Training methods for climate and neural network models

Research output: ThesisDoctoral ThesisCollection of Articles

Researchers

Research units

Abstract

When modeling complex phenomena in nature and in technological systems, one is often faced with  the task of tuning/calibrating the models. In such cases, there typically exists a need for model  parameter (and/or meta-parameter) value tuning for more effective modeling performance. Often such cannot be done manually, and in the machine learning approach, the tuning is done in an algorithmic and data-driven manner, and is called model training. The thesis presents studies in which such methods are adopted, in the contexts of climate and artificial neural networks, and proposes novel techniques. One of the studies is on the suitability of a well-known machine learning method called Bayesian optimization (BO), for parametric tuning of chaotic systems such as climate and numerical weatherprediction (NWP) models. The obtained results show that BO is a suitable method for such tuning tasks. A major desiderata for a trained machine learning model is the ability to generalize well to unseen data, and thus the phenomena such as (so-called) under- and overfitting are to be avoided. In this context, adopting (so-called) regularization methods as part of the model training process has become a standard procedure. In this thesis, we introduce a regularization framework that is shown to have close connections with many existing state-of-the-art regularization approaches. An adversarial variant, derived from the proposed regularization framework, is used for solving a classification task, and the obtained results are compared to those of other regularization methods.

Details

Translated title of the contributionTraining methods for climate and neural network models
Original languageEnglish
QualificationDoctor's degree
Awarding Institution
Supervisors/Advisors
Award date14 Dec 2018
Publisher
  • Aalto University
Print ISBNs978-952-60-8258-5
Electronic ISBNs978-952-60-8259-2
Publication statusPublished - 2018
MoE publication typeG5 Doctoral dissertation (article)

    Research areas

  • chaotic systems, filtering, Bayesian optimization

ID: 30203552