While the oil palm industry has been recognized for its contribution towards economic growth and rapid development, it has also contributed to environmental pollution due to the production of huge quantities of by-products from the oil extraction process. A phytoremediation technique (floating Vetiver system) was used to treat Palm Oil Mill Secondary Effluent (POMSE). A batch study using 40 L treatment tanks was carried out under different conditions and Response Surface Methodology (RSM) was applied to optimize the treatment process. A three factor central composite design (CCD) was used to predict the experimental variables (POMSE concentration, Vetiver plant density and time). An extraordinary decrease in organic matter as measured by BOD and COD (96% and 94% respectively) was recorded during the experimental duration of 4 weeks using a density of 30 Vetiver plants. The best and lowest final BOD of 2 mg/L was obtained when using 15 Vetiver plants after 13 days for low concentration POMSE (initial BOD = 50 mg/L). The next best result of BOD at 32 mg/L was obtained when using 30 Vetiver plants after 24 days for medium concentration POMSE (initial BOD = 175 mg/L). These results confirmed the validity of the model, and the experimental value was determined to be quite close to the predicted value, implying that the empirical model derived from RSM experimental design can be used to adequately describe the relationship between the independent variables and response. The study showed that the Vetiver system is an effective method of treating POMSE.
Artificial neural networks (ANNs) have been widely used to solve the problems because of their reliable, robust, and salient characteristics in capturing the nonlinear relationships between variables in complex systems. In this study, ANN was applied for modeling of Chemical Oxygen Demand (COD) and biodegradable organic matter (BOD) removal from palm oil mill secondary effluent (POMSE) by vetiver system. The independent variable, including POMSE concentration, vetiver slips density, and removal time, has been considered as input parameters to optimize the network, while the removal percentage of COD and BOD were selected as output. To determine the number of hidden layer nodes, the root mean squared error of testing set was minimized, and the topologies of the algorithms were compared by coefficient of determination and absolute average deviation. The comparison indicated that the quick propagation (QP) algorithm had minimum root mean squared error and absolute average deviation, and maximum coefficient of determination. The importance values of the variables was included vetiver slips density with 42.41%, time with 29.8%, and the POMSE concentration with 27.79%, which showed none of them, is negligible. Results show that the ANN has great potential ability in prediction of COD and BOD removal from POMSE with residual standard error (RSE) of less than 0.45%.