Journal article · 2021 · Open access

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

Charlie Kirkwood, Theo Economou, Henry M. Odbert, Nicolas Pugeault

Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, 379(2194), 20200099 · Published 15 February 2021 · DOI 10.1098/rsta.2020.0099

Read the free full textCite this paper

In brief

“A framework for probabilistic weather forecast post-processing across models and lead times using machine learning” is a 2021 journal article by Charlie Kirkwood and 3 co-authors, published in Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences. OpenAlex counts 44 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences.

Citations
44
Most cited in
2024 (19)
Field-weighted impact
2.96
References
46
Authors
4

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'.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kirkwood, C., Economou, T., Odbert, H. M., & Pugeault, N. (2021). A framework for probabilistic weather forecast post-processing across models and lead times using machine learning. Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, 379(2194), 20200099. https://doi.org/10.1098/rsta.2020.0099

MLA 9

Kirkwood, Charlie, et al. “A framework for probabilistic weather forecast post-processing across models and lead times using machine learning.” Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, vol. 379, no. 2194, 2021, p. 20200099. https://doi.org/10.1098/rsta.2020.0099.

Chicago

Kirkwood, Charlie, Theo Economou, Henry M. Odbert, and Nicolas Pugeault. 2021. “A framework for probabilistic weather forecast post-processing across models and lead times using machine learning.” Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences 379 (2194): 20200099. https://doi.org/10.1098/rsta.2020.0099.

Harvard

Kirkwood, C. et al. (2021) ‘A framework for probabilistic weather forecast post-processing across models and lead times using machine learning’, Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, 379(2194), p. 20200099. doi:10.1098/rsta.2020.0099.

IEEE

C. Kirkwood, T. Economou, H. M. Odbert, and N. Pugeault, “A framework for probabilistic weather forecast post-processing across models and lead times using machine learning,” Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, vol. 379, no. 2194, p. 20200099, 2021, doi: 10.1098/rsta.2020.0099.

BibTeX

@article{kirkwood2021framework,
  title     = {{A framework for probabilistic weather forecast post-processing across models and lead times using machine learning}},
  author    = {Kirkwood, Charlie and Economou, Theo and Odbert, Henry M. and Pugeault, Nicolas},
  journal   = {Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences},
  year      = {2021},
  volume    = {379},
  number    = {2194},
  pages     = {20200099},
  doi       = {10.1098/rsta.2020.0099},
  url       = {https://doi.org/10.1098/rsta.2020.0099}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202011
202144
202277
202366
20241919
202544
202633

Its field-weighted citation impact is 2.96: it has been cited 2.96 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • probabilistic weather forecasting
  • forecast post-processing
  • numerical weather prediction
  • ensemble model combination
  • quantile regression forest
  • road surface temperature
  • forecast calibration
  • predictive distribution

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Kirkwood, C., Economou, T., Odbert, H. M., & Pugeault, N. (2021). A framework for probabilistic weather forecast post-processing across models and lead times using machine learning. Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, 379(2194), 20200099. https://doi.org/10.1098/rsta.2020.0099

How many times has this paper been cited?

44 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences.

Who wrote this paper?

Charlie Kirkwood, Theo Economou, Henry M. Odbert, Nicolas Pugeault.

What is the DOI of this paper?

10.1098/rsta.2020.0099. The permanent link is https://doi.org/10.1098/rsta.2020.0099.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.