A new approach based on a synergetic combination of statistical/machine learning and deterministic modeling within atmospheric models is presented. The approach uses neural networks as a statistical or machine learning technique for an accurate and fast emulation or statistical approximation of model physics parameterizations. It is applied to development of an accurate and fast approximation of an atmospheric longwave radiation parameterization for the NCAR Community Atmospheric Model, which is the most time consuming component of model physics. The developed neural network emulation is two orders of magnitude, 50–80 times, faster than the original parameterization. A comparison of the parallel 10-yr climate simulations performed with the original parameterization and its neural network emulations confirmed that these simulations produce almost identical results. The obtained results show the conceptual and practical possibility of an efficient synergetic combination of deterministic and statistical learning components within an atmospheric climate or forecast model. A developmental framework and practical validation criteria for neural network emulations of model physics components are outlined.
7 May 2013 in Advances in Artificial Neural Systems
A novel approach based on the neural network (NN) ensemble technique is formulated and used for development of a NN stochastic convection parameterization for climate and numerical weather prediction (NWP) models. This fast parameterization is built based on learning from data simulated by a cloud-resolving model (CRM) initialized with and forced by the observed meteorological data available for 4-month boreal winter from November 1992 to February 1993. CRM-simulated data were averaged and processed to implicitly define a stochastic convection parameterization. This parameterization is learned from the data using an ensemble of NNs. The NN ensemble members are trained and tested. The inherent uncertainty of the stochastic convection parameterization derived following this approach is estimated. The newly developed NN convection parameterization has been tested in National Center of Atmospheric Research (NCAR) Community Atmospheric Model (CAM). It produced reasonable and promising decadal climate simulations for a large tropical Pacific region. The extent of the adaptive ability of the developed NN parameterization to the changes in the model environment is briefly discussed. This paper is devoted to a proof of concept and discusses methodology, initial results, and the major challenges of using the NN technique for developing convection parameterizations for climate and NWP models.
The approach to accurate and fast-calculating model physics using neural network emulations was previously developed by the authors for both longwave and shortwave radiation parameterizations or the full model radiation, which is the most time-consuming component of model physics. It was successfully tested for a moderate-resolution uncoupled NCAR Community Atmospheric Model (CAM) that is driven by climatological SST for a decadal climate simulation mode. In this study, the approach has been further developed and implemented into the NCEP coupled Climate Forecast System (CFS) with significantly higher resolution and time-dependent CO2. The higher complexity of NCEP CFS required further adjustments to the neural network emulation methodology. Validation of the approach for the NCEP CFS has been performed through a decadal climate simulation and seasonal predictions. The developed highly-accurate neural network emulations of longwave and shortwave radiation parameterizations are, on average, 16 and 60 times faster than the original/control longwave and shortwave radiation parameterizations, respectively. The authors present 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. The differences between the parallel runs are overall within or less than the observation errors and uncertainties of reanalysis. Moreover, the differences (both in terms of bias and RMSE) are of a similar magnitude as the model’s internal variability. These results justify the practical use of efficient neural network emulations of full model radiation for climate simulations and seasonal predictions.
A novel multimodel ensemble approach based on learning from data using the neural network (NN) technique is formulated and applied for improving 24-hour precipitation forecasts over the continental US. The developed nonlinear approach allowed us to account for nonlinear correlation between ensemble members and to produce “optimal” forecast represented by a nonlinear NN ensemble mean. The NN approach is compared with the conservative multi-model ensemble, with multiple linear regression ensemble approaches, and with results obtained by human forecasters. The NN multi-model ensemble improves upon conservative multi-model ensemble and multiple linear regression ensemble, it (1) significantly reduces high bias at low precipitation level, (2) significantly reduces low bias at high precipitation level, and (3) sharpens features making them closer to the observed ones. The NN multi-model ensemble performs at least as well as human forecasters supplied with the same information. The developed approach is a generic approach that can be applied to other multi-model ensemble fields as well as to single model ensembles.