IBM

Data mining techniques for analysing complex simulation models

Individual-based models of plant populations and communities can be highly complex, reflecting the underlying dynamics of the natural systems under study. Analysing and understanding model behaviour can be extremely challenging. To address this we are collaborating with researchers from the Department of Knowledge Technologies of the Jožef Stefan Institute, Slovenia on the application of data mining and machine learning techniques to the analysis of the IBMs we have developed.

Model analysis

Machine learning methods are being used to analyse the relationship between simulation outputs with IBM inputs (model parameters) in order to gain insight into the behaviour of the model system. Here we rely on a Monte Carlo approach in which simulations are based on IBM parameter values sampled at random from across a predefined parameter space. By applying machine learning methods, we can generalise over the specific simulations made and derive more general rules concerning the behaviour of the system.

Plant population and community modelling

The objective of plant population and community modelling in the Agroecology group is to understand, and where necessary anticipate, the effects on arable vegetation of technical innovations and global change, and thereby to understand the role of the vegetation in the sustainability of the arable system as a whole.  System-level responses, such as primary production, nutrient retention and biodiversity, emerge over time, often unpredictably, from complex ecological and evolutionary processes. By developing models of plant populations and communities, we are able to assess the response of arable vegetation in a way that can't be addressed by experiment or observation alone.

Our current focus is the influence of the genetic and functional characteristics (life-history traits or their physiological determinants) of plants on system-level properties. A common thread is the definition of populations and communities in terms of the genetic and functional variation of individuals. Using the individual enables intra- and inter-specific variation to be presented on a common scale and both ecological and evolutionary processes to be combined in a single model framework.

Syndicate content