Chapter 28 – Modeling of constructed wetland performance

Publisher Summary This chapter presents a case study to examine the utility of applying K-nearest neighbors (KNN), support vector machine (SVM), and self-organizing map (SOM) to predict the outflow water quality of experimental constructed treatment wetlands by comparing the accuracy of these models. KNN, SVM, and SOM were applied to predict five-day @ 20C N-Allylthiourea biochemical oxygen demand (BOD) and suspended solids (SS), and to assess novel alternative methods of analyzing water quality performance indicators for constructed treatment wetlands. The BOD and SS, which are expensive to estimate, can be cost-effectively monitored by applying machine learning tools with input variables such as turbidity and conductivity. As far as accuracy of prediction is concerned, SOM showed a better performance compared to both KNN and SVM. SOM also had the potential to visualize the relationship between complex biochemical variables. However, optimizing the SOM requires more time in comparison to KNN and SVM, because of its trial and error process in searching for the optimal map. The results suggest that BOD and SS can be efficiently estimated by applying machine learning tools with input variables such as redox potential and conductivity, which can be monitored in real time. Their performances are encouraging and support the potential for future use of these models as management tools for the day-to-day process control.