Machine-Learned Preconditioners for Linear Solvers in Geophysical Fluid Flows

It is tested whether machine learning methods can be used for preconditioning to increase the performance of the linear solver -- the backbone of the semi-implicit, grid-point model approach for weather and climate models. Embedding the machine-learning method within the framework of a linear solver circumvents potential robustness issues that machine learning approaches are often criticized for, as the linear solver ensures that a sufficient, pre-set level of accuracy is reached. The approach does not require prior availability of a conventional preconditioner and is highly flexible regarding complexity and machine learning design choices. Several machine learning methods are used to learn the optimal preconditioner for a shallow-water model with semi-implicit timestepping that is conceptually similar to more complex atmosphere models. The machine-learning preconditioner is competitive with a conventional preconditioner and provides good results even if it is used outside of the dynamical range of the training dataset.

[1]  Joanna Szmelter,et al.  An edge-based unstructured mesh discretisation in geospherical framework , 2010, J. Comput. Phys..

[2]  Cheng Yang,et al.  Data‐driven projection method in fluid simulation , 2016, Comput. Animat. Virtual Worlds.

[3]  Stephen J. Lord,et al.  Accurate and Fast Neural Network Emulations of Model Radiation for the NCEP Coupled Climate Forecast System: Climate Simulations and Seasonal Predictions* , 2010 .

[4]  Andrew Stuart,et al.  Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High‐Resolution Simulations , 2017, 1709.00037.

[5]  Felix J. Herrmann,et al.  Learned Iterative Solvers for the Helmholtz Equation , 2019, 81st EAGE Conference and Exhibition 2019.

[6]  Tzu-Yi Chen,et al.  Neural Networks for Predicting the Behavior of Preconditioned Iterative Solvers , 2007, International Conference on Computational Science.

[7]  Torsten Hoefler,et al.  Near-global climate simulation at 1 km resolution: establishing a performance baseline on 4888 GPUs with COSMO 5.0 , 2017 .

[8]  Matthew England,et al.  Using Machine Learning to Decide When to Precondition Cylindrical Algebraic Decomposition with Groebner Bases , 2016, 2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC).

[9]  B. Stevens,et al.  The scientific challenge of understanding and estimating climate change , 2019, Proceedings of the National Academy of Sciences.

[10]  R. C. Malone,et al.  Parallel ocean general circulation modeling , 1992 .

[11]  Barbara Solenthaler,et al.  Data-driven fluid simulations using regression forests , 2015, ACM Trans. Graph..

[12]  Jessica Lowell.  Neural Network , 2001 .

[13]  Hartwig Anzt,et al.  Machine Learning-Aided Numerical Linear Algebra: Convolutional Neural Networks for the Efficient Preconditioner Generation , 2018, 2018 IEEE/ACM 9th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (scalA).

[14]  Alain Chedin,et al.  A Neural Network Approach for a Fast and Accurate Computation of a Longwave Radiative Budget , 1998 .

[15]  Prabhat,et al.  Exascale Deep Learning for Climate Analytics , 2018, SC18: International Conference for High Performance Computing, Networking, Storage and Analysis.

[16]  P. K. Smolarkiewicz,et al.  VARIATIONAL METHODS FOR ELLIPTIC PROBLEMS IN FLUID MODELS , 2000 .

[17]  Pierre Gentine,et al.  Could Machine Learning Break the Convection Parameterization Deadlock? , 2018, Geophysical Research Letters.

[18]  Tzu-Yi Chen,et al.  On Using Reinforcement Learning to Solve Sparse Linear Systems , 2008, ICCS.

[19]  Francis X. Giraldo,et al.  Current and Emerging Time-Integration Strategies in Global Numerical Weather and Climate Prediction , 2019 .

[20]  Mats Hamrud,et al.  A finite-volume module for simulating global all-scale atmospheric flows , 2016, J. Comput. Phys..

[21]  Leszek Marcinkowski,et al.  Parallel ADI Preconditioners for All-Scale Atmospheric Models , 2015, PPAM.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Eike Hermann Müller,et al.  Multigrid preconditioners for the mixed finite element dynamical core of the LFRic atmospheric model , 2020, ArXiv.

[24]  Jonathan A. Weyn,et al.  Can Machines Learn to Predict Weather? Using Deep Learning to Predict Gridded 500‐hPa Geopotential Height From Historical Weather Data , 2019, Journal of Advances in Modeling Earth Systems.

[25]  Joanna Szmelter,et al.  FVM 1.0: a nonhydrostatic finite-volume dynamical core for the IFS , 2019, Geoscientific Model Development.

[26]  Jaspreet Singh,et al.  Recommendation System , 2021, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[27]  Andreas Dedner,et al.  Efficient multigrid preconditioners for atmospheric flow simulations at high aspect ratio , 2014, 1408.2981.

[28]  L. Margolin,et al.  MPDATA: A Finite-Difference Solver for Geophysical Flows , 1998 .

[29]  Vivek Sarin,et al.  A Recommendation System for Preconditioned Iterative Solvers , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[30]  Chao Yang,et al.  10M-Core Scalable Fully-Implicit Solver for Nonhydrostatic Atmospheric Dynamics , 2016, SC16: International Conference for High Performance Computing, Networking, Storage and Analysis.

[31]  Tzu-Yi Chen,et al.  Using reinforcement learning to vary the m in GMRES(m) , 2011, ICCS.

[32]  S. Eisenstat,et al.  Variational Iterative Methods for Nonsymmetric Systems of Linear Equations , 1983 .

[33]  J. Prusa,et al.  EULAG, a computational model for multiscale flows , 2008 .

[34]  Takahiro Katagiri,et al.  Preconditioner Auto-Tuning Using Deep Learning for Sparse Iterative Algorithms , 2018, 2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW).

[35]  Christian Kühnlein,et al.  Semi-implicit integrations of perturbation equations for all-scale atmospheric dynamics , 2019, J. Comput. Phys..

[36]  P. Swarztrauber,et al.  A standard test set for numerical approximations to the shallow water equations in spherical geometry , 1992 .

[37]  Pierre Gentine,et al.  Deep learning to represent subgrid processes in climate models , 2018, Proceedings of the National Academy of Sciences.

[38]  Sanjiv Kumar,et al.  On the Convergence of Adam and Beyond , 2018 .

[39]  Peter Bauer,et al.  Challenges and design choices for global weather and climate models based on machine learning , 2018, Geoscientific Model Development.

[40]  Ken Perlin,et al.  Accelerating Eulerian Fluid Simulation With Convolutional Networks , 2016, ICML.