Dissertation · 2023 · Open access
Machine Learning for Improved Weather and Climate Predictions
TSpace (University of Toronto) · Published 1 November 2023
In brief
“Machine Learning for Improved Weather and Climate Predictions” is a 2023 dissertation by Soukayna Mouatadid, published in TSpace (University of Toronto). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at TSpace (University of Toronto).
- Citations
- 0
- Authors
- 1
Abstract
Numerical prediction models that simulate the complex and chaotic atmospheric system have successfully transformed the field of weather and climate prediction in recent decades. However, there are several real-world scenarios in which numerical models prove to be slow, uncertain or biased. These models are characterized by immense computational costs due to the large amounts of data they regularly process. This raises the question: how can we use machine learning to efficiently improve the accuracy of weather and climate predictions? In this thesis, we introduce novel algorithms for tackling the stubbornly challenging task of subseasonal forecasting.We start by exploring whether we can train neural networks to emulate the full dynamics of a numerical weather prediction (NWP) model and predict the global atmospheric flow in the medium-range. Creating such a forecast requires understanding complex atmospheric dynamics as well as the interplay between several variables across a range of scales. We show that neural networks can indeed perform this task, closely emulating the one performed by physical NWP models. We then use the task and dataset defined in this work, to establish the first benchmark for medium-range data-driven weather forecasting. An even more challenging forecasting task is sub-seasonal to seasonal climate prediction. While the accuracy of short-term forecasting is sustained by physics-based dynamical models, these models, due to their deterministic nature, suffer from a decrease in skill on subseasonal to seasonal timescales. We tackle this problem using a hybrid dynamical-learning approach and introduce an adaptive bias correction algorithm that outperforms both de-biased NWP models as well as state-of-the-art learning models. We conclude this thesis by discussing the future directions and challenges in data-driven weather and climate prediction, with the aim of identifying our approaches’ shortcomings and limiting assumptions. The studies presented in this thesis illustrate how large and varied data, an increase in computing resources, and advances in deep learning intersect, meet and collide to create a fertile playground for a promising field of research.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Mouatadid, S. (2023). Machine Learning for Improved Weather and Climate Predictions. TSpace (University of Toronto). https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download
MLA 9
Mouatadid, Soukayna. “Machine Learning for Improved Weather and Climate Predictions.” TSpace (University of Toronto), 2023. https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download.
Chicago
Mouatadid, Soukayna. 2023. “Machine Learning for Improved Weather and Climate Predictions.” TSpace (University of Toronto). https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download.
Harvard
Mouatadid, S. (2023) ‘Machine Learning for Improved Weather and Climate Predictions’, TSpace (University of Toronto). Available at: https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download.
IEEE
S. Mouatadid, “Machine Learning for Improved Weather and Climate Predictions,” TSpace (University of Toronto), 2023.
BibTeX
@phdthesis{mouatadid2023machine,
title = {{Machine Learning for Improved Weather and Climate Predictions}},
author = {Mouatadid, Soukayna},
year = {2023},
url = {https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download}
}
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
- subseasonal forecasting
- seasonal climate prediction
- medium-range forecasting
- atmospheric dynamics
Work with this paper
Most-cited papers in Earth and Planetary Sciences
- The ERA5 global reanalysisHans Hersbach, Bill Bell, Paul Berrisford and 40 more · Quarterly Journal of the Royal Meteorological Society · 2020 · 35,424 citations
- The NCEP/NCAR 40-Year Reanalysis ProjectEugenia Kalnay, Masao Kanamitsu, Robert E. Kistler and 19 more · Bulletin of the American Meteorological Society · 1996 · 28,486 citations
- Chemical and isotopic systematics of oceanic basalts: implications for mantle composition and processesShen‐Su Sun, W. F. McDonough · Geological Society London Special Publications · 1989 · 26,603 citations
- The ERA‐Interim reanalysis: configuration and performance of the data assimilation systemDick P. Dee, Sakari M. Uppala, A. J. Simmons and 33 more · Quarterly Journal of the Royal Meteorological Society · 2011 · 25,245 citations
- PAST: PALEONTOLOGICAL STATISTICAL SOFTWARE PACKAGE FOR EDUCATION AND DATA ANALYSISØyvind Hammer, David A. T. Harper, Paul D. Ryan · 2001 · 17,871 citations
Questions about this paper
How do I cite this paper in APA style?
Mouatadid, S. (2023). Machine Learning for Improved Weather and Climate Predictions. TSpace (University of Toronto). https://utoronto.scholaris.ca/bitstreams/3484f7cd-aa78-4dbf-b0cb-2573bf082b28/download
How many times has this paper been cited?
0 times, according to OpenAlex on 20 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 at TSpace (University of Toronto): sign in and open the full text from this page.
Who wrote this paper?
Soukayna Mouatadid.
Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.