Unravelling and forecasting algal population dynamics in two lakes different in morphometry and eutrophication by neural and evolutionary computation

摘要: Abstract Precious ecological information extracted from limnological long-term time series advances the theory on functioning and evolution of freshwater ecosystems. This paper presents results applications artificial neural networks (ANN) evolutionary algorithms (EA) for ordination, clustering, forecasting rule discovery complex time-series data two distinctively different lakes. Ten years shallow hypertrophic Lake Kasumigaura (Japan) are utilized in comparison with 13 deep mesotrophic Soyang (Korea). Results demonstrate potential that: (1) recurrent supervised ANN EA facilitate 1-week-ahead outbreaks harmful algae or water quality changes, (2) discover explanatory sets timing abundance algal populations, (3) non-supervised provide clusters to unravel relationships regarding seasons, ranges environmental changes.