Deep learning to represent sub-grid processes in climate models

Abstract

The representation of nonlinear sub-grid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational limitations. Here we demonstrate that deep learning can be used to capture many advantages of cloud-resolving modeling at a fraction of the computational cost. We train a deep neural network to represent all atmospheric sub-grid processes in a climate model by learning from a multi-scale model in which convection is treated explicitly. The trained neural network then replaces the traditional sub-grid parameterizations in a global general circulation model in which it freely interacts with the resolved dynamics and the surface-flux scheme. The prognostic multi-year simulations are stable and closely reproduce not only the mean climate of the cloud-resolving simulation but also key aspects of variability, including precipitation extremes and the equatorial wave spectrum. Furthermore, the neural network approximately conserves energy despite not being explicitly instructed to. Finally, we show that the neural network parameterization generalizes to new surface forcing patterns but struggles to cope with temperatures far outside its training manifold. Our results show the feasibility of using deep learning for climate model parameterization. In a broader context, we anticipate that data-driven Earth System Model development could play a key role in reducing climate prediction uncertainty in the coming decade.

View official PNAS version at https://doi.org/10.1073/pnas.1810286115

References in corpus (1)

• Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events

Cited by in corpus (64)

• Learning data driven discretizations for partial differential equations
• Neural networks for post-processing ensemble weather forecasts
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
• Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions
• Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events
• Will Artificial Intelligence supersede Earth System and Climate Models?
• Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere
• Analog forecasting of extreme-causing weather patterns using deep learning
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
• Deep Learning for Post-Processing Ensemble Weather Forecasts
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Bridging observation, theory and numerical simulation of the ocean using Machine Learning
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling
• Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
• Supervised learning from noisy observations: Combining machine-learning techniques with data assimilation
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Short-term precipitation prediction using deep learning
• Learned discretizations for passive scalar advection in a 2-D turbulent flow
• Interpreting and Stabilizing Machine-learning Parametrizations of Convection
• Deep Learning Based Cloud Cover Parameterization for ICON
• A posteriori learning for quasi-geostrophic turbulence parametrization
• Machine learning emulation of gravity wave drag in numerical weather forecasting
• Machine learning for weather and climate are worlds apart
• Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains
• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning
• Machine Learning Emulation of 3D Cloud Radiative Effects
• Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models with Real-Geography Boundary Conditions
• Reduced-Order Models for Coupled Dynamical Systems: Data-driven Methods and the Koopman Operator
• Non-local parameterization of atmospheric subgrid processes with neural networks
• Where Are We? Using Scopus to Map the Literature at the Intersection Between Artificial Intelligence and Research on Crime
• Climbing down Charney's ladder: Machine Learning and the post-Dennard era of computational climate science
• Copula-based synthetic data augmentation for machine-learning emulators
• Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models
• Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations
• Stability analysis of chaotic systems from data
• Controlled abstention neural networks for identifying skillful predictions for regression problems
• Data-driven Control of Agent-based Models: an Equation/Variable-free Machine Learning Approach
• Differentiable Programming for Earth System Modeling
• Forecasting: theory and practice
• Machine learning applications for weather and climate need greater focus on extremes
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• Combining data assimilation and machine learning to estimate parameters of a convective-scale model
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• Frame invariant neural network closures for Kraichnan turbulence
• A Primer on Topological Data Analysis to Support Image Analysis Tasks in Environmental Science
• Resampling with neural networks for stochastic parameterization in multiscale systems
• Supervised machine learning to estimate instabilities in chaotic systems: estimation of local Lyapunov exponents
• A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networks
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• Combining data assimilation and machine learning to infer unresolved scale parametrisation
• Subgrid-scale parametrization of unresolved scales in forced Burgers equation using Generative Adversarial Networks (GAN)
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• PCE-PINNs: Physics-Informed Neural Networks for Uncertainty Propagation in Ocean Modeling
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods
• Understanding ML driven HPC: Applications and Infrastructure