WeatherBench: A Benchmark Data Set for Data‐Driven Weather Forecasting

Rasp, Stephan; Dueben, Peter; Scher, Sebastian; Weyn, Jonathan A.; Mouatadid, Soukayna; Thuerey, Nils

doi:10.1029/2020ms002203

Cited by 227 publications

(187 citation statements)

References 69 publications

Supporting

Mentioning

186

Contrasting

Unclassified

Order By: Relevance

“…The ECMWF S2S forecasts are available at https://apps.ecmwf.int/datasets/data/s2s. The T42 and T63 IFS forecasts are available from Rasp et al (2020b).…”

Section: Data Availability Statementmentioning

confidence: 99%

Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere

Weyn

Durran

Caruana

2020

J Adv Model Earth Syst

Self Cite

145

123

View full text Add to dashboard Cite

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.

show abstract

“…The ECMWF S2S forecasts are available at https://apps.ecmwf.int/datasets/data/s2s. The T42 and T63 IFS forecasts are available from Rasp et al (2020b).…”

Section: Data Availability Statementmentioning

confidence: 99%

Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere

Weyn

Durran

Caruana

2020

J Adv Model Earth Syst

Self Cite

145

123

View full text Add to dashboard Cite

show abstract

“…What is largely missing in the field of meteorological DL are benchmark datasets with a specification of appropriate baseline scores and software frameworks which make it easy for the DL community to adopt a meteorological problem and try out different approaches. One notable exception is Weatherbench [ 142 ]. Such benchmark datasets and frameworks are well established in the ML community (e.g.…”

Section: Discussionmentioning

confidence: 99%

Can deep learning beat numerical weather prediction?

Schultz

Betancourt

Gong

et al. 2021

Phil. Trans. R. Soc. A.

194

127

View full text Add to dashboard Cite

The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

show abstract

“…While data‐driven integrations of such complex models of small‐scale processes can be difficult, there are reasons to be encouraged. One reason is that recent studies in the climate science and fluid dynamics communities have shown promising results of fully DD 2D or 3D spatiotemporal forecasting of complex, chaotic dynamical systems with RNNs, CNNs, or convolutional RNNs (Chattopadhyay, Hassanzadeh, & Pasha, 2020; Chattopadhyay, Hassanzadeh, & Subramanian 2020; Chattopadhyay, Mustafa, et al, 2020; Chattopadhyay, Nabizadeh, et al, 2020; Dueben & Bauer, 2018; Mohan et al, 2019, 2020; Pathak et al, 2018; Rasp et al, 2020; Scher, 2018; Scher & Messori, 2019a, 2019b; Wang et al, 2019; Weyn et al, 2019; Wu et al, 2020). Such methods, particularly with some key physics‐based constraints enforced, can be used to integrate the 2D or 3D complex governing equations of the small‐scale processes data‐drivenly.…”

Section: Discussionmentioning

confidence: 99%

Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning

Chattopadhyay

Subel

Hassanzadeh

2020

J Adv Model Earth Syst

View full text Add to dashboard Cite

To make weather and climate models computationally affordable, small-scale processes are usually represented in terms of the large-scale, explicitly resolved processes using physics-based/ semi-empirical parameterization schemes. Another approach, computationally more demanding but often more accurate, is super-parameterization (SP). SP involves integrating the equations of small-scale processes on high-resolution grids embedded within the low-resolution grid of large-scale processes. Recently, studies have used machine learning (ML) to develop data-driven parameterization (DD-P) schemes. Here, we propose a new approach, data-driven SP (DD-SP), in which the equations of the small-scale processes are integrated data-drivenly (thus inexpensively) using ML methods such as recurrent neural networks. Employing multiscale Lorenz 96 systems as the testbed, we compare the cost and accuracy (in terms of both short-term prediction and long-term statistics) of parameterized low-resolution (PLR) SP, DD-P, and DD-SP models. We show that with the same computational cost, DD-SP substantially outperforms PLR and is more accurate than DD-P, particularly when scale separation is lacking. DD-SP is much cheaper than SP, yet its accuracy is the same in reproducing long-term statistics (climate prediction) and often comparable in short-term forecasting (weather prediction). We also investigate generalization: when models trained on data from one system are applied to a more chaotic system, we find that models often do not generalize, particularly when short-term prediction accuracies are examined. However, we show that transfer learning, which involves retraining the data-driven model with a small amount of data from the new system, significantly improves generalization. Potential applications of DD-SP and transfer learning in climate/weather modeling are discussed. Plain Language Summary The weather/climate system involves intertwined physical processes acting on scales from centimeters (or even smaller) to tens of thousands of kilometers. Most weather/climate models used in practice include parameterization schemes that relate small-scale processes, which are not explicitly resolved (due to coarse spatiotemporal resolution), to large-scale processes that are resolved. Recently, studies have explored using machine learning for data-driven parameterization (DD-P) of small-scale (subgrid) processes. Here, we first introduce a novel way to leverage recent advances in deep learning to improve the modeling of subgrid processes. In this approach, called data-driven super-parameterization (DD-SP), deep learning is used for fast, data-driven integration of equations of small-scale processes, while other equations are integrated using conventional numerical methods. Employing a relatively simple chaotic system, we show the advantages of DD-SP over DD-P and conventional parameterizations. Second, we examine how these data-driven models generalize (extrapolate) from one system to other (e.g., more chaotic) systems. We demonstrate that these mod...

show abstract

WeatherBench: A Benchmark Data Set for Data‐Driven Weather Forecasting

Abstract: • 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.

Cited by 227 publications

References 69 publications

Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere

Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere

Can deep learning beat numerical weather prediction?

Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning

Contact Info

Product

Resources

About