Articles | Volume 12, issue 10
Development and technical paper
10 Oct 2019
Development and technical paper |  | 10 Oct 2019

Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model

Jiali Wang, Prasanna Balaprakash, and Rao Kotamarthi

Related authors

WRF-ELM v1.0: a Regional Climate Model to Study Atmosphere-Land Interactions Over Heterogeneous Land Use Regions
Huilin Huang, Yun Qian, Gautam Bisht, Jiali Wang, Tirthankar Chakraborty, Dalei Hao, Jianfeng Li, Travis Thurber, Balwinder Singh, Zhao Yang, Ye Liu, Pengfei Xue, William Sacks, Ethan Coon, and Robert Hetland
EGUsphere,,, 2024
Short summary
A conditional approach for joint estimation of wind speed and direction under future climates
Qiuyi Wu, Julie Bessac, Whitney Huang, Jiali Wang, and Rao Kotamarthi
Adv. Stat. Clim. Meteorol. Oceanogr., 8, 205–224,,, 2022
Short summary
Augmentation of WRF-Hydro to simulate overland-flow- and streamflow-generated debris flow susceptibility in burn scars
Chuxuan Li, Alexander L. Handwerger, Jiali Wang, Wei Yu, Xiang Li, Noah J. Finnegan, Yingying Xie, Giuseppe Buscarnera, and Daniel E. Horton
Nat. Hazards Earth Syst. Sci., 22, 2317–2345,,, 2022
Short summary
Efficient high-dimensional variational data assimilation with machine-learned reduced-order models
Romit Maulik, Vishwas Rao, Jiali Wang, Gianmarco Mengaldo, Emil Constantinescu, Bethany Lusch, Prasanna Balaprakash, Ian Foster, and Rao Kotamarthi
Geosci. Model Dev., 15, 3433–3445,,, 2022
Short summary
Fast and accurate learned multiresolution dynamical downscaling for precipitation
Jiali Wang, Zhengchun Liu, Ian Foster, Won Chang, Rajkumar Kettimuthu, and V. Rao Kotamarthi
Geosci. Model Dev., 14, 6355–6372,,, 2021
Short summary

Related subject area

Earth and space science informatics
Accelerating Lagrangian transport simulations on graphics processing units: performance optimizations of Massive-Parallel Trajectory Calculations (MPTRAC) v2.6
Lars Hoffmann, Kaveh Haghighi Mood, Andreas Herten, Markus Hrywniak, Jiri Kraus, Jan Clemens, and Mingzhao Liu
Geosci. Model Dev., 17, 4077–4094,,, 2024
Short summary
Focal-TSMP: deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation
Mohamad Hakam Shams Eddin and Juergen Gall
Geosci. Model Dev., 17, 2987–3023,,, 2024
Short summary
Tomofast-x 2.0: an open-source parallel code for inversion of potential field data with topography using wavelet compression
Vitaliy Ogarko, Kim Frankcombe, Taige Liu, Jeremie Giraud, Roland Martin, and Mark Jessell
Geosci. Model Dev., 17, 2325–2345,,, 2024
Short summary
Functional analysis of variance (ANOVA) for carbon flux estimates from remote sensing data
Jonathan Hobbs, Matthias Katzfuss, Hai Nguyen, Vineet Yadav, and Junjie Liu
Geosci. Model Dev., 17, 1133–1151,,, 2024
Short summary
The 4D reconstruction of dynamic geological evolution processes for renowned geological features
Jiateng Guo, Zhibin Liu, Xulei Wang, Lixin Wu, Shanjun Liu, and Yunqiang Li
Geosci. Model Dev., 17, 847–864,,, 2024
Short summary

Cited articles

Attali, J. G. and Pagès, G.: Approximations of functions by a multilayer perception: A new approach, Neural Networks, 6, 1069–1081, 1997. 
Chen, T. and Chen, H.: Approximation capability to functions of several variables, nonlinear functionals and operators by radial basis function neural networks, Neural Networks, 6, 904–910, 1995a. 
Chen, T. and Chen, H.: Universal approximation to nonlinear operators by neural networks with arbitrary activation function and its application to dynamical systems, Neural Networks, 6, 911–917, 1995b. 
Chevallier, F., Chéruy, F., Scott, N. A., and Chédin, A.: A neural network approach for a fast and accurate computation of longwave radiative budget, J. Appl. Meteorol., 37, 1385–1397, 1998. 
Chevallier, F., Morcrette, J.-J., Chéruy, F., and Scott, N. A.: Use of a neural-network-based longwave radiative transfer scheme in the EMCWF atmospheric model, Q. J. Roy. Meteor. Soc., 126, 761–776, 2000. 
Short summary
Parameterizations are frequently used in models representing physical phenomena and are often the computationally expensive portions of the code. Using model output from simulations performed using a weather model, we train deep neural networks to provide an accurate alternative to a physics-based parameterization. We demonstrate that a domain-aware deep neural network can successfully simulate the entire diurnal cycle of the boundary layer physics and the results are transferable.