Bayesian Hierarchical Space-Time Models with Application to Significant Wave Height

This book provides an example of a thorough statistical treatment in space and time of ocean wave data. It is demonstrated how the flexible framework of Bayesian hierarchical space-time models can be applied to oceanographic processes such as significant wave height in order to describe dependence structures and uncertainties in the data.

This monograph is a research book and it is in some sense cross-disciplinary. The methodology itself is firmly rooted in the statistical research tradition, based on probability theory and stochastic processes. However, the methodology has been applied to a problem within physical oceanography, analysing data for significant wave height, which are of crucial importance to ocean engineering disciplines. Indeed, the statistical properties of significant wave height are important for the design, construction and operation of ships and other marine and coastal structures. Furthermore, the book addresses the question of whether climate change has an effect of the ocean wave climate, and if so what these effects might be. Thus, this book is an important contribution to the on-going debate on climate change, its implications and how to adapt to a changing climate, with a particular focus on the maritime industries and the marine environment.

This book should be of general interest to anyone with an interest in statistical modelling of environmental processes, and in particular to those with a particular interest in the ocean wave climate. It is written on a level that should be understandable to everyone with a basic background in statistics or elementary mathematics, and an introduction to some basic concepts is given in appendices for the uninitiated reader. The intended readership incudes students and professionals involved in statistics, oceanography, ocean engineering, environmental research, climate sciences and risk assessment. Moreover, different stakeholders within the maritime industries such as design offices, classification societies, ship owners, yards and operators, flag states and intergovernmental agencies such as the IMO might find the results relevant.
show more

Preface.- Acronyms.- 1.Introduction and Background.- 2.Literature Survey on StochasticWave Models.- 3.A Bayesian Hierarchical Space-Time Model for Significant Wave Height.- 4.Including a Log-Transform of the Data.- 6.Bayesian Hierarchical Modelling of the Ocean Windiness.- 7.Application: Impacts on Ship Structural Loads.- 8.Case study: Modelling the Effect of Climate Change on the World's Oceans.- 9.Summary and Conclusions.- A.Markov Chain Monte Carlo Methods.- B.Extreme Value Modelling.- C.Markov Random Fields.- D.Derivation of the Full Conditionals of the Bayesian Hierarchical Space-Time Model for Significant Wave Height.- E.Sampling from a Multi-normal Distribution.
show more

"The core of this book is the development of a space-time model for significant wave heights. ... the models are carefully constructed and executed. They should serve as a useful guide to anyone who wishes to experiment with similar techniques and I recommend this book to researchers interested in exploring time series data by Bayesian methods." (George Z. Forristall, Journal of Ocean Engineering and Marine Energy, Vol. 1, 2015)
show more

"The core of this book is the development of a
space-time model for significant wave heights. ... the models are carefully
constructed and executed. They should serve as a useful guide to anyone who
wishes to experiment with similar techniques and I recommend this book to
researchers interested in exploring time series data by Bayesian methods." (George
Z. Forristall, Journal of Ocean Engineering and Marine Energy, Vol. 1, 2015)
show more