Preprint · 2023 · Open access

Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts

Luke Conibear, Ashley E. Payne, Allison E Reed Harris, Tyler C. McCandless, Steven J. Brey, Kushal Keshavamurthy, Maxfield E Green, Stylianos Flampouris, Luke Thomas Peffers

Published 27 October 2023 · DOI 10.22541/essoar.169841550.08343114/v1

Free PDFView at the publisherCite this paper

In brief

“Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts” is a 2023 preprint by Luke Conibear and 8 co-authors. OpenAlex counts 1 citations as of 16 November 2026. It is open access under a CC BY-NC licence: the full text is free to read.

Citations
1
Most cited in
2025 (1)
References
52
Authors
9

Abstract

We present a machine learning model that post-processes high-resolution, deterministic forecasts to produce short to medium-range probabilistic forecasts for seven core weather variables.We developed and operationally implemented a multi-task neural network with a custom loss function, the Continuous Ranked Probability Score (CRPS), using input data from the High Resolution Rapid Refresh (HRRR) model.This combined high-resolution Numerical Weather Prediction (NWP) modeling with machine learning to generate more accurate deterministic and probabilistic forecasts.The results show deterministic forecast improvements in Root Mean Squared Error (RMSE) from 3% to 25% and probabilistic improvements in CRPS from 31% to 45% over the HRRR model.The multi-task neural network is cheap to train and fast to run operationally on hourly forecasts.SIGNIFICANCE STATEMENT: Weather forecasting is a challenging problem.Operational forecasts use numerical weather prediction (NWP) models that solve physical equations.These weather forecasts are statistically post-processed to correct errors.Traditionally, uncertainties in the forecasts are captured by creating an ensemble of deterministic predictions with variations in the initial conditions and the NWP model.In this study, we developed a post-processing system to correct weather forecasting errors relative to observations and to produce probabilistic ensembles.Our system uses machine learning to generate more accurate deterministic and probabilistic weather forecasts.The post-processing system is cheap, fast, and deployed operationally.

Cite this paper

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

APA 7

Conibear, L., Payne, A. E., Harris, A. E. R., McCandless, T. C., Brey, S. J., Keshavamurthy, K., Green, M. E., Flampouris, S., & Peffers, L. T. (2023). Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts. https://doi.org/10.22541/essoar.169841550.08343114/v1

MLA 9

Conibear, Luke, et al. “Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts.” 2023. https://doi.org/10.22541/essoar.169841550.08343114/v1.

Chicago

Conibear, Luke, Ashley E. Payne, Allison E Reed Harris, Tyler C. McCandless, Steven J. Brey, Kushal Keshavamurthy, Maxfield E Green, Stylianos Flampouris, and Luke Thomas Peffers. 2023. “Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts.” https://doi.org/10.22541/essoar.169841550.08343114/v1.

Harvard

Conibear, L. et al. (2023) ‘Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts’. doi:10.22541/essoar.169841550.08343114/v1.

IEEE

L. Conibear et al., “Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts,” 2023, doi: 10.22541/essoar.169841550.08343114/v1.

BibTeX

@misc{conibear2023post,
  title     = {{Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts}},
  author    = {Conibear, Luke and Payne, Ashley E. and Harris, Allison E Reed and McCandless, Tyler C. and Brey, Steven J. and Keshavamurthy, Kushal and Green, Maxfield E and Flampouris, Stylianos and Peffers, Luke Thomas},
  year      = {2023},
  doi       = {10.22541/essoar.169841550.08343114/v1},
  url       = {https://doi.org/10.22541/essoar.169841550.08343114/v1}
}

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

Topic and keywords

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

  • probabilistic weather forecasting
  • forecast post-processing
  • multi-task neural network
  • continuous ranked probability score
  • HRRR model
  • operational forecasting
  • forecast uncertainty
  • numerical weather prediction

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?

Conibear, L., Payne, A. E., Harris, A. E. R., McCandless, T. C., Brey, S. J., Keshavamurthy, K., Green, M. E., Flampouris, S., & Peffers, L. T. (2023). Post-processing using deep learning to create operational, high-resolution, and probabilistic weather forecasts. https://doi.org/10.22541/essoar.169841550.08343114/v1

How many times has this paper been cited?

1 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.

Who wrote this paper?

Luke Conibear, Ashley E. Payne, Allison E Reed Harris, Tyler C. McCandless, Steven J. Brey, Kushal Keshavamurthy, Maxfield E Green, Stylianos Flampouris, Luke Thomas Peffers.

What is the DOI of this paper?

10.22541/essoar.169841550.08343114/v1. The permanent link is https://doi.org/10.22541/essoar.169841550.08343114/v1.

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.