Aarhus University Seal / Aarhus Universitets segl

Artificial Intelligence for improved weather forecasts – new frontiers in data-driven methods for improved weather and renewable energy forecasts

PhD defence, Wednesday 25 May 2022. Andreas Holm Nielsen.

Andreas Holm Nielsen

During his PhD studies, Andreas Holm Nielsen researched fully data-driven methods for improving weather and renewable energy forecasting.  Accurate weather forecasts play an important role in our daily lives, ranging from everyday conveniences such as precipitation and temperature estimates to more critical and potentially life-threatening scenarios of hazardous and extreme weather. In this regard, Andreas Holm Nielsen studied how advanced artificial intelligence and machine learning methods compare with existing state-of-the-art models within this field and the extent to which these methods can learn the fundamental dynamics of our atmosphere.

The findings from the research contribute to the rapidly growing field of machine learning for weather forecasting, and it showed promising results for several short-term and medium-term weather forecasting tasks, even compared to some of the best existing meteorological and numerical weather prediction models.


The PhD study was completed at the Department of Electrical and Computer Engineering – Signal Processing and Machine Learning, Faculty of Technical Sciences, Aarhus University.

This summary was prepared by the PhD student.

Time: 25-05-2022,  15.00-18.00 UTC +2
Place: 5125-430, Finlandgade 22, 8200 Aarhus C, Denmark
Title of PhD thesis: Data-Driven Weather Forecasting using Deep Learning

Contact information: Andreas Holm Nielsen, e-mail: andreashn@gmail.com, tel.: +45 61679620

Members of the assessment committee:

Professor Pierre Pinson, Department of Technology, Management and Economics Management Science, Technical University of Denmark (DTU), Denmark

David John Gagne, Computational & Information Systems Lab, National Center for Atmospheric Research (NCAR), Colorado, USA

Associate Professor Qi Zhang (chair), Department of Electrical and Computer Engineering, Aarhus University, Denmark

Main supervisor:
Professor (Docent) Henrik Karstoft, Department of Electrical and Computer Engineering – Signal Processing and Machine Learning, Aarhus University, Denmark

Co-supervisor:
Professor Alexandros Iosifidis Department of Electrical and Computer Engineering – Signal Processing and Machine Learning, Aarhus University, Denmark

Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS,

Katrinebjergvej 89F, building 5132, 8200 Aarhus N.

17427 / i43