 |
 |
The first meeting of Environmental Stats Study group for the new session will be held on Thursday 21st October at Errol St, London. The meeting commences at 2pm and there are two speakers Howard Grubb, University of Reading Uncertainty in Geophysical and meteorological modelling. Abstract Geophysics and Meteorology make use of complex models of physical systems to estimate observables and to predict future behaviour of the systems. A large amount of data and knowledge goes into specifing and estimating these models. However, there remain many uncertainties, particularly due to the increased complexity of fine-scale representations. The sources of uncertainty and their likely effect on the required estimates or predictions will be reviewed and illustrated with specific cases from geophysics. and Tony O'Hagan, University of Sheffield "Reducing Uncertainty in Mechanistic Models". Abstract There are several sources of uncertainty that need to be recognised in the use of mechanistic computer models of environmental processes. The talk will begin by reviewing these, but will focus on two particular sources of uncertainty. Often, there are model inputs whose values are not known exactly, but we can learn about these if there are observations of the process itself. We present a Bayesian method for calibrating models in this way that allows for remaining uncertainty in the fitted inputs. A more complex source of error is deficiencies in the model itself. We show how the residual errors after calibration can be used to estimate and reduce model inadequacy. All welcome ====================================================== Dr. Marian Scott [log in to unmask] Department of Statistics www.stats.gla.ac.uk/~marian University of Glasgow Phone: +44(0) 141 330 5125 Glasgow G12 8QW Fax: +44(0) 141 330 4814 ====================================================== %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%