Modelling constructed wetland treatment system performance

Performance evaluation and prediction for a pilot two-stage on-site constructed wetland system employing dewatered alum sludge as main substrate

“…On the other hand, the appropriate design, operation and evaluation of CW systems are crucial as well as contingent on a good understanding of the internal treatment processes and mechanisms. Regression analysis has been found to be useful for simplified description and analysis of CW systems performance as they provide a means of understanding their treatment process/mechanism (Tomenko et al, 2007;Murray-Gulde et al, 2008;Tang et al, 2009). Although, there are many more approaches with stronger capabilities that could be used to model CW systems performance such as artificial neural networks and multi-component reactive transport module (CW2D) (Langergraber, 2008;Akratos et al, 2009), the use of these complex approaches has been limited and yet to be proven.…”

“…They are regarded as cost-effective and eco-friendly treatment systems with low maintenance and comparatively less energy consumption (Tomenko et al, 2007). They are also fast becoming the system of choice for wastewater treatment especially in rural or isolated areas where conventional systems are not as feasible because of cost effectiveness.…”

Modeling the performance of “up-flow anaerobic sludge blanket” reactor based wastewater treatment plant using linear and nonlinear approaches—A case study

“…Hong et al [52] applied supervised neural network for discovering the complex dependence between the process variables and diagnosed the behavior of the municipal WWTP system. Tomenko et al [53] developed ANN models based on multiple regression analysis (MRA), multi-layer perception and radial basis function approaches for predicting the wastewater treatment efficiency of a constructed wetland treatment (CWT) system relating the input-output wastewater variables and reported a high correlation (0.84-0.99) between the measured and the model predicted values of the effluent BOD.…”

Modeling total phosphorus removal in an aquatic environment restoring horizontal subsurface flow constructed wetland based on artificial neural networks

“…To data, ANNs have been widely used to forecast water demand in urban areas (Liu et al 2003), to forecast daily stream flow (Wang et al 2006), to simulate the lake level fluctuations (Talebizadeh and Moridnejad 2011), and to find the deterministic factors influencing algal blooms (Wilson and Recknagel 2001). ANN-based predictions of the effluent contaminant concentrations, such as chemical oxygen demand, biochemical oxygen demand, total nitrogen, total suspended solids, and organic matter, have also been studied (Akratos et al 2009;Naz et al 2009;Pastor et al 2003;Tomenko et al 2007). However, few published data are available on the application of ANNs to simulation of total phosphorus (TP) removal in waterfowl-contaminated aquatic environment, which places restrictions to the wide application of HSSF-CWs.…”