Abstract:
The trophic state is one of the significant environmental impacts that must be monitored
and controlled in any aquatic environment. This phenomenon due to nutrient imbalance
in water strengthened with global warming, inhibits the natural system to progress. With
eutrophication, the mass of algae in the water surface increases and results to lower dissolved
oxygen in the water that is essential for fishes. Numerous limnological and physical features
affect the trophic state and thus require extensive analysis to asses it. The univariate ap proach for trophic state classification is based on specified ranges of the cause (Nitrogen,
Phosphorus) or response (Chlorophyll-a [Chl-a] and Secchi Depth [SD]) variables or on the
variable information expressed in the form of indices. Therefore, in this project, an attempt
is made to study about the accurate prediction of TSI using effective combination of differ ent features using Machine Learning(ML), Deep Learning(DL) and hybrid techniques. The
framework was applied to a dataset of 11 lakes, 4 reservoirs and 2 ponds in Kerala for the
period, 2012-2018. In this study, four different Artificial Intelligence(AI) models were devel oped for the prediction of Multivariate Trophic State Index(MTSI) and propose the usage
of random forest as an effective model. Auto-tuned hybrid models are also proposed for
effective Trophic state classification and they show better accuracy than their corresponding
stand-alone models
