Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations

Abstract

Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of sub-grid processes in Earth System Models (ESMs). So far, all studies were based on the same three-step approach: first a training dataset was created from a high-resolution simulation, then a machine learning algorithm was fitted to this dataset, before the trained algorithm was implemented in the ESM. The resulting online simulations were frequently plagued by instabilities and biases. Here, coupled online learning is proposed as a way to combat these issues. Coupled learning can be seen as a second training stage in which the pretrained machine learning parameterization, specifically a neural network, is run in parallel with a high-resolution simulation. The high-resolution simulation is kept in sync with the neural network-driven ESM through constant nudging. This enables the neural network to learn from the tendencies that the high-resolution simulation would produce if it experienced the states the neural network creates. The concept is illustrated using the Lorenz 96 model, where coupled learning is able to recover the "true" parameterizations. Further, detailed algorithms for the implementation of coupled learning in 3D cloud-resolving models and the super parameterization framework are presented. Finally, outstanding challenges and issues not resolved by this approach are discussed.

Code and interactive notebook available at https://github.com/raspstephan/Lorenz-Online; see https://doi.org/10.5194/gmd-2019-319 for journal version

References in corpus (4)

• Deep learning to represent sub-grid processes in climate models
• Neural networks for post-processing ensemble weather forecasts
• Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling
• Interacting Langevin Diffusions: Gradient Structure And Ensemble Kalman Sampler

Cited by in corpus (6)

• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning
• Online learning of both state and dynamics using ensemble Kalman filters
• Resampling with neural networks for stochastic parameterization in multiscale systems
• Machine Learning for Robust Identification of Complex Nonlinear Dynamical Systems: Applications to Earth Systems Modeling
• Using Machine Learning for Model Physics: an Overview