The paper presents an overview of modern anaerobic wastewater treatment technologies.Characterised reactors for anaerobic wastewater treatment include UASB, ABR, AMBR, ASBR, AnMBR and EGSB reactors.Comparison with aerobic methods shows that use of anaerobic reactors allows for at least three times reduction of the amount sludge.Analysing the disadvantages and advantages of anaerobic wastewater treatment reactors, it can be concluded that their use is beneficial in wastewater treatment plants with problems of high COD concentrations in incoming wastewater and problems of the amount of sewage sludge produced.

The aim of the study was to evaluate the possibility of applying different methods of data mining to model the inflow of sewage into the municipal sewage treatment plant. Prediction models were elaborated using methods of support vector machines (SVM),random forests (RF), k-nearest neighbour (k-NN) and of Kernel regression (K). Data consisted of the time series of daily rainfalls, water level measurements in the clarified sewage recipient and the wastewater inflow into the Rzeszow city plant. Results indicate that the best models with one input delayed by 1 day were obtained using the k-NN method while the worst with the K method. For the models with two input variables and one explanatory one the smallest errors were obtained if model inputs were sewage inflow and rainfall data delayed by 1 day and the best fit is provided using RF method while the worst with the K method. In the case of models with three inputs and two explanatory variables, the best results were reported for the SVM and the worst for the K method. In the most of the modelling runs the smallest prediction errors are obtained using the SVM method and the biggest ones with the K method. In the case of the simplest model with one input delayed by 1 day the best results are provided using k-NN method and by the models with two inputs in two modelling runs the RF method appeared as the best.

In the study, models developed using data mining methods are proposed for predicting wastewater quality indicators: biochemical and chemical oxygen demand, total suspended solids, total nitrogen and total phosphorus at the inflow to wastewater treatment plant (WWTP). The models are based on values measured in previous time steps and daily wastewater inflows. Also, independent prediction systems that can be used in case of monitoring devices malfunction are provided. Models of wastewater quality indicators were developed using MARS (multivariate adaptive regression spline) method, artificial neural networks (ANN) of the multilayer perceptron type combined with the classification model (SOM) and cascade neural networks (CNN). The lowest values of absolute and relative errors were obtained using ANN+SOM, whereas the MARS method produced the highest error values. It was shown that for the analysed WWTP it is possible to obtain continuous prediction of selected wastewater quality indicators using the two developed independent prediction systems. Such models can ensure reliable WWTP work when wastewater quality monitoring systems become inoperable, or are under maintenance.

Due to a stochastic nature of sewage inflow into a treatment plant the inflow amount and its quality are highly variable which has a significant impact on the plant technological objects operation. Hence, sewage inflow forecasting would be desirable as it allows for mitigating the impact of abnormal events that might lead to major plant installation disruption. This paper presents the results of a raw sewage inflow modeling using Artificial Neural Networks (ANNs). Results of the three-year measurements of precipitation rates and sewage treatment plant inflow in Rzeszow and Kielce were used in the analyses. To assess the impact of exogenous variables on the model quality the logistic regression method was applied. The variables considered were the precipitation rate and daily sewage inflow, which were appropriately delayed in relation to the forecasted inflow values. Impact of the model structure parameters on accuracy of the mathematical model forecasts was also investigated.

Forecasting the amount and quality of wastewater flowing into a treatment plant sufficiently in advance, enables effective control of numerous treatment process parameters. Therefore, mathematical (physical deterministic and time series statistical) models forecasting both the amount and quality of wastewater inflow into a sewage treatment plant are under development. In this paper, a possibility of simpler time series models application to forecasting values of selected indicators (biochemical oxygen demand (BOD5), total suspended solids (TSS), total nitrogen (TN), total phosphorus (TP) and ammonium (NH4+)) of sewage quality in the inflow into a treatment plant was investigated. The research was based solely on sewage flow rate data and - for the purpose of comparison - the actual measured indicator values. For this purpose, MARS type blackbox and random forest (RF) methods were used. Also, a possibility of combining the RF method with a classification model (RF+SOM) was investigated. Boosted trees (BT) and principal component analysis (PCA) methods were applied for identification of data that determine variability of the selected sewage quality indicators. The models were developed on the basis of continuous daily measurements performed in the period of 2013-2015 in the municipal sewage treatment plant in Rzeszow.

In municipal waterworks the operation of water and wastewater networks decides about the functioning of the sewage treatment plant that is the last element of the whole water and sewage system. The both networks are connected each other and the work of the water net affects the operation of the wastewater one. The parameters which are important for right leading of all waterworks objects are their hydraulic loads that have to be not exceeded. Too large loads can cause accidents in the wastewater net or the tratment plant and an early knowledge of them is of importance for undertaking some counteractions. In the paper different algorithms to model hydraulic loads of municipal water and wastewater nets are described and compared regarding their computation velocity and accuracy. Some exemplary computations have been done with some real data received from a Polish water company.

In communal waterworks the whole water and sewage system consists usually of three basic objects: of water supply system, wastewater network and of sewage treatment plant. They are connected each other in series and the work quality of one of them affects the functioning of the following one. It means, that the water production for the waternet has an influence on the hydraulic load of the wastewater net and it decides of the raw sewage inflow entering the sewage treatment plant. This sewage inflow affects the quality of sewage purification and makes worse the treatment plant control in case of fast and big inflow changes. Because of that there is important to know in advance these inflow changes to have the opportunity to prepare the plant controllers on the oncoming events. A method to predict the sewage inflow changes is to model them. In the paper some mathematical models of raw sewage inflow using the neuronal nets and the time series methods are presented. For the modeling the real data from some Polish waterworks have been used.