Discrimination of water quality monitoring sites in River Vouga using a mixed-effect state space model

Costa, Marco; Monteiro, Magda

doi:10.1007/s00477-015-1137-y

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These values indicate a greater variability of the DO in this site compared to the others. One possible reason is the activity of the poultry and lagomorph slaughterhouses; the lowest DO concentration mean level may be associated with pollutant discharge into the waterways [13]. However, the analysis of these sample statistics must be prudent, since data have a time correlation and, possibly, they are a non-stationary times series.…”

Section: Vouga River Description and Datamentioning

confidence: 99%

“…In the period up to May 2013, the percentage of missing values ranged from 16% up to 20%, while, in the remaining period up to May 2015, these percentages are larger. The missing values in the modeling period were filled as specified in [13], who used the same data for other goals. …”

Section: Vouga River Description and Datamentioning

confidence: 99%

“…In [1], the case study of the hydrological basin of the river Vouga, in Portugal was presented. A discrimination analysis of water monitoring sites, using the monthly dissolved oxygen concentration, was proposed by [13], performing the extraction of both trend and seasonal components in a linear mixed-effect state-space model. Linear state-space models were applied by [14] as an improvement of the linear regression model, since these models allow the incorporation of a constructed hydro-meteorological covariate.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Time Series Model Comparison for Monitoring and Forecasting Water Quality Variables

Monteiro

Costa

2018

Hydrology

Self Cite

View full text Add to dashboard Cite

Abstract:The monitoring and prediction of water quality parameters are important tasks in the management of water resources. In this work, the performances of time series statistical models were evaluated to predict and forecast the dissolved oxygen (DO) concentration in several monitoring sites located along the main river Vouga, in Portugal, during the period from January 2002 to May 2015. The models being compared are a regression model with correlated errors and a state-space model, which can be seen as a calibration model. Both models allow the incorporation of water quality variables, such as time correlation or seasonality. Results show that, for the DO variable, the calibration model outperforms the regression model for sample modeling, that is, for a short-term forecast, while the regression model with correlated errors has a better performance for the forecasting h-steps ahead framework. So, the calibration model is more useful for water monitoring using an online or real-time procedure, while the regression model with correlated errors can be applied in order to forecast over a longer period of time.

show abstract

Section: Vouga River Description and Datamentioning

confidence: 99%

Section: Vouga River Description and Datamentioning

confidence: 99%