A Bayesian Deep Learning Approach to Near-Term Climate Prediction

Abstract

Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of predicting natural variability of the North Atlantic sea surface temperature on the interannual timescale in the pre-industrial control simulation of the Community Earth System Model (CESM2). While previous works have considered the use of recurrent networks such as convolutional LSTMs and reservoir computing networks in this and other similar problem settings, we currently focus on the use of feedforward convolutional networks. In particular, we find that a feedforward convolutional network with a Densenet architecture is able to outperform a convolutional LSTM in terms of predictive skill. Next, we go on to consider a probabilistic formulation of the same network based on Stein variational gradient descent and find that in addition to providing useful measures of predictive uncertainty, the probabilistic (Bayesian) version improves on its deterministic counterpart in terms of predictive skill. Finally, we characterize the reliability of the ensemble of ML models obtained in the probabilistic setting by using analysis tools developed in the context of ensemble numerical weather prediction.

arXiv comment32 pages, 12 figures

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Improving neural networks by preventing co-adaptation of feature detectors
• Variational Inference: A Review for Statisticians
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• A guide to convolution arithmetic for deep learning
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
• Reservoir Computing as a Tool for Climate Predictability Studies
• Bayesian deep learning with hierarchical prior: Predictions from limited and noisy data
• Feature Importance in a Deep Learning Climate Emulator

Cited by in corpus (1)

• Uncertainties of Satellite-based Essential Climate Variables from Deep Learning