Abstract:
OpenMI is a widely used standard allowing exchange of data between integrated
models, which has mostly been applied to dynamic, deterministic models. Within
the FP7 UncertWeb project we are developing mechanisms and tools to support the management
of uncertainty in environmental models. In this paper we explore the integration
of the UncertWeb framework with OpenMI, to assess the issues that arise when propagating
uncertainty in OpenMI model compositions, and the degree of integration possible
with UncertWeb tools. In particular we develop an uncertainty-enabled model for a simple
Lotka-Volterra system with an interface conforming to the OpenMI standard, exploring
uncertainty in the initial predator and prey levels, and the parameters of the model
equations. We use the Elicitator tool developed within UncertWeb to identify the initial
condition uncertainties, and show how these can be integrated, using UncertML, with
simple Monte Carlo propagation mechanisms. The mediators we develop for OpenMI
models are generic and produce standard Web services that expose the OpenMI models
to a Web based framework. We discuss what further work is needed to allow a more
complete system to be developed and show how this might be used practically.
