Modelling Community Structure in Freshwater Ecosystems (eBook)

Foreword 5
Contents 11
General introduction 13
1 Using bioindicators to assess rivers in Europe: An overview 18
1.1 Introduction 18
1.2 Stream typology 18
1.3 Diatom ecology and use for river quality assessment 20
1.4 Typologies, assessment systems and prediction techniques based on macroinvertebrates 23
1.5 Advantages of using fish as an indicator taxon 27
1.6 Conclusions 29
2 Review of modelling techniques 31
2.1 Introduction 31
2.2 Conventional statistical models 31
2.3 Artificial neural networks (ANNs) 36
2.4 Bayesian and Mixture models 45
2.5 Support vector machines (SVMs) 47
2.6 Genetic algorithms (GAs) 48
2.7 Mutual information and regression maximisation (MIR-max) 49
2.8 Structural dynamic models 49
3 Fish community assemblages 51
3.1 Introduction 51
3.2 Patterning riverine fish assemblages using an unsupervised neural network 53
3.3 Predicting fish assemblages in France and evaluating the influence of their environmental variables 64
3.4 Fish diversity conservation and river restoration in southwest France: a review 74
3.5 Modelling of freshwater fish and macro-crustacean assemblages for biological assessment in New Zealand 86
3.6 A Comparison of various fitting techniques for predicting fish yield in Ubolratana reservoir ( Thailand) from a time series data 100
3.7 Patterning spatial variations in fish assemblage structures and diversity in the Pilica River system 110
3.8 Optimisation of artificial neural networks for predicting fish assemblages in rivers 124
4 Macroinvertebrate community assemblages 140
4.1 Introduction 140
4.2 Sensitivity and robustness of a stream model based on artificial neural networks for the simulation of different management scenarios 142
4.3 A neural network approach to the prediction of benthic macroinvertebrate fauna composition in rivers 156
4.4 Predicting Dutch macroinvertebrate species richness and functional feeding groups using five modelling techniques 167
4.5 Comparison of clustering and ordination methods implemented to the full and partial data of benthic macroinvertebrate communities in streams and channels 176
4.6 Prediction of macroinvertebrate diversity of freshwater bodies by adaptive learning algorithms 198
4.7 Hierarchical patterning of benthic macroinvertebrate communities using unsupervised artificial neural networks 215
4.8 Species spatial distribution and richness of stream insects in south- western France using artificial neural networks with potential use for biosurveillance 230
4.9 Patterning community changes in benthic macroinvertebrates in a polluted stream by using artificial neural networks 248
4.10 Patterning, predicting stream macroinvertebrate assemblages in Victoria ( Australia) using artificial neural networks and genetic algorithms 261
5 Diatom and other algal assemblages 270
5.1 Introduction 270
5.2 Applying case-based reasoning to explore freshwater phytoplankton dynamics 272
5.3 Modelling community changes of cyanobacteria in a flow regulated river ( the lower Nakdong River, S. Korea) by means of a Self- Organizing Map ( SOM) 282
5.4 Use of artificial intelligence (MIR-max) and chemical index to define type diatom assemblages in Rhône basin and Mediterranean region 297
5.5 Classification of stream diatom communities using a self- organizing map 313
5.6 Diatom typology of low-impacted conditions at a multi- regional scale: combined results of multivariate analyses and SOM 326
5.7 Prediction with artificial neural networks of diatom assemblages in headwater streams of Luxembourg 352
5.8 Use of neural network models to predict diatom assemblages in the Loire- Bretagne basin ( France) 364
6 Development of community assessment techniques 375
6.1 Introduction 375
6.2 Evaluation of relevant species in communities: development of structuring indices for the classification of communities using a self- organizing map 377
6.3 Projection pursuit with robust indices for the analysis of ecological data 389
6.4 A framework for computer-based data analysis and visualisation by pattern recognition 398
6.5 A rule-based vs. a set-covering implementation of the knowledge system LIMPACT and its significance for maintenance and discovery of ecological knowledge 409
6.6 Predicting macro-fauna community types from environmental variables by means of support vector machines 419
7 User interface tool 443
7.1 Introduction 443
7.2 Software aims 444
7.3 System requirements 444
7.4 Installing/Uninstalling 444
7.5 Models implemented in the tool 444
7.6 How to use the software 447
7.7 Organisms used in the PAEQANN software 455
8 General conclusions and perspectives 459
References 463
Subject index 521