ASFB Home > 2003 > Biological Invasions: Consequences for Parasites, Pathogens, Emerging Diseases, and Fisheries in the Marine Environment.

Predictive modeling and spatial mapping of freshwater fish and decapod assemblages: an integrated GIS and neural network approach

Michael K. Joy & Russell G. Death

Institute of Natural Resources-Ecology, Massey University, Private Bag 11 222, Palmerston North, New Zealand
Email: m.k.joy@massey.ac.nz

We used stream fish and decapod spatial occurrence data extracted from a national database combined with recent surveys and geospatial data landuse, geomorphologic, climatic, and spatial data in a geographical information system (GIS) to model fish occurrence in the Wellington Region, New Zealand. To predict the occurrence of each species at a site from a common set of predictor variables we used a multi-response, artificial neural network (ANN), to produce a single model to predict the entire fish and decapod assemblage in one procedure. The predictions from the ANN using this landscape scale data proved very accurate. Four other evaluation metrics independent of species abundance or probability thresholds also confirmed the accuracy of the model. The important variables contributing to the predictions included the spatial and elevational position of the site reach, watershed area, the landuse and vegetation type proportions of the watershed, and watershed geology. The geospatial data available for the entire regional river network were then used to create a habitat-suitability map for all 18 species over the regional river network using GIS. This prediction map has many potential uses including; monitoring and predicting temporal changes in fish communities caused by human activities and shifts in climate, identifying of areas in need of protection, biodiversity hotspots, and areas for the reintroduction of endangered or rare species.

Room 1 Friday 10.50 am