Self-Organising Maps for the Classification and Diagnosis of River Quality from Biological and Environmental Data
The paper addresses the problem of how to classify and diagnose the state of health of a river from the composition of its biological community. It is claimed that experts use two complex mental processes when interpreting such data, knowledge-based reasoning and pattern recognition. It is argued that existing classification methods are inadequate and that the application of advanced computer-based techniques is vital to the realisation of the full potential of biological monitoring. The paper then concentrates on a pattern recognition approach and demonstrates how Self Organising Maps (SOM), a type of unsupervised-learning neural network, can be used to classify and diagnose river quality. A brief introduction is given to the theory of SOMs and the interpretation of their output, as expressed in feature maps and class templates. SOMs are developed using two different methods of accounting for the confounding effects of environmental factors, and their relative performances are compared. Some improvements to the SOM architecture and functionality that are currently being implemented are briefly described, together with plans to use information theory for the assessment of performance. Finally, it is concluded that the methods of classification/diagnosis described in the paper have considerable potential not only in river quality monitoring, but also in other environmental fields.
Key wordsNeural networks pattern recognition self-organising maps river quality biomonitoring RIVPACS pollution classification diagnosis.
- Bishop C. M. (1995) Neural Networks for Pattern Recognition. Oxford University Press. Cover T. M. and Thomas J. A. (1991) Elements of Information Theory. Wiley.Google Scholar
- DePauw N. and Hawkes H. A. (1993) Biological monitoring of river water quality. In River Water Quality Monitoring and Control, eds. Walley W. J. and Judd S. Aston University, Birmingham. 87–111. ISBN 1–85449–115–6.Google Scholar
- Haykin S. (1994) Neural Networks: A Comprehensive Foundation. Macmillan. Kohonen T. (1997) Self-Organising Maps. Second Edition. Springer-Verlag.Google Scholar
- Walley W. J. and Fontama V. N. (2000) New approaches to the biological classification of river quality based upon artificial intelligence. In: Assessing the biological quality of fresh waters. RIVPACS and other techniques. Eds. Wright J. F., Sutcliffe D. W. and Furse M. T. Freshwater Biological Association, Ambleside. 263–279.Google Scholar
- Walley W. J., Fontama V. N. and Martin R. W. (1998) Applications of Artificial Intelligence for the Biological Surveillance of River Quality. RandD Technical Report E52, Environment Agency, Bristol.Google Scholar
- Walley W. J. (1994) New approaches to the interpretation and classification of water quality data based on techniques from the field of artificial intelligence. In Proceedings of Monitoring Tailor-made, eds. Adriaanse M., Kraats J., Stoks P. G. and Ward R. C., RIZA, The Netherlands. 195–210.Google Scholar
- Walley W. J. (1993) Artificial Intelligence in River Water Quality Monitoring and Control. In Proceedings of the Freshwater Europe Symposium on River Water Quality Monitoring and Control, eds. Walley W. J. and Judd S. Aston University. February 1993. ISBN 185449–115–6.Google Scholar