Predicting water quality is the key factor in the water quality management of reservoirs. Since a large number of factors affect the water quality, traditional data processing methods are no longer good enough for solving the problem. The dissolved oxygen (DO) level is a measure of the health of the aquatic system and its prediction is very important. DO dynamics are highly nonlinear and artificial intelligence techniques are capable of modelling this complex system. The objective of this study was to develop an adaptive network-based fuzzy inference system (ANFIS) to predict the DO in the Gruža Reservoir, Serbia. The fuzzy model was developed using experimental data which were collected during a 3-year period. The input variables analysed in this paper are: water pH, water temperature, total phosphate, nitrites, ammonia, iron, manganese and electrical conductivity. The selection of an appropriate set of input variables is based on the building of ANFIS models for each possible combination of input variables. Results of fuzzy models are compared with measured data on the basis of correlation coefficient, mean absolute error and mean square error. Comparing the predicted values by ANFIS with the experimental data indicates that fuzzy models provide accurate results.

The aim of the study was to examine heavy metal tolerance (Cd²⁺, Zn²⁺, Ni²⁺ and Cu²⁺) of single- and mixed-species biofilms (Rhodotorula mucilaginosa and Escherichia coli) and to determine metal removal efficiency (Cd²⁺, Zn²⁺, Ni²⁺, Cu²⁺, Pb²⁺ and Hg²⁺). Metal tolerance was quantified by crystal violet assay and results were confirmed by fluorescence microscopy. Metal removal efficiency was determined by batch biosorption assay. The tolerance of the mixed-species biofilm was higher than the single-species biofilms. Single- and mixed-species biofilms showed the highest sensitivity in the presence of Cu²⁺ (E. coli-MIC 4 mg/ml, R. mucilaginosa-MIC 8 mg/ml, R. mucilaginosa/E. coli-MIC 64 mg/ml), while the highest tolerance was observed in the presence of Zn²⁺ (E. coli-MIC 80 mg/ml, R. mucilaginosa-MIC 161 mg/ml, R. mucilaginosa-E. coli-MIC 322 mg/ml). The mixed-species biofilm exhibited better efficiency in removal of all tested metals than single-species biofilms. The highest efficiency in Cd²⁺ removal was shown by the E. coli biofilm (94.85%) and R. mucilaginosa biofilm (97.85%), individually. The highest efficiency in Cu²⁺ (99.88%), Zn²⁺ (99.26%) and Pb²⁺ (99.52%) removal was shown by the mixed-species biofilm. Metal removal efficiency was in the range of 81.56%–97.85% for the single- and 94.99%–99.88% for the mixed-species biofilm.