This article deals with issues related to the optimization of traffic management in modern cities, the so-called Smart City. In particular, the article presents the process of evolution of the traffic flow prediction model at a selected crossroads in a selected city in Poland - the city of Rzeszów. Rzeszow is an example of a smart city equipped with an extensive system of real-time data collection and processing from multiple road points in the city. The research was aimed at a detailed analysis of the feasibility and degree of fit of different variants of the regression model: linear, polynomial, trigonometric, polynomial-trigonometric, and regression-based Random Forest algorithm. Several studies were carried out evaluating different generations of models, in particular, an analysis was carried out based on which the superiority of the trigonometric model was demonstrated. This model had the best fit and the lowest error rate, which could be a good conclusion for widespread use and implementation in Smart City supervisory systems.

The paper presents the toxicity changes of landfill leachate during landfill processes simulation as well as after Advanced Oxidation Processes implementation to the leachate. A bioluminescence toxicity test Toxalert®10 with the pure cultures of Vibrio fischeri was used. The significant difference in the leachate toxicity originating from acidogenic landfill phase in comparison to the methanogenic phase was noticed. The leachate ozonation led to the toxicity reductions. The hydrogen peroxide application caused the toxicity increase and slowed down the landfill processes.