Effect of Parametric Uncertainty of Selected Classification Models and Simulations of Wastewater Quality Indicators on Predicting the Sludge Volume Index

Abstract

Commonly used models for predicting natural phenomena include classification models. These may be black box methods (neural networks, support vector machines, random forests, etc.) or models giving an explicit dependence enabling conclusive assessment of the influence of the explanatory variables on the result of calculations. However, because in this model the result is a specific discrete value, the result often proves unsatisfactory. In the case of classification models, the problem is of a different nature, because only allocation to the appropriate class is modelled, which in many cases makes it possible to identify technological parameters with a much smaller number of input variables than in

Changes in Concentrations and Loads of Total Phosphorus in Domestic and Treated Wastewater Over a 15-Year Observation Period in Terms of Limiting Negative Anthropopressure on the Quality of Surface Water – Case Study

“…The average value of the analysed nutrient in the wastewater obtained by the author, amounting to 4.2 mg • dm -3 , is significantly lower than that found in this study, in the years 2003-2010. Decreased values of total phosphorus in wastewater were also reported in the publications by Chmielowski et al (2020), Wałęga et al (2019), andJucherski et al (2019).…”