A comparison of data-driven approaches to build low-dimensional ocean models

Abstract

We present a comprehensive inter-comparison of linear regression (LR), stochastic, and deep-learning approaches for reduced-order statistical emulation of ocean circulation. The reference dataset is provided by an idealized, eddy-resolving, double-gyre ocean circulation model. Our goal is to conduct a systematic and comprehensive assessment and comparison of skill, cost, and complexity of statistical models from the three methodological classes. The model based on LR is considered as a baseline. Additionally, we investigate its additive white noise augmentation and a multi-level stochastic approach, deep-learning methods, hybrid frameworks (LR plus deep-learning), and simple stochastic extensions of deep-learning and hybrid methods. The assessment metrics considered are: root mean squared error, anomaly cross-correlation, climatology, variance, frequency map, forecast horizon, and computational cost. We found that the multi-level linear stochastic approach performs the best for both short- and long-timescale forecasts. The deep-learning hybrid models augmented by additive state-dependent white noise came second, while their deterministic counterparts failed to reproduce the characteristic frequencies in climate-range forecasts. Pure deep learning implementations performed worse than LR and its noise augmentations. Skills of LR and its white noise extension were similar on short timescales, but the latter performed better on long timescales, while LR-only outputs decay to zero for long simulations. Overall, our analysis promotes multi-level LR stochastic models with memory effects, and hybrid models with linear dynamical core augmented by additive stochastic terms learned via deep learning, as a more practical, accurate, and cost-effective option for ocean emulation than pure deep-learning solutions.

arXiv comment47 pages, 9 figures, submitted to Journal of Advances in Modelling Earth Systems

References in corpus (16)

• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Prediction of Sea Surface Temperature using Long Short-Term Memory
• Stochastic Parameterization: Towards a new view of Weather and Climate Models
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• Data-driven non-Markovian closure models
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Global Existence and Regularity for the 3D Stochastic Primitive Equations of the Ocean and Atmosphere with Multiplicative White Noise
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Reservoir Computing as a Tool for Climate Predictability Studies
• Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning
• Interpreting neural network models of residual scalar flux