The lower Nakdong River is one of regulated river systems lies in Eastern Asian region (South Korea), and strongly governed by summer concentrated rainfall due to monsoon climate in June to July and several typhoons in the rest of summer (July to early September). The annual phytoplankton dynamics in the lower part of the river are influenced by the summer rainfall due to extensive discharge control by dams and the estuarine barrage constructed at the river mouth. Because of large magnitude of summer rainfall in the recent decade, summer cyanobacterial proliferations are rarely observed which frequently caused serious water quality problem during dry summers in 1994 to 1996. River flow control diminishes winter Stephanodiscus hantzschii blooms in magnitude, however, annually this species dominates the phytoplankton community from November to the next February up to 90%. Some studies suggested that the environmental condition during the bloom period is quite preferable for the species, so that mostly hydrological characteristics which are governed by climate variations are responsible for the dynamics of S. hantzschii. The development of Evolving Neural Network (ENN) in this study was aimed to predict and discover relationship between the species proliferations and climate variation data such as indices values of Pacific Decadal Oscillation (PDO), Southern Oscillation Index (SOI), Multivariate Enso Index (MEI), sea surface temperature-related indices (Nin?-3 and Nin?-3.4), and Arctic Oscillation (AO). Genetic operators successfully selected influential input variables among them, and the final model's predictability was reasonable for the training and testing data sets. Sensitivity analysis showed the possible relationship between the input and output variables, which could be translated that the changes of climate in short term (more or less than 10-12 months) led the fluctuations of hydrological conditions in the river, which resulted in the bloom formation of S. hantzschii. The results of this study can be considered as a good example for the application of Ecological Informatics to long-term ecological data with respect to global climate changes. On the basis of the information, further interdisciplinary in-depth research regarding climate-hydrology-ecology should be addressed.