• Benchmarks with strong baselines are a key ingredient for rapid progress on a problem. • Here, we define a benchmark for data-driven global, medium-range weather prediction. • The data is processed for convenient use in machine learning models and a quickstart guide is provided.
We develop elementary weather prediction models using deep convolutional neural networks (CNNs) trained on past weather data to forecast one or two fundamental meteorological fields on a Northern Hemisphere grid with no explicit knowledge about physical processes. At forecast lead times up to 3 days, CNNs trained to predict only 500‐hPa geopotential height easily outperform persistence, climatology, and the dynamics‐based barotropic vorticity model, but do not beat an operational full‐physics weather prediction model. These CNNs are capable of forecasting significant changes in the intensity of weather systems, which is notable because this is beyond the capability of the fundamental dynamical equation that relies solely on 500‐hPa data, the barotropic vorticity equation. Modest improvements to the CNN forecasts can be made by adding 700‐ to 300‐hPa thickness to the input data. Our best performing CNN does a good job of capturing the climatology and annual variability of 500‐hPa heights and is capable of forecasting realistic atmospheric states at lead times of 14 days. Although our simple models do not perform better than an operational weather model, machine learning warrants further exploration as a weather forecasting tool; in particular, the potential efficiency of CNNs might make them attractive for ensemble forecasting.
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 off‐line 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 currently does not compete with 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.
One important limitation on the accuracy of weather forecasts is imposed by unavoidable errors in the specification of the atmosphere’s initial state. Much theoretical concern has been focused on the limits to predictability imposed by small-scale errors, potentially even those on the scale of a butterfly. Very modest errors at much larger scales may nevertheless pose a more important practical limitation. We demonstrate the importance of large-scale uncertainty by analyzing ensembles of idealized squall-line simulations. Our results imply that minimizing initial errors on scales around 100 km is more likely to extend the accuracy of forecasts at lead times longer than 3–4 h than efforts to minimize initial errors on much smaller scales. These simulations also demonstrate that squall lines, triggered in a horizontally homogeneous environment with no initial background circulations, can generate a background mesoscale kinetic energy spectrum roughly similar to that observed in the atmosphere.
An ensemble forecast system is developed using convolution neural networks (CNNs) to generate data-driven global forecasts.• Only 3 seconds are required to compute a large 320-member ensemble of skillful 10 6-week sub-seasonal predictions.
11• Shorter lead time forecasts also show skill, including a single deterministic 4-day 12 forecast for Hurricane Irma.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.