Describing and simulating phytoplankton of a small and shallow reservoir using decision trees and rule-based models.

Phytoplankton represents one of the most important biological components of primary production, trophic interactions, and circulation of organic matter in lakes and reservoirs. To contribute to the understanding of eutrophication processes and ecological status of the small, shallow Butoniga reservoir, a machine learning tool for induction of models in form of decision trees and rule-based models was applied on a dataset comprising physical, chemical, and biological variables measured at four stations. Two types of models were successfully elaborated, i.e., (1) model describing phytoplankton Phylum, which describes and connects phytoplankton Phylum with phytoplankton abundance and biomass, and (2) model simulating phytoplankton biomass according to environmental variables which could be used in management purposes. Such models and their presentation contribute to a better understanding of the Butoniga reservoir ecosystem functioning.

Hybrid modeling approach for the northern Adriatic watershed management.

Northern Adriatic (NA) is one of the most productive parts of the Mediterranean Sea due to vast nutrient discharges from the contributing watershed. To understand better the excess of nutrients as stressors to the state of the marine ecosystem, a hybrid modeling approach following the DPSIR framework and terminology was developed, linking: 1) the AVGWLF model for modeling the pressures, i.e. nutrients originating from the watershed caused by two major drivers (urbanization and agriculture), 2) the ML tool MTSMOTI for inducing a model tree connecting the pressures with the marine ecosystem state, and 3) the water quality index, TRIX, equation to evaluate the trophic state of the marine ecosystem. Data used for the modeling purpose comprised GIS layers (i.e., digital terrain model, land use/cover data, soil map, locations of hydro-meteorological stations and WWTPs), time series data (i.e., hydro-meteorological data and nutrient concentrations), and statistical data (i.e., number of inhabitants, connections to wastewater treatment, livestock statistics, etc.) as well as physical, chemical and biological parameters, measured at six marine water monitoring stations, located between the Po River delta (Italy) and the city of Rovinj (west Istrian coast, Croatia). Using the model, seven watershed management scenarios related to wastewater treatment and agricultural activities were evaluated for their influence on the state of the NA marine ecosystem. According to the results, the gradual implementation of the UWWTD in the last 10years contributed significantly to the preservation and improvement of the NA marine ecosystem state. However, despite the full implementation of the UWWTD, the state of the NA marine ecosystem could deteriorate in case of increased nutrient loads from agriculture. Since the UWWTD is already close to its full implementation, NA watershed management should focus on controlling agricultural activities in order to maintain 'high' state of the NA marine ecosystem.