Modelling aeration efficiency of free surface flows by using least square support vector machines

Most important water quality parameter is amount of dissolved oxygen. Amount of dissolved oxygen is vital importance for aquatic life. Concentration of dissolved oxygen is decreased with a lot of natural, biological and chemical events. In this biological events and chemical reactions oxygen is used. Therefore, amount of dissolved oxygen is decreased. The same quantity of oxygen transfer that normally would occur over several kilometers in rivers can occur quickly with hydraulic structures. A lot of air bubbles are entrained into the flow by means of hydraulic structures. This air bubbles greatly increases the surface area for oxygen transfer and so oxygen transfer occurs easily.Computation on civil engineering has concentrated primarily on artificial intelligence applications in the past few years. These applications generally involve Expert Systems. This work deals with a different artificial intelligence approach involving Least Square Support Vector Machines and three applications are presented. In these applications of Least Square Support Vector Machines, air entrainment and aeration efficiency in sharp-crested weirs, flow conditions and aeration efficiency in stepped cascades and aeration efficiency in free surface gated conduits are modeled. Moreover, aeration efficiency in free surface gated conduits are modeled with Artificial Neural Networks and Adaptive Network-Based Fuzzy Inference System and compared with the results of Least Square Support Vector Machines. It has been shown that the Least Square Support Vector Machines computation is an alternative solution for decision and design in civil engineering.