Abstract: Prediction of highly non linear behavior of suspended
sediment flow in rivers has prime importance in the field of water
resources engineering. In this study the predictive performance of
two Artificial Neural Networks (ANNs) namely, the Radial Basis
Function (RBF) Network and the Multi Layer Feed Forward (MLFF)
Network have been compared. Time series data of daily suspended
sediment discharge and water discharge at Pari River was used for
training and testing the networks. A number of statistical parameters
i.e. root mean square error (RMSE), mean absolute error (MAE),
coefficient of efficiency (CE) and coefficient of determination (R2)
were used for performance evaluation of the models. Both the models
produced satisfactory results and showed a good agreement between
the predicted and observed data. The RBF network model provided
slightly better results than the MLFF network model in predicting
suspended sediment discharge.
Abstract: Petroleum refineries discharged large amount of
wastewater -during the refining process- that contains hazardous
constituents that is hard to degrade. Anaerobic treatment process is
well known as an efficient method to degrade high strength
wastewaters. Up-flow Anaerobic Sludge Blanker (UASB) is a
common process used for various wastewater treatments. Two UASB
reactors were set up and operated in parallel to evaluate the treatment
efficiency of petroleum refinery wastewater. In this study four
organic volumetric loading rates were applied (i.e. 0.58, 0.89, 1.21
and 2.34 kg/m3·d), two loads to each reactor. Each load was applied
for a period of 60 days for the reactor to acclimatize and reach steady
state, and then the second load applied. The chemical oxygen demand
(COD) removals were satisfactory with the removal efficiencies at the
loadings applied were 78, 82, 83 and 81 % respectively.