computing; neural nets; stochastic processes; weather forecasting; TOGA-COARE data; general circulation model space; neural network convection parameterization; numerical climate prediction model; resolving model simulation; stochastic convection parameterization; weather prediction model; Artificial neural networks; Cooling; Electricity; Heating; Numerical models;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
ISSN :
1098-7576
Print_ISBN :
978-1-4244-6916-1
Type :
conf
DOI :
10.1109/IJCNN.2010.5596766
Filename :
5596766
Link To Document :
بازگشت