Trial lecture: "Data assimilation approaches for numerical weather prediction. A review of classic and currently used approaches for ensemble data assimilation in numerical weather prediction."
Ordinary opponents:
- First opponent: Professor Thordis Linda Thorarinsdottir, University of Oslo
- Second opponent: Professor Wen-Huang Cheng, National Taiwan University
- The chair of the committee: Professor Sølve Selstø, OsloMet
Leader of the public defence: Associate Professor Boning Feng, OsloMet
Main supervisor: Professor Michael Riegler, OsloMet/SimulaMet
Co-supervisors:
- Professor Hugo Hammer, OsloMet/SimulaMet
- Professor John Bjørnar Bremnes, The Norwegian Meteorological Institute
Abstract
This thesis seeks to improve weather forecasting, by investigating the question: How can we best exploit the potential that lies in the complex nature of meteorological data, using Deep Learning? The work explores different levels of complexity of deep neural networks, the benefits of combining heterogeneous input data in a multimodal neural network, and the value of providing ensembles of weather forecasts to a neural network, all with a view to identify the best ways of extracting the potential within the data.
Through the development of two novel deep learning model architectures, the thesis finds that the combination of data sources in a multimodal network provides great value beyond the use of a single data source; increasing the complexity of the networks does not necessarily translate into improved performance; and the use of ensemble data shows promise, and ought to be explored further in future work.
