Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction

Abstract

Dynamical weather and climate prediction models underpin many studies of the Earth system and hold the promise of being able to make robust projections of future climate change based on physical laws. However, simulations from these models still show many differences compared with observations. Machine learning has been applied to solve certain prediction problems with great success, and recently it's been proposed that this could replace the role of physically-derived dynamical weather and climate models to give better quality simulations. Here, instead, a framework using machine learning together with physically-derived models is tested, in which it is learnt how to correct the errors of the latter from timestep to timestep. This maintains the physical understanding built into the models, whilst allowing performance improvements, and also requires much simpler algorithms and less training data. This is tested in the context of simulating the chaotic Lorenz '96 system, and it is shown that the approach yields models that are stable and that give both improved skill in initialised predictions and better long-term climate statistics. Improvements in long-term statistics are smaller than for single time-step tendencies, however, indicating that it would be valuable to develop methods that target improvements on longer time scales. Future strategies for the development of this approach and possible applications to making progress on important scientific problems are discussed.

arXiv comment26p, 7 figures To be published in Journal of Advances in Modeling Earth Systems

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Deep learning to represent sub-grid processes in climate models
• Neural networks for post-processing ensemble weather forecasts
• Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations
• Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events
• Toward an AI Physicist for Unsupervised Learning
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Optimisation of an idealised ocean model, stochastic parameterisation of sub-grid eddies
• Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles

Cited by in corpus (16)

• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• Bridging observation, theory and numerical simulation of the ocean using Machine Learning
• Using machine learning to correct model error in data assimilation and forecast applications
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Machine learning for weather and climate are worlds apart
• 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
• Inferring unknown unknowns: Regularized bias-aware ensemble Kalman filter
• Machine learning applications for weather and climate need greater focus on extremes
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• Development of an offline and online hybrid model for the Integrated Forecasting System
• Sparse Symplectically Integrated Neural Networks
• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case
• Programming with Neural Surrogates of Programs
• A comparison of data-driven approaches to build low-dimensional ocean models