Geodesy

Geopotential height

Algorithm

Residual

Benchmark (surveying)

Ecology

Biology

Weather Research and Forecasting Model

Materials science

Forecast skill

Precipitation

Weather forecasting

Range (aeronautics)

Computer science

Climate model

Physics

Climate change

Numerical weather prediction

Geography

Overfitting

Artificial intelligence

Composite material

Deep learning

Meteorology

Artificial neural network

Residual neural network

Convolutional neural network

Machine learning

Journal of Advances in Modeling Earth Systems

Numerical weather prediction has traditionally been based on physical models of the atmosphere. Recently, however, the rise of deep learning has created increased interest in purely data-driven medium-range weather forecasting with first studies exploring the feasibility of such an approach. To accelerate progress in this area, the WeatherBench benchmark challenge was defined. Here, we train a deep residual convolutional neural network (Resnet) to predict geopotential, temperature and precipitation at 5.625 degree resolution up to 5 days ahead. To avoid overfitting and improve forecast skill, we pretrain the model using historical climate model output before fine-tuning on reanalysis data. The resulting forecasts outperform previous submissions to WeatherBench and are comparable in skill to a physical baseline at similar resolution. We also analyze how the neural network creates its predictions and find that, with some exceptions, it is compatible with physical reasoning. Finally, we perform scaling experiments to estimate the potential skill of data-driven approaches at higher resolutions.

Data‐Driven Medium‐Range Weather Prediction With a Resnet Pretrained on Climate Simulations: A New Model for WeatherBench