Use of artificial neural network in the prediction of algal blooms

A model to quantify the interactions between abiotic factors and algal gene ra in Lake Kasumigaura, Japan was developed using artificial neural network technology. Results showed that the timing and magnitude of algal blooms o f Microcystis. Phormidium and Synedra in Lake Kasumigaura could be successf ully predicted. As for the newly occurring dominant Oscillatoria. results w ere not satisfactory. The evaluation of the importance of factors showed th at Microcystis. Phormidium, Oscillatoria and Synedra were alkalophilic. The algal proliferation for Microcystis. Oscillatoria and Synedra decrease due to the increase in total nitrogen. while the growth of Phormidium is enhan ced with more nitrogen, In addition. the algal density is affected by zoopl ankton grazing but with the exception of Phormidium due to it being poor fo od source. Algal responses to the orthogonal combinations of the external e nvironmental factors, chemical oxygen demand, pH, total nitrogen and total phosphorus at three levels were modeled. Various combinations of environmen tal factors enhance the proliferation of some algae while other combination s inhibit bloom formation. (C) 2001 Elsevier Science Ltd. All rights reserv ed.