Peter Goethals

Fuzzy rule-based models for decision support in ecosystem management

To facilitate decision support in the ecosystem management, ecological expertise and site-specific data need to be integrated. Fuzzy logic can deal with highly variable, linguistic, vague and uncertain data or knowledge and, therefore, has the ability to allow for a logical, reliable and transparent information stream from data collection down to data usage in decision-making. Several environmental applications already implicate the use of fuzzy logic. Most of these applications have been set up by trial and error and are mainly limited to the domain of environmental assessment. In this article, applications of fuzzy logic for decision support in ecosystem management are reviewed and assessed, with an emphasis on rule-based models. In particular, the identification, optimisation, validation, the interpretability and uncertainty aspects of fuzzy rule-based models for decision support in ecosystem management are discussed.

A review of Bayesian belief networks in ecosystem service modelling

A wide range of quantitative and qualitative modelling research on ecosystem services (ESS) has recently been conducted. The available models range between elementary, indicator-based models and complex process-based systems. A semi-quantitative modelling approach that has recently gained importance in ecological modelling is Bayesian belief networks (BBNs). Due to their high transparency, the possibility to combine empirical data with expert knowledge and their explicit treatment of uncertainties, BBNs can make a considerable contribution to the ESS modelling research. However, the number of applications of BBNs in ESS modelling is still limited. This review discusses a number of BBN-based ESS models developed in the last decade. A SWOT analysis highlights the advantages and disadvantages of BBNs in ESS modelling and pinpoints remaining challenges for future research. The existing BBN models are suited to describe, analyse, predict and value ESS. Nevertheless, some weaknesses have to be considered, including poor flexibility of frequently applied software packages, difficulties in eliciting expert knowledge and the inability to model feedback loops. BBNs are increasingly used to analyse, predict and value ecosystem services (ESS).Most BBN applications in ESS modelling target only a single service.Numerous advantages of BBNs in ESS modelling are demonstrated in current applications.Model drawbacks are absence of feedback loops and obligatory variable discretization.Spatially explicit modelling and modelling of ESS bundles are future opportunities.

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.

Knowledge-based versus data-driven fuzzy habitat suitability models for river management

Aquatic habitat suitability models have increasingly received attention due to their wide management applications. Ecological expert knowledge has been frequently incorporated in such models to link environmental conditions to the quantitative habitat suitability of aquatic species. Since the formalisation of problem-specific human expert knowledge is often difficult and tedious, data-driven machine learning techniques may be helpful to extract knowledge from ecological datasets. In this paper, both expert knowledge-based and data-driven fuzzy habitat suitability models were developed and the performance of these models was compared. For the data-driven models, a hill-climbing optimisation algorithm was applied to derive ecological knowledge from the available data. Based on the available ecological expert knowledge and on biological samples from the Zwalm river basin (Belgium), habitat suitability models were generated for the mayfly Baetis rhodani (Pictet 1843). Data-driven models appeared to outperform expert knowledge-based models substantially, while a step-forward model selection procedure indicated that physical habitat variables adequately described the mayfly habitat suitability in the studied area. This study has important implications on the application of expert knowledge in ecological studies, especially if this knowledge is extrapolated to other areas. The results suggest that data-driven models can complement expert knowledge-based approaches and hence improve model reliability.

Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinvertebrates

Abstract Predicting freshwater organisms based on machine learning is becoming more and more reliable due to the availability of appropriate datasets, advanced modelling techniques and the continuously increasing capacity of computers. A database consisting of measurements collected at 360 sampling sites in non-navigable watercourses in Flanders was applied to predict the absence/presence of benthic macroinvertebrate taxa by means of decision trees. The measured variables were a combination of physical–chemical (temperature, pH, dissolved oxygen concentration, conductivity, total organic carbon, Kjeldahl nitrogen and total phosphorus), structural (granulometric analysis of the sediment, width, depth and flow velocity of the river) and two ecotoxicological variables. The predictive power of decision trees was assessed on the basis of the number of Correctly Classified Instances (CCI). A genetic algorithm was introduced to compare the predictive power of different sets of input variables for the decision trees. The number of input variables was reduced from 15 to 2–8 variables without affecting the predictive power of the decision trees significantly. Furthermore, reducing the number of input variables allowed to ease the identification of general data trends.

Combining data-driven methods and lab studies to analyse the ecology of Dikerogammarus villosus

Abstract The spread of aquatic invasive species is a worldwide problem. In the aquatic environment, especially exotic Crustacea are affecting biodiversity. The amphipod Dikerogammarus villosus is such an exotic species in Flanders, which is rapidly spreading and probably has a serious impact on aquatic communities. The purpose of the present study was to make use of lab results, field data and modelling techniques to investigate the potential impact of this species on other macroinvertebrates. All types of prey that were used in predator–prey experiments ( Gammarus pulex , Gammarus tigrinus , Crangonyx pseudogracilis , Asellus aquaticus , Cloeon dipterum and Chironomus species) were consumed by D. villosus , especially species that were less mobile such as the Chironomus species. The presence of gravel somewhat reduced predation by providing shelter to the prey. Substrate preference experiments indicated that D. villosus preferred a stony substrate. Using decisions trees to construct habitat suitability models based on field observations, it could be concluded that D. villosus is mainly found in habitats with an artificial bank structure, a high oxygen saturation and a low conductivity, which corresponds with canals with a good chemical water quality. Moreover, a synecological classification tree, based on the abundance of the taxa present in the macroinvertebrate communities, indicated that the presence of D. villosus negatively affected the presence of the indigenous G. pulex . When the laboratory experiments and the field observations are combined, it can be concluded that D. villosus can seriously affect macroinvertebrate communities in Flanders.

Traits-based approaches in bioassessment and ecological risk assessment: Strengths, weaknesses, opportunities and threats

We discuss the application of traits-based bioassessment approaches in retrospective bioassessment as well as in prospective ecological risk assessments in regulatory frameworks. Both approaches address the interaction between species and stressors and their consequences at different levels of biological organization, but the fact that a specific species may be less abundant in a potentially impacted site compared with a reference site is, regrettably, insufficient to provide diagnostic information. Species traits may, however, overcome the problems associated with taxonomy-based bioassessment. Trait-based approaches could provide signals regarding what environmental factors may be responsible for the impairment and, thereby, provide causal insight into the interaction between species and stressors. For development of traits-based (TBA), traits should correspond to specific types of stressors or suites of stressors. In this paper, a strengths, weaknesses, opportunities, and threats (SWOT) analysis of TBA in both applications was used to identify challenges and potentials. This paper is part of a series describing the output of the TERA (Traits-based ecological risk assessment: Realising the potential of ecoinformatics approaches in ecotoxicology) Workshop held between 7 and 11 September, 2009, in Burlington, Ontario, Canada. The recognized strengths were that traits are transferrable across geographies, add mechanistic and diagnostic knowledge, require no new sampling methodology, have an old tradition, and can supplement taxonomic analysis. Weaknesses include autocorrelation, redundancy, and inability to protect biodiversity directly. Automated image analysis, combined with genetic and biotechnology tools and improved data analysis to solve autocorrelation problems were identified as opportunities, whereas low availability of trait data, their transferability, their quantitative interpretation, the risk of developing nonrelevant traits, low quality of historic databases, and their standardization were listed as threats.

APPLICATION OF CLASSIFICATION TREES AND SUPPORT VECTOR MACHINES TO MODEL THE PRESENCE OF MACROINVERTEBRATES IN RIVERS IN VIETNAM

Abstract In the present study, classification trees (CTs) and support vector machines (SVMs) were used to study habitat suitability for 30 macroinvertebrate taxa in the Du river in Northern Vietnam. The presence/absence of the 30 most common macroinvertebrate taxa was modelled based on 21 physical-chemical and structural variables. The predictive performance of the CT and SVM models was assessed based on the percentage of Correctly Classified Instances (CCI) and Cohens kappa statistics. The results of the present study demonstrated that SVMs performed better than CTs. Attribute weighing in SVMs could replace the application of genetic algorithms for input variable selection. By weighing attributes, SVMs provided quantitative correlations between environmental variables and the occurrence of macroinvertebrates and thus allowed better ecological interpretation. SVMs thus proved to have a high potential when applied for decision-making in the context of river restoration and conservation management.

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.

Comparison of modelling techniques to predict macroinvertebrate community composition in rivers of Ethiopia

Abstract In order to fulfil the millennium development goals and to ensure environmental sustainability in Ethiopia, ecological indicator systems can support river managers to analyse the status of watercourses and to select critical restoration actions. In order to use macroinvertebrates as river water quality monitoring and assessment tools, Ethiopia needs data from reference as well as disturbed conditions of surface water ecosystems. Macroinvertebrates, structural and physical–chemical data were in this context collected in the Gilgel Gibe river basin in South-Western Ethiopia during the period 2005–2008. In the next stage, ecological metrics were compared for their assessment relevance. In the present paper, classification trees and support vector machines were used to induce models describing the relation between the river characteristics and the ecological conditions of these streams. Greedy stepwise and genetic search algorithms improved the performance and easy interpretation of these models by making a selection of the variables that were used as input of these models. The developed models allowed to identify the major variables affecting river quality. These tools can support river managers in their decision-making regarding the status of rivers and potential restoration options, for example by providing rules concerning critical values of major river characteristics at which certain actions should be undertaken.