Date of Award:

5-2012

Document Type:

Dissertation

Degree Name:

Doctor of Philosophy (PhD)

Department:

Civil and Environmental Engineering

Committee Chair(s)

David K. Stevens

Committee

David K. Stevens

Committee

Thomas Hardy

Committee

Gilberto E. Urroz

Committee

John Schmidt

Committee

Michael J. McFarland

Abstract

The main objective of the research is the development of Multivariate Relevant Vector Machine (MVRVM) to predict suspended fine sediment, water quality constituents, and provide an understanding for the practical problem of determining the amount of data required for the MVRVM. MVRVM is a statistical learning algorithm that is based on Bayes theory. It has been widely used to predict patterns in hydrological systems and other fields. This research represents the first known attempt to use a MVRVM approach to predict transport of very fine sediment and water quality constituents in a complex natural system.

The results demonstrate the ability of the MVRVM to capture and predict the underlying patterns in data. Also careful construction of the experimental design for data collection can lead the Relevant Vectors (RVs is a subset of training observation which carry significant information that is used for prediction) to show locations of significant patterns.

Checksum

987ea0f3da3e8da78b1de04f39fa9bc5

Comments

This work made publicly available electronically on September 18, 2013.

Share

COinS