Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks

The assessment of properties and processes of running waters is a major iss ue in aquatic environmental management. Because system analysis and predict ion with deterministic and stochastic models is often limited by the comple xity and dynamic nature of these ecosystems, supplementary or alternative m ethods have to be developed. We tested the suitability of various types of artificial neural networks for system analysis and impact assessment in dif ferent fields: (1) temporal dynamics of water quality based on weather, urb an storm-water run-off and waste-water effluents; (2) bioindication of chem ical and hydromorphological properties using benthic macroinvertebrates; an d (3) long-term population dynamics of aquatic insects. Specific pre-proces sing methods and neural models were developed to assess relations among com plex variables with high levels of significance. For example, the diurnal v ariation of oxygen concentration (modelled from precipitation and oxygen of the preceding day; R-2 = 0.79), population dynamics of emerging aquatic in sects (modelled from discharge, water temperature and abundance of the pare ntal generation; R-2 = 0.93), and water quality and habitat characteristics as indicated by selected sensitive benthic organisms (e.g. R-2 = 0.83 for pH and R-2 = 0.82 for diversity of substrate, using five out of 248 species ). Our results demonstrate that neural networks and modelling techniques ca n conveniently be applied to the above mentioned fields because of their sp ecific features compared with classical methods. Particularly, they can be used to reduce the complexity of data sets by identifying important (functi onal) inter-relationships and key variables. Thus, complex systems can be r easonably simplified in clear models with low measuring and computing effor t. This allows new insights about functional relationships of ecosystems wi th the potential to improve the assessment of complex impact factors and ec ological predictions. (C) 1999 Elsevier Science B.V. All rights reserved.