Application of the Kohonen neural network in coastal water management: Methodological development for the assessment and prediction of water quality

Kohonen neural network (KNN) was applied to nutrient data (ammonia, nitrite , nitrate and phosphate) taken from coastal waters in a Spanish tourist are a. The activation maps obtained were not sufficient to evaluate and predict the trophic status of coastal waters. To achieve this aim, a new methodolo gy is proposed which uses as its starting point the activation maps obtaine d from KNN. Firstly, to evaluate the trophic status of the coastal waters. it consists of the development of a quadrat system which enables a better c lassification than the traditional classification based simply on standardi zed data. The new classification allows clear differentiation of water qual ity within the mesotrophic band. Secondly, and in order to use the activati on maps as predictive tools, the trophic classification. obtained from acti vation maps, was transposed onto new activation maps. To do this, the activ ation maps of the sampling points which defined each trophic group were sup erimposed. To avoid unnecessary complexity and to facilitate the process, t his superimposition was undertaken only where the frequency exceeded 0.05. In this way, four frequency maps related to the trophic status of coastal w aters (potentially eutrophic, high mesotrophic, low mesotrophic and oligotr ophic) were obtained. There was no loss of relevant information in the new maps thus obtained. These frequency maps served as the basis for the succes sful prediction of the trophic status of random samples of coastal waters. This methodology, based on KNN, is proposed as a tool to aid the decision-m aking in coastal water quality management. (C) 2001 Elsevier Science Ltd. A ll rights reserved.