Wim Gabriels

Applications of artificial neural networks predicting macroinvertebrates in freshwaters

To facilitate decision support in freshwater ecosystem protection and restoration management, habitat suitability models can be very valuable. Data driven methods such as artificial neural networks (ANNs) are particularly useful in this context, seen their time-efficient development and relatively high reliability. However, specialized and technical literature on neural network modelling offers a variety of model development criteria to select model architecture, training procedure, etc. This may lead to confusion among ecosystem modellers and managers regarding the optimal training and validation methodology. This paper focuses on the analysis of ANN development and application for predicting macroinvertebrate communities, a species group commonly used in freshwater assessment worldwide. This review reflects on the different aspects regarding model development and application based on a selection of 26 papers reporting the use of ANN models for the prediction of macroinvertebrates. This analysis revealed that the applied model training and validation methodologies can often be improved and moreover crucial steps in the modelling process are often poorly documented. Therefore, suggestions to improve model development, assessment and application in ecological river management are presented. In particular, data pre-processing determines to a high extent the reliability of the induced models and their predictive relevance. This also counts for the validation criteria, that need to be better tuned to the practical simulation requirements. Moreover, the use of sensitivity methods can help to extract knowledge on the habitat preference of species and allow peer-review by ecological experts. The selection of relevant input variables remains a critical challenge as well. Model coupling is a missing crucial step to link human activities, hydrology, physical habitat conditions, water quality and ecosystem status. This last aspect is probably the most valuable aspect to enable decision support in water management based on ANN models.

Analysis of macrobenthic communities in Flanders, Belgium, using a stepwise input variable selection procedure with artificial neural networks

The effect of environmental conditions on river macrobenthic communities was studied using a dataset consisting of 343 sediment samples from unnavigable watercourses in Flanders, Belgium. Artificial neural network models were used to analyse the relation among river characteristics and macrobenthic communities. The dataset included presence or absence of macroinvertebrate taxa and 12 physicochemical and hydromorphological variables for each sampling site. The abiotic variables served as input for the artificial neural networks to predict the macrobenthic community. The effects of the input variables on model performance were assessed in order to identify the most diagnostic river characteristics for macrobenthic community composition. This was done by consecutively eliminating the least important variables and, when beneficial for model performance, adding previously removed ones again. This stepwise input variable selection procedure was tested not only on a model predicting the entire macrobenthic community, but also on three models, each predicting an individual taxon. Additionally, during each step of the stepwise leave-one-out procedure, a sensitivity analysis was performed to determine the response of the predicted macroinvertebrate taxa to the input variables applied. This research illustrated that a combination of input variable selection with sensitivity analyses can contribute to the development of reliable and ecologically relevant ANN models. The river characteristics predicting presence or absence of the benthic macroinvertebrates best were the Julian day, conductivity, and dissolved oxygen content. These conditions reflect the importance of discharges of untreated wastewater that occurred during the period of investigation in nearly all Flemish rivers.

Implications of taxonomic modifications and alien species on biological water quality assessment as exemplified by the Belgian Biotic Index method

In this paper, some important problems related to taxonomic resolution in water quality assessment by means of macroinvertebrates are discussed. Most quality indices based on macroinvertebrates only require identification up to genus or family level. Although this can be seen as a practical trade-off between taxonomic precision and time constraints and financial resources, it can result in biased assessment scores for certain stream types. An additional difficulty of identification levels other than species is caused by possible changes in taxonomy over time. A given genus may indeed have been split up into two or more genera or a species could be assigned to a different genus. These changes may alter biotic index values calculated over time, due to a change in number of taxa or replacement of one taxon by another one having a different tolerance class. An additional problem is caused by the invasion of exotic species. The genus Corbicula for instance is currently invading Belgian watercourses in increasing numbers. Since no Belgian Biotic Index (BBI) tolerance class is defined for Corbicula, this may cause inconsistencies in index calculations as well. In order to eliminate these, a semi-fixed taxa list, including a tolerance class for each taxon, for BBI calculation is proposed.

Development of a multimetric assessment system based on macroinvertebrates for rivers in Flanders (Belgium) according to the European Water Framework Directive

The European Water Framework Directive (WFD; EU 2000) requires member states to develop an assessment system for all types of rivers, lakes, transitional and coastal waters based on a number of biological elements, including macroinvertebrates. These assessment methods have to meet a number of requirements. Currently, the Flemish Environment Agency (VMM) uses the Belgian Biotic Index (BBI; DE PAUW & VANHOOREN 1983) for assessing river water quality by means of macroinvertebrates. Throughout the years, the BBI has proven to be a reliable method providing a good indication of general degradation o f river water and habitat quality. Nevertheless, the BBI does not meet all requirements of the WFD. The BBI has to be adapted to the requirements o f the WFD o r a new assessment method must be developed.

Prediction of macroinvertebrate communities in sediments of Flemish watercourses based on artificial neural networks

Artificial neural networks (ANNs) are mathematical models based on the transfer of information through a network of functional units, called neurons. Given a number of input values, entered at the basis of the network, one or more outputs are generated. Several algorithms exist for determining the inner parameters of the neural network, based on calibration data. ANNs are currently recognized as an alternative to multivariate statistics in predicting aquatic communities. Recently, several studies have been published concerning the application of neural networks in relating freshwater macroinvertebrates with their abiotic environment (e.g. WALLEY & FoNTAMA 1998, ScHLEITER et al. 1999, GABRIELS er al. 2000). The aim of this srudy was to test the potential of ANNs in predicting which taxa would occur in the sediment at a particular sampling point. For this purpose, a dataset of sediment samples from unnavigable watercourses, including abiotic variables and abundances of macroinvenebrates, was used.