Spatio-temporal statistical models for river monitoring networks

• Published in: Water science and technology Vol. 53; no. 1; pp. 9 - 15
• Main Authors: Clement, L, Thas, O, Vanrolleghem, P A, Ottoy, J P
• Format: Journal Article
• Language: English
• Published: England IWA Publishing 2006
• Subjects: Autoregressive models; Autoregressive processes; Data Collection; Dissolved oxygen; Environmental monitoring; Environmental Monitoring - statistics & numerical data; Forecasting; Freshwater; Graphical representations; Mathematical models; Models, Theoretical; Oxygen - analysis; Policies; Quality Control; River water; Rivers; State space models; State variable; Statistical analysis; Statistical models; Waste Disposal, Fluid; Wastewater; Wastewater treatment; Wastewater treatment plants; Water - chemistry; Water quality; Water treatment plants
• ISBN: 1843395541; 9781843395546
• ISSN: 0273-1223; 1996-9732
• DOI: 10.2166/wst.2006.002

When introducing new wastewater treatment plants (WWTP), investors and policy makers often want to know if there indeed is a beneficial effect of the installation of a WWTP on the river water quality. Such an effect can be established in time as well as in space. Since both temporal and spatial components affect the output of a monitoring network, their dependence structure has to be modelled. River water quality data typically come from a river monitoring network for which the spatial dependence structure is unidirectional. Thus the traditional spatio-temporal models are not appropriate, as they cannot take advantage of this directional information. In this paper, a state-space model is presented in which the spatial dependence of the state variable is represented by a directed acyclic graph, and the temporal dependence by a first-order autoregressive process. The state-space model is extended with a linear model for the mean to estimate the effect of the activation of a WWTP on the dissolved oxygen concentration downstream.