A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts.

Despite continuous improvements, precipitation forecasts are still not as accurate and reliable as those of other meteorological variables. A major contributing factor to this is that several key processes affecting precipitation distribution and intensity occur below the resolved scale of global weather models. Generative adversarial networks (GANs) have been demonstrated by the computer vision community to be successful at super-resolution problems, that is, learning to add fine-scale structure to coarse images. Leinonen et al. (2020, https://doi.org/10.1109/TGRS.2020.3032790) previously applied a GAN to produce ensembles of reconstructed high-resolution atmospheric fields, given coarsened input data. In this paper, we demonstrate this approach can be extended to the more challenging problem of increasing the accuracy and resolution of comparatively low-resolution input from a weather forecasting model, using high-resolution radar measurements as a "ground truth." The neural network must learn to add resolution and structure whilst accounting for non-negligible forecast error. We show that GANs and VAE-GANs can match the statistical properties of state-of-the-art pointwise post-processing methods whilst creating high-resolution, spatially coherent precipitation maps. Our model compares favorably to the best existing downscaling methods in both pixel-wise and pooled CRPS scores, power spectrum information and rank histograms (used to assess calibration). We test our models and show that they perform in a range of scenarios, including heavy rainfall.

Machine Learning Emulation of Gravity Wave Drag in Numerical Weather Forecasting.

We assess the value of machine learning as an accelerator for the parameterization schemes of operational weather forecasting systems, specifically the parameterization of nonorographic gravity wave drag. Emulators of this scheme can be trained to produce stable and accurate results up to seasonal forecasting timescales. Generally, networks that are more complex produce emulators that are more accurate. By training on an increased complexity version of the existing parameterization scheme, we build emulators that produce more accurate forecasts. For medium range forecasting, we have found evidence that our emulators are more accurate than the version of the parametrization scheme that is used for operational predictions. Using the current operational CPU hardware, our emulators have a similar computational cost to the existing scheme, but are heavily limited by data movement. On GPU hardware, our emulators perform 10 times faster than the existing scheme on a CPU.

Opportunities and challenges for machine learning in weather and climate modelling: hard, medium and soft AI.

In September 2019, a workshop was held to highlight the growing area of applying machine learning techniques to improve weather and climate prediction. In this introductory piece, we outline the motivations, opportunities and challenges ahead in this exciting avenue of research. This article is part of the theme issue 'Machine learning for weather and climate modelling'.