Predicting Aquatic Ecosystem Quality using Artificial Neural Networks: Impact of Environmental characteristics on the Structure of Aquatic Communities (Algae, Benthic and Fish Fauna) (EVK1-CT1999- 00026)

Project: Research

Project Details

Description

The goal of the PAEQANN project was to develop general methodologies, based on advanced modelling techniques, for predicting structure and diversity of key aquatic communities (diatoms, micro-invertebrates and fish), under natural (i.e. undisturbed by human activities) and under man-made disturbance (i.e. submitted to various pollutions, discharge regulation, ...). Such an approach to the analysis of aquatic communities will make it possible to:
i)set up robust and sensitive ecosystem evaluation procedures that will work across a large range of running water ecosystems throughout European countries;
ii)predict biocenosis structure in disturbed ecosystems, taking into account all relevant ecological variables;
iii)test for ecosystem sensitivity to disturbance;
iv)explore specific actions to be taken for restoration of ecosystem integrity.
Our investigations will therefore help to define strategies for conservation and restoration, compatible with local and regional development, and supported by a strong scientific background. Among the available modelling techniques, artificial neural networks are particularly appropriate for establishing relationships among variables in the natural processes that shape ecosystems, as these relationship are frequently non-linear.
LFE (Laboratory of Freshwater Ecology, URBO, FUNDP) is in charge of coordinating the work on benthic diatom communities and was organising the first PAEQANN workshop (http://www.sciences.fundp.ac.be/ paeqann).
AcronymPAEQANN
StatusFinished
Effective start/end date1/03/0028/02/03

Keywords

  • Modelling
  • Ecology
  • Community structure
  • Health of water ecosystem
  • Management

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.