J2.6 A Neural Network Emulator for Microphysics Schemes

Tuesday, 24 January 2017: 5:00 PM
Conference Center: Skagit 2 (Washington State Convention Center )
Vladimir Krasnopolsky, NOAA/NWS/NCEP, Camp Springs, MD; and J. Middlecoff, J. Beck, I. Geresdi, and Z. Toth

Subgrid-scale physical processes not resolvable at a defined spatial resolution (e.g., convection, diffusion) in Numerical Weather Prediction (NWP) models are usually represented via schemes that parameterize these processes using resolved model variables. Parameterization Schemes (PS) are based on physical and statistical considerations and are typically very complicated and hence computationally expensive. The behavior of a PS can be emulated via a Neural Network (NN) at a reduced computational cost, and without possible extraneous levels of complexity (Krasnopolsky 2013).

 In this study, a three-layer NN was trained to reproduce the behavior of the Thompson Microphysics (TM) scheme in the WRF-ARW model (Thompson 2008). After determining the number of hidden neurons necessary for the statistical modeling of the TM scheme, we evaluated the performance of the NN-MP scheme through an off-line assessment of the variance explained in the behavior of the original TM scheme, and by a comparison of the WRF-ARW model skill using TM vs NN-MP.

 If tested successfully, the NN-MP scheme can potentially be used to (a) speed up the performance of MP schemes in NWP models, (b) represent uncertainty related to subgrid-scale (stochastic) processes in ensemble forecasting, and (c) constrain the covariance of microphysical and other variables in variational data assimilation. In subsequent studies, the performance of NN-MP will also be verified against and improved by relevant observational data.

 Acknowledgements: Steve Albers, Geoff Dimego, Jun Du, Brad Ferrier, Mark Govett, Isidora Jankov, Kevin Kelleher, and Gregory Thompson  provided valuable input to and support for this project.


Krasnopolsky V., 2013. "The Application of Neural Networks in the Earth System Sciences. Neural Network Emulations for Complex Multidimensional Mappings", Springer.

Thompson, G., P. R. Field, R. M. Rasmussen, and W. D. Hall, 2008: Explicit Forecasts of Winter Precipitation Using an Improved Bulk Microphysics Scheme. Part II: Implementation of a New Snow Parameterization. MWR, 138, 5095-5115.

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner