Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere

Abstract

We present a significantly-improved data-driven global weather forecasting framework using a deep convolutional neural network (CNN) to forecast several basic atmospheric variables on a global grid. New developments in this framework include an offline volume-conservative mapping to a cubed-sphere grid, improvements to the CNN architecture, and the minimization of the loss function over multiple steps in a prediction sequence. The cubed-sphere remapping minimizes the distortion on the cube faces on which convolution operations are performed and provides natural boundary conditions for padding in the CNN. Our improved model produces weather forecasts that are indefinitely stable and produce realistic weather patterns at lead times of several weeks and longer. For short- to medium-range forecasting, our model significantly outperforms persistence, climatology, and a coarse-resolution dynamical numerical weather prediction (NWP) model. Unsurprisingly, our forecasts are worse than those from a high-resolution state-of-the-art operational NWP system. Our data-driven model is able to learn to forecast complex surface temperature patterns from few input atmospheric state variables. On annual time scales, our model produces a realistic seasonal cycle driven solely by the prescribed variation in top-of-atmosphere solar forcing. Although it is currently less accurate than operational weather forecasting models, our data-driven CNN executes much faster than those models, suggesting that machine learning could prove to be a valuable tool for large-ensemble forecasting.

arXiv commentManuscript submitted to Journal of Advances in Modeling Earth Systems

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Deep learning to represent sub-grid processes in climate models
• Neural networks for post-processing ensemble weather forecasts
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• Analog forecasting of extreme-causing weather patterns using deep learning
• Artistic style transfer for videos and spherical images
• A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networks
• State-of-the-art in 360° Video/Image Processing: Perception, Assessment and Compression

Cited by in corpus (27)

• Neural General Circulation Models for Weather and Climate
• Will Artificial Intelligence supersede Earth System and Climate Models?
• Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
• Bridging observation, theory and numerical simulation of the ocean using Machine Learning
• Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models
• Evaluation of post-hoc interpretability methods in time-series classification
• SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
• Combining distribution-based neural networks to predict weather forecast probabilities
• Variational Quantum Solutions to the Advection-Diffusion Equation for Applications in Fluid Dynamics
• Reservoir Computing as a Tool for Climate Predictability Studies
• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Reduced-Order Models for Coupled Dynamical Systems: Data-driven Methods and the Koopman Operator
• Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers
• Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems
• A Practical Probabilistic Benchmark for AI Weather Models
• 3D-Var Data Assimilation using a Variational Autoencoder
• BAMCAFE: A Bayesian Machine Learning Advanced Forecast Ensemble Method for Complex Turbulent Systems with Partial Observations
• A Deep Learning Earth System Model for Efficient Simulation of the Observed Climate
• Log-Gaussian Gamma Processes for Training Bayesian Neural Networks in Raman and CARS Spectroscopies
• Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
• Latent assimilation with implicit neural representations for unknown dynamics
• Community Research Earth Digital Intelligence Twin (CREDIT)
• Bridging Logic Programming and Deep Learning for Explainability through ILASP
• Spatial verification of global precipitation forecasts
• HydroChronos: Forecasting Decades of Surface Water Change
• Smoothing and spatial verification of global fields
• A comparison of data-driven approaches to build low-dimensional ocean models