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.
The Flanders Environment Agency (VMM) has been performing biological water quality assessments on inland waters in Flanders (Belgium) since 1989 and sediment quality assessments since 2000. The water ...quality monitoring network is a combined physico-chemical and biological network, the biological component focusing on macro-invertebrates. The sediment monitoring programme produces biological data to assess the sediment quality. Both monitoring programmes aim to provide index values, applying a similar conceptual methodology based on the presence of macro-invertebrates. The biological data obtained from both monitoring networks are consolidated in the VMM macro-invertebrates database and include identifications at family and genus level of the freshwater phyla Coelenterata, Platyhelminthes, Annelida, Mollusca, and Arthropoda. This paper discusses the content of this database, and the dataset published thereof: 282,309 records of 210 observed taxa from 4,140 monitoring sites located on 657 different water bodies, collected during 22,663 events. This paper provides some background information on the methodology, temporal and spatial coverage, and taxonomy, and describes the content of the dataset. The data are distributed as open data under the Creative Commons CC-BY license.
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.
The European Water Framework Directive requires that member states assess all their surface waters based on a number of biological elements, including macroinvertebrates. Since 1989, the Flemish ...Environment Agency has been using the Belgian Biotic Index for assessing river water quality based on macroinvertebrates. Throughout the years, the Belgian Biotic Index has proven to be a reliable and robust method providing a good indication of general degradation of river water and habitat quality. Since the Belgian Biotic Index does not meet all the requirements of the Water Framework Directive, a new index, the Multimetric Macroinvertebrate Index Flanders (MMIF) for evaluating rivers and lakes was developed and tested. This index was developed in order to provide a general assessment of ecological deterioration caused by any kind of stressor, such as water pollution and habitat quality degradation. The MMIF is based on macroinvertebrate samples that are taken using the same sampling and identification procedure as the Belgian Biotic Index. The index calculation is a type-specific multimetric system based on five equally weighted metrics, which are taxa richness, number of Ephemeroptera, Plecoptera and Trichoptera taxa, number of other sensitive taxa, the Shannon–Wiener diversity index and the mean tolerance score. The final index value is expressed as an Ecological Quality Ratio ranging from zero for very bad ecological quality to one for very good ecological quality. The MMIF correlates positively with dissolved oxygen and negatively with Kjeldahl nitrogen, total nitrogen, ammonium, nitrite, total phosphorous, orthophosphate and biochemical and chemical oxygen demand. This new index is now being used by the Flemish Environment Agency as a standard method to report about the status of macroinvertebrates in rivers and lakes in Flanders within the context of the European Water Framework Directive.
Legislation in Europe has been adopted to determine and improve the ecological integrity of inland and coastal waters. Assessment is based on four biotic groups, including benthic macroinvertebrate ...communities. For lakes, benthic invertebrates have been recognized as one of the most difficult organism groups to use in ecological assessment, and hitherto their use in ecological assessment has been limited. In this study, we review and intercalibrate 13 benthic invertebrate-based tools across Europe. These assessment tools address different human impacts: acidification (3 methods), eutrophication (3 methods), morphological alterations (2 methods), and a combination of the last two (5 methods). For intercalibration, the methods were grouped into four intercalibration groups, according to the habitat sampled and putative pressure. Boundaries of the ‘good ecological status’ were compared and harmonized using direct or indirect comparison approaches. To enable indirect comparison of the methods, three common pressure indices and two common biological multimetric indices were developed for larger geographical areas. Additionally, we identified the best-performing methods based on their responsiveness to different human impacts. Based on these experiences, we provide practical recommendations for the development and harmonization of benthic invertebrate assessment methods in lakes and similar habitats.
Display omitted
•Ecological status of European surface waters is assessed using biological communities.•We reviewed and intercalibrated 13 lake benthic invertebrate-based tools across Europe.•These tools address acidification, eutrophication and morphological alterations.•Two biological multimetric indices were developed for two large regions of Europe.•We provide recommendations for the use of benthic invertebrates in lake assessment.
The Flanders Environment Agency (
VMM
) has been performing biological water quality assessments on inland waters in Flanders (Belgium) since 1989 and sediment quality assessments since 2000. The ...water quality monitoring network is a combined physico-chemical and biological network, the biological component focusing on macro-invertebrates. The sediment monitoring programme produces biological data to assess the sediment quality. Both monitoring programmes aim to provide index values, applying a similar conceptual methodology based on the presence of macro-invertebrates. The biological data obtained from both monitoring networks are consolidated in the
VMM
macro-invertebrates database and include identifications at family and genus level of the freshwater phyla
Coelenterata
,
Platyhelminthes
,
Annelida
,
Mollusca
, and
Arthropoda
. This paper discusses the content of this database, and the dataset published thereof: 282,309 records of 210 observed taxa from 4,140 monitoring sites located on 657 different water bodies, collected during 22,663 events. This paper provides some background information on the methodology, temporal and spatial coverage, and taxonomy, and describes the content of the dataset. The data are distributed as open data under the Creative Commons CC-BY license.
In this study we developed and applied a multimetric index to assess the biological water quality of rivers in Vietnam as a complementary tool to the traditional physical–chemical analysis. ...Macroinvertebrate samples were collected at 15 monitoring sites in the Cau river basin, Northern of Vietnam. Eighteen candidate metrics were tested for their range, stability, sensitivity and responsiveness to anthropogenic impacts. The MMI was calculated as the arithmetic mean of five metrics that were retained being the Biological Monitoring Working Party (BMWP) – Viet, total number of taxa, Margalef index, number of ephemeroptera, plecoptera and trichoptera (EPT) and percent of insects. The MMI is split up in five water quality classes, ranging from class one (high biological status) to class five (bad biological status). The study demonstrated that the multimetric approach is suitable for application in the Vietnamese national monitoring and assessment program.
To meet the requirements of the EU Water Framework Directive, models are useful to predict communities in watercourses based on the abiotic characteristics of their aquatic environment. For that ...purpose back-propagation Artificial Neural Network (ANN) algorithms were used to induce predictive models on a dataset of the Zwalm river basin (Flanders, Belgium). This dataset consisted of 120 samples, collected over a 2-year period. Fifteen environmental variables were measured at each site, as well as the abundance of the aquatic macroinvertebrate taxa. Different neural networks were developed and optimized to obtain the best model configuration for the prediction of the habitat suitability of macroinvertebrate taxa. The best performing number of hidden layers and neurons and training algorithms have been searched for. The different options were theoretically and practically validated and assessed. The theoretical validation was based on cross-validation. For the practical validation, potential applications of the neural network models were analyzed, and the predictive performance of the models was assessed using ecological expert knowledge. The results indicate that the number of times a taxon was found in the whole river basin influences the performance measures and the architecture of the network. Based on the Cohen’s kappa, it could be concluded that ANN models predicting the presence/absence of very rare taxa (e.g.
Aplexa) or very common taxa (e.g. Tubificidae) were rather irrelevant, although their correctly classified instances (CCI) was high. Predicting the presence/absence of Asellidae (a moderately present taxon), the highest performances (CCI and Cohen’s kappa) were found for the network model with two hidden layers each having 10 neurons. When calculation time was also taken into account, the network model with one hidden layer having 10 neurons could be preferred. Applying this network architecture, performances were only slightly worse, while calculation time was a lot shorter. One may also conclude that not all network models resulted in a relevant relation between a variable and a specific taxon. For Gammaridae for example, a rather small ANN structure gave a better idea of the impact of dissolved oxygen on its presence than a larger one. More reliable predictions and ecological interpretations for river ecosystem management would thus be possible provided the best configuration could be found.