Spatio-Temporal Models for Environmental Pollution MonitoringProjektleiter: Prof. Manfred Deistler
Dieses Projekt wird gefördert vom FWF unter der Projektnummer P12508.
The objective of this project is to build a model for environmental data with dynamic and spatial structure. The particular example under consideration is ozone formation and - transport. An emphasis is put on problemoriented modeling. The aim is to find a suitable model class and appropriate identification procedures in an iterative process using both a priori information (meteorological and physical knowledge) and data from the Austrian ozone monitoring network.
Efforts to build and statistically analyze models which simultaneously show temporal and spatial structure are relatively new (e.g. Pfeiffer&Deutsch, 1979; Stoffer, 1986; Haslett&Rafterty, 1989; Franke&Gründer, 1995; Huang&Cressie, 1996). Models of this kind seem to be appropriate for monitoring of different kinds of air pollutants. We have chosen to analyze the example of ozone, were in addition to the dynamic features marked spatial features can be observed. In modeling the spatio-temporal features of ozone concentrations, the understanding of the dynamics of ozone formation, ozone catabolism and ozone transport is essential. In addition the dependence on meteorological input data (e.g. temperature, wind direction, wind speed), the topography and other air pollutant concentrations (e.g. NOx) has to be taken into account.
The objectives of modeling ozone are as follows: prediction of ozone concentrations, spatial interpolation (estimation of ozone concentrations at non observed locations), monitoring of ozone concentrations and to obtain hints concerning the spatial allocation (redesign) of monitoring stations (if sufficient time is left).
In our opinion, the intended modeling task will also lead to methodological innovations and will be of exemplary importance for the modeling of other air pollution data. As has been pointed out by Patil (1994), the extension of the statistical concepts underlying spatial statistics and time series analysis is a major goal for ecological research and environmental management.