Combining distribution-based neural networks to predict weather forecast probabilities

Abstract

The success of deep learning techniques over the last decades has opened up a new avenue of research for weather forecasting. Here, we take the novel approach of using a neural network to predict full probability density functions at each point in space and time rather than a single output value, thus producing a probabilistic weather forecast. This enables the calculation of both uncertainty and skill metrics for the neural network predictions, and overcomes the common difficulty of inferring uncertainty from these predictions. This approach is data-driven and the neural network is trained on the WeatherBench dataset (processed ERA5 data) to forecast geopotential and temperature 3 and 5 days ahead. Data exploration leads to the identification of the most important input variables, which are also found to agree with physical reasoning, thereby validating our approach. In order to increase computational efficiency further, each neural network is trained on a small subset of these variables. The outputs are then combined through a stacked neural network, the first time such a technique has been applied to weather data. Our approach is found to be more accurate than some numerical weather prediction models and as accurate as more complex alternative neural networks, with the added benefit of providing key probabilistic information necessary for making informed weather forecasts.

arXiv comment21 pages, 14 figures, Github repository: https://github.com/mc4117/ResNet_Weather, Submitted to Quarterly Journal of the Royal Meteorological Society

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Neural networks for post-processing ensemble weather forecasts
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions
• Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere
• Deep Learning for Post-Processing Ensemble Weather Forecasts
• Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models
• Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
• Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining

Cited by in corpus (6)

• SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
• Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics
• 3D-Var Data Assimilation using a Variational Autoencoder
• Evaluation of Machine Learning Techniques for Forecast Uncertainty Quantification
• Latent assimilation with implicit neural representations for unknown dynamics
• Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks