Search

In the past few decades, there has been a rapid growth in the concentration of nitrogenous compounds such as nitrate-nitrogen and ammonia-nitrogen in rivers, primarily due to increasing agricultural and industrial activities. These nitrogenous compounds are mainly responsible for eutrophication when present in river water, and for 'blue baby syndrome' when present in drinking water. High concentrations of these compounds in rivers may eventually lead to the closure of treatment plants. This study presents a training and a selection approach to develop an optimum artificial neural network model for predicting monthly average nitrate-N and monthly average ammonia-N. Several studies have predicted these compounds, but most of the proposed procedures do not involve testing various model architectures in order to achieve the optimum predicting model. Additionally, none of the models have been trained for hydrological conditions such as the case of Malaysia. This study presents models trained on the hydrological data from 1981 to 2017 for the Langat River in Selangor, Malaysia. The model architectures used for training are General Regression Neural Network (GRNN), Multilayer Neural Network and Radial Basis Function Neural Network (RBFNN). These models were trained for various combinations of internal parameters, input variables and model architectures. Post-training, the optimum performing model was selected based on the regression and error values and plot of predicted versus observed values. Optimum models provide promising results with a minimum overall regression value of 0.92. [ABSTRACT FROM AUTHOR]

• The highest MPR and yield were observed at thermophilic temperature. • Biological treatment of POME using integrated UASFF bioreactor is a clean method of producing biogas. • Treating POME using two-stage UASFF bioreactor is the first study in Malaysia. • More than 70% of total COD removal of POME could be achieved using integrated UASFF bioreactor. In a two-stage of up-flow anaerobic sludge fixed-film (UASFF) bioreactor, palm oil mill effluent (POME) wastewater was used as inoculum and substrate to study the biodegradation in association with hydrogen and methane production. During the first stage (H 2 -UASFF unit), different temperatures (37–70 °C) and hydraulic retention time (HRT) was designed and analyzed using response surface methodology (RSM) for biohydrogen production. In the second stage (CH 4 -UASFF unit), at 24 h HRT, a continuous experiment was carried out using the same temperature and effluent from H 2 -UASFF unit (also known as dark fermentation effluent) was used as substrate (12–20 g COD L−1). This study is focusing on the second stage of UASFF bioreactor (i.e. CH 4 -UASFF) for biomethane production. Studied parameters were designed using Historical Data in RSM. Its effects on methane production rate (MPR), methane yield, biogas percentage and COD removal were analyzed. The relation between initial effluent COD and temperature on biomethane production and overall reactor performance treating POME wastewater were also examined. Results showed that 76% of total COD removal efficiency (TCOD) was achieved using two-stage UASFF bioreactor. The MPR of 15.63 L CH 4 d−1, methane yield of 0.803 L CH 4 g−1 CODrem.d−1, COD removal efficiency of 66.28% and 93.31% of CH 4 at optimum temperature and effluent COD of 54 °C and 12 g COD L−1, respectively were obtained in CH 4 -UASFF unit. Based on this study, thermophilic temperature and low POME concentration showed a significant impact on biomethane production and more than 70% of TCOD of POME was reduced at 24 h HRT. [ABSTRACT FROM AUTHOR]

• Decision tree model for water quality index prediction proposed in this study. • Authors identified the inter-relationship of WQI with different sets of parameters. • The proposed methodology is offering as cost-effective approach for WQI estimation. The development of water quality prediction models is an important step towards better water quality management of rivers. The traditional method for computing WQI is always associated with errors due to the protracted analysis of the water quality parameters in addition to the great effort and time involved in gathering and analyzing water samples. In addition, the cost of identifying the magnitude of some of the parameters through experimental testing is very high. The water quality of rivers in Malaysia is ranked into five classes based on water quality index (WQI). WQI is function of six water quality parameters: ammoniac nitrogen (NH 3 -N), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS). In this research, the decision tree machine learning technique is used to predict the WQI for the Klang River and its classification within a specific water quality class. Klang River is one of the most polluted rivers in Malaysia. Modeling experiments are designed to test the prediction and classification accuracy of the model based on various scenarios composed of different water quality parameters. Results show that the proposed prediction model has a promising potential to predict the class of the WQI. Moreover, the proposed model offers a more efficient process and cost-effective approach for the computation and prediction of WQI. [ABSTRACT FROM AUTHOR]