XVI
Contents
8.3.2 Elman Network .................................................................................... 151
8.3.3 Fully Connected Recurrent Network ................................................... 154
8.3.4 Impact ofEnvironmental Factors Trained with the Recurrent
Network .............................................................................................. 158
8.4 Patteming Organizational Aspects of Community ................................ 161
8.4.1 Relationships among Hierarchical Levels in Communities ................. 161
8.4.2 Patteming of Exergy ............................................................................ 167
8.5 Summary and Conclusions .................................................................... 173
Acknowledgements ............................................................................. 174
References ........................................................................................... 174
9. Elucidation of Hypothetical Relationships between Habitat
Conditions and
Macroinvertebrate Assemblages in
Freshwater Streams by Artificial Neural Networks ............... 179
9.1 Introduction ......................................................................................... 179
9.2 Study Site ............................................................................................ 180
9.3 Materials and Methods ........................................................................ 180
9.3.1
Data ...................................................................................... 180
9.3.2
Neural Network Modelling ................................................... 181
9.3.3
Sensitivity Analysis .............................................................. 182
9.4 Results and Discussion ....................................................................... 183
9.4.1
Elucidation ofHypothetical Relationships ........................... 183
9.4.2
Discovery of Contradictory Relationships ............................ 187
9.4.3
Limitations of the Method .................................................... 188
9.5 Conclusions ......................................................................................... 189
References ........................................................................................... 190
Part 111 Prediction and Elucidation of River Ecosystems
193
10. Prediction and Elucidation of Population Dynamics of the
Blue-green Aigae Microcystis aeruginosa and the Diatom
Stephanodiscus hantzschii in the Nakdong
RiverReservoir System (South Korea) by a Recurrent Artificial
Neural Network ........................................................................ 195
10.1 Introduction ....................................................................................... 195
10.2 Description of the Study Site ............................................................ 196
10.3 Materials and Methods ...................................................................... 197
10.3.1 Data Collection and Analysis ............................................... 197
10.3.2 Modelling the Phytoplankton Dynamics .............................. 199
10.3.3 Neural Network Validation and Knowledge Discovery on
Algal Succession .................................................................. 201
10.4 Results and Discussion ...................................................................... 201
10.4.1 Limnological Aspects and Plankton Dynamics in the Lower Nakdong