Conference paper · 2023 · Open access

Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing

Mariana Clare, Zied Ben Bouallègue, Matthew Chantry, Martin Leutbecher, Thomas Haiden

EGU General Assembly Conference Abstracts · Published 22 February 2023 · DOI 10.5194/egusphere-egu23-946

Read the free full textCite this paper

In brief

“Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing” is a 2023 conference paper by Mariana Clare and 4 co-authors, published in EGU General Assembly Conference Abstracts. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at EGU General Assembly Conference Abstracts.

Citations
0
Authors
5

Abstract

The large data volumes available in weather forecasting make post-processing an attractive field for applying machine learning. In turn, novel statistical machine learning methods that can be used to generate uncertainty information from a deterministic forecast are of great interest to forecast users, especially given the computational cost of running high resolution ensembles. In this work, we show how one such method, a Bayesian Neural Network (BNN), can be used to post-process a single global high resolution forecast for 2m temperature. This methodology improves both the accuracy of the forecast and adds uncertainty information, by predicting the distribution of the forecast error relative to its own analysis.Here we assess both model and data uncertainty using two different BNN approaches. In the first approach, the BNN’s parameters are defined to be distributions rather than deterministic parameters, thereby generating an ensemble of models that can be used to quantify model uncertainty. In the second approach, the BNN remains deterministic but predicts a distribution rather than a deterministic output thereby quantifying data uncertainty. Our BNN results are benchmarked against simpler statistical methods, as well as statistics from the ECMWF operational ensemble.Finally, in order to add trustworthiness to the BNN predictions, we apply an explainable AI technique (Layerwise Relevance Propagation) so as to understand whether the variables on which the BNN bases its prediction are physically reasonable or whether it is instead learning spurious correlations.

Cite this paper

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

APA 7

Clare, M., Bouallègue, Z. B., Chantry, M., Leutbecher, M., & Haiden, T. (2023). Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu23-946

MLA 9

Clare, Mariana, et al. “Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing.” EGU General Assembly Conference Abstracts, 2023. https://doi.org/10.5194/egusphere-egu23-946.

Chicago

Clare, Mariana, Zied Ben Bouallègue, Matthew Chantry, Martin Leutbecher, and Thomas Haiden. 2023. “Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing.” EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu23-946.

Harvard

Clare, M. et al. (2023) ‘Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing’, EGU General Assembly Conference Abstracts. doi:10.5194/egusphere-egu23-946.

IEEE

M. Clare, Z. B. Bouallègue, M. Chantry, M. Leutbecher, and T. Haiden, “Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing,” EGU General Assembly Conference Abstracts, 2023, doi: 10.5194/egusphere-egu23-946.

BibTeX

@inproceedings{clare2023combining,
  title     = {{Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing}},
  author    = {Clare, Mariana and Bouallègue, Zied Ben and Chantry, Matthew and Leutbecher, Martin and Haiden, Thomas},
  booktitle = {EGU General Assembly Conference Abstracts},
  year      = {2023},
  doi       = {10.5194/egusphere-egu23-946},
  url       = {https://doi.org/10.5194/egusphere-egu23-946}
}

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

  • Bayesian neural networks
  • probabilistic forecasting
  • weather forecasting
  • forecast post-processing
  • uncertainty quantification
  • model uncertainty
  • data uncertainty
  • layer-wise relevance propagation

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?

Clare, M., Bouallègue, Z. B., Chantry, M., Leutbecher, M., & Haiden, T. (2023). Combining Bayesian Neural Networks with explainable AI techniques for trustworthy probabilistic post-processing. EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu23-946

How many times has this paper been cited?

0 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 EGU General Assembly Conference Abstracts.

Who wrote this paper?

Mariana Clare, Zied Ben Bouallègue, Matthew Chantry, Martin Leutbecher, Thomas Haiden.

What is the DOI of this paper?

10.5194/egusphere-egu23-946. The permanent link is https://doi.org/10.5194/egusphere-egu23-946.

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.