Predicting the total suspended solids in wastewater: A data-mining approach

Simultaneous nitrification–denitrification of wastewater: effect of zeolite as a support in sequential batch reactor with step-feed strategy

“…On the other hand, it is presumed that the nitrite accumulations in the initial phases are mainly due to the effects of insufficient dissolved oxygen (DO) (0.70 and 0.75 mg O 2 /L in R1 and R2) for nitrite-oxidizing bacteria (NOB) (Chiu et al 2007;Verma et al 2013) in the process of adapting to the SBR operational conditions (days 0-70).…”

“…That is to say, the conditions for the establishment of the SND are favored in R2. At the same time, the zeolite will allow for in R2, on a microenvironmental scale, the adequate microbial ecological morphology for the concurrent coexistence of nitrifying and denitrifying microorganisms within the same floccules, allowing for the boosting of SND metabolism in comparison with R1 (Chiu et al 2007;Zhang et al 2009;Jia et al 2011;Verma et al 2013). The implications of the symbiont coexistence probably lie in that both microbial groups would establish a more expedited link for the metabolic pathways of the oxidation of ammonium and reduction of nitrate/nitrite, favoring the biological process of SND.…”

“…This can be explained by the rapid penetration of CODs in the microbial flocs and/or by its storage in the form of slow biodegradability matter such as in the internal structure of polyhydroxybutyrate (PHB) (Chiu et al 2007;Zhang et al 2009;Jia et al 2011;Verma et al 2013). …”

Application of Selected Methods of Artificial Intelligence to Activated Sludge Settleability Predictions

“…Consequently, to model the processes going on in the individual parts of the treatment plant, i.e. degree of pollutant load reduction (suspended solids, biogenic compounds), to optimise the operation of the treatment plant parts (determination of oxygen amount in activated sludge tanks, the electrical energy used in pumping stations), and also to produce biogas, artificial neural networks [6][7][8][9], genetic programming [10], Support Vector Machines (SVM) [11][12][13], autoregressive models [14], regression trees [15][16], and others are used.…”

Application of Selected Methods of Black Box for Modelling the Settleability Process in Wastewater Treatment Plant

“…Trees are strengthened modification of the classical model of regression trees, while in the method MARS relationship is linear regression spline function of a conditional character. Within the methods of the black box an interesting solution is also random forests [6,7] increasingly used for modeling both the quantity and quality of upstream and downstream of the WWTP as well as forecasting processes taking place in different places of the plant.…”