|
Key words: Macrophytes, Artificial Neural Networks, Modelling, Forecasting
Between 1991 and 1998 several macrophyte surveys were made of the Rivers Test and Itchen, Hampshire, UK. Alongside these surveys, data were also gathered on environmental, hydrological, and meteorological factors. In an attempt to model macrophyte presence several linear models were developed based on the data gathered. While these models provided a basis on which factors influencing macrophyte presence could be investigated, they were somewhat crude and lacking in accuracy. As an alternative, inductive learning methods (for example, Artificial Neural Networks) have been used as a means to model macrophyte presence (specifically, Ranunculus spp.). Inductive learning algorithms are well suited to problems of this nature due to their ability to handle non-linear, noisy, and inconsistent data. This paper discusses how data were gathered, processed, and used to develop artificial neural network models of Ranunculus spp. presence in the Rivers Test and Itchen. This paper presents the results of the models developed and compares them with more popular statistical techniques.