An advanced hidden Markov model for hourly rainfall time series

Stoner, O. and Economou, T. (2020) An advanced hidden Markov model for hourly rainfall time series. Computational Statistics and Data Analysis, 152, 107045. (doi: 10.1016/j.csda.2020.107045)

Abstract

The hidden Markov framework is adapted to construct a compelling model for simulation of sub-daily rainfall, capable of capturing important characteristics of sub-daily rainfall well, including: long dry periods or droughts; seasonal and temporal variation in occurrence and intensity; and propensity for extreme values. These adaptations include both clone states and temporally non-homogeneous state persistence probabilities. Set in the Bayesian framework, a rich quantification of parametric and predictive uncertainty is available, and thorough model checking is made possible through posterior predictive analyses. Results from the model are highly interpretable, allowing for meaningful examination of diurnal, seasonal and annual variation in sub-daily rainfall occurrence and intensity. To demonstrate the effectiveness of this approach, both in terms of model fit and interpretability, the model is applied to an 8-year long time series of hourly observations.

• Item Type: Articles
• Additional Information: This work was funded in part by a Natural Environment Research Council GW4+ Doctoral Training Partnership studentship, United Kingdom [NE/L002434/1].
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Stoner, Dr Oliver
• Authors: Stoner, O., and Economou, T.
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• Journal Name: Computational Statistics and Data Analysis
• Publisher: Elsevier
• ISSN: 0167-9473
• ISSN (Online): 1872-7352
• Published Online: 11 July 2020
• Copyright Holders: Copyright © 2020 The Authors
• First Published: First published in Computational Statistics and Data Analysis 152: 107045
• Publisher Policy: Reproduced under a Creative Commons License