A framework for probabilistic weather forecast post-processing across models and lead times using machine learning

Abstract

Forecasting the weather is an increasingly data-intensive exercise. Numerical weather prediction (NWP) models are becoming more complex, with higher resolutions, and there are increasing numbers of different models in operation. While the forecasting skill of NWP models continues to improve, the number and complexity of these models poses a new challenge for the operational meteorologist: how should the information from all available models, each with their own unique biases and limitations, be combined in order to provide stakeholders with well-calibrated probabilistic forecasts to use in decision making? In this paper, we use a road surface temperature example to demonstrate a three-stage framework that uses machine learning to bridge the gap between sets of separate forecasts from NWP models and the ‘ideal’ forecast for decision support: probabilities of future weather outcomes. First, we use quantile regression forests to learn the error profile of each numerical model, and use these to apply empirically derived probability distributions to forecasts. Second, we combine these probabilistic forecasts using quantile averaging. Third, we interpolate between the aggregate quantiles in order to generate a full predictive distribution, which we demonstrate has properties suitable for decision support. Our results suggest that this approach provides an effective and operationally viable framework for the cohesive post-processing of weather forecasts across multiple models and lead times to produce a well-calibrated probabilistic output. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

“…This site-specific dataset highlights the challenges involved in providing fully probabilistic forecasts from NWP outputs. Kirkwood et al [98] provide more details of the dataset and propose a machine learning-based solution to this forecasting problem. Figure 5 presents an example time series from this dataset.…”

“…Kirkwood et al. [98] provide more details of the dataset and propose a machine learning-based solution to this forecasting problem. Figure 5 presents an example time series from this dataset.…”

Artificial Intelligence Revolutionises Weather Forecast, Climate Monitoring and Decadal Prediction

“…The combination of multiple models can be an effective way to reduce the uncertainty of the forecasts, as demonstrated by using neural network techniques for hurricane intensity forecasts in [61]. An example of the use of DL techniques for the combination of multimodel outputs was given in [62].…”

Bayesian Deep Learning for Spatial Interpolation in the Presence of Auxiliary Information

“…This is one example of how probabilistic machine learning can be used as a guide towards discovery of further knowledge. By outputting a full predictive distribution, the Bayesian deep learning approach can provide probabilistic answers to all sorts of questions (e.g., Cawley et al 2007;Kirkwood et al 2021). Probabilities of exceedance at any location, for example, can be calculated simply as the proportion of probability mass in excess of any chosen threshold.…”