Bayesian Analysis of a Water Quality Turbidity High Frequency Time Series Through Markov Switching Autoregressive Models

Roberta Paroli, L. SPEZIA, M. STUTTER, A VINTEN

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order to provide simulation inputs for investigations on diffuse water pollution and support rural land management policy on soil and water management, a turbidity time series recorded in a Scottish stream for more than a year, along with two covariates, is considered. Turbidity time series have complex dynamics because they are non-linear, non-Normal, non-stationary, with a long memory, and present missing values. Given these issues the turbidity process is analysed by Markov switching autoregressive models under the Bayesian paradigm using novel evolutionary Monte Carlo algorithms. Hence, it is possible to efficiently fit the actual data, reconstruct the sequence of hidden states, restore the missing values, and classify the observations into a few regimes, providing new insight on turbidity dynamics.
Original languageEnglish
Title of host publicationCLADAG 2021 BOOK OF ABSTRACTS AND SHORT PAPERS
Pages400-403
Number of pages4
DOIs
Publication statusPublished - 2021
Event13th Scientific Meeting of the Classification and Data Analysis Group - Firenze
Duration: 9 Sep 202111 Sep 2021

Conference

Conference13th Scientific Meeting of the Classification and Data Analysis Group
CityFirenze
Period9/9/2111/9/21

Keywords

  • non-homogeneous hidden Markov chain
  • water quality
  • population Markov chain MonteCarlo
  • path sampling

Fingerprint

Dive into the research topics of 'Bayesian Analysis of a Water Quality Turbidity High Frequency Time Series Through Markov Switching Autoregressive Models'. Together they form a unique fingerprint.

Cite this