Single hidden layer artificial neural network models versus multiple linear regression model in forecasting the time series of total ozone

It is known that hydrogen peroxide interferes with chemical oxygen demand analysis by consuming oxidation agents such as potassium dichromate, thus leading to overestimation of the chemical oxygen demand measurements. The objective of the study was to investigate the effects of hydrogen peroxide interference and to determine true chemical oxygen demand values on interpreting treatment performance during ozone-based advanced oxidation of livestock wastewater in which hydrogen peroxide concentration and chemical oxygen demand values are dynamically changing. According to the chemical oxygen demand monitoring data, chemical oxygen demand values were always higher than the initial chemical oxygen demand load when hydrogen peroxide was involved and the treatment performance with ozone alone or ozone/ultraviolet was better than with coupled hydrogen peroxide. The extent of overestimation was proportional to the remaining hydrogen peroxide concentration and the average overestimation ratio in livestock wastewater was in the range of 0.50~0.58 mg per 1 mg of hydrogen peroxide, depending upon the quality of the wastewater treated. True chemical oxygen demand values were estimated by correlating the extent of overestimation with the remaining hydrogen peroxide concentration during treatment. The extent of overestimation decreased to zero gradually as the amount of hydrogen peroxide also approached zero as oxidation proceeded. The corrected chemical oxygen demand values indicated underlying tendency of oxidation, which could not be seen in the original chemical oxygen demand monitoring data. Application of ozone/hydrogen peroxide was more efficient for reducing chemical oxygen demand than ozone alone, as was ozone/hydrogen peroxide/ultraviolet compared to ozone/ultraviolet. When coupled with ozone, ultraviolet irradiation was more efficient than hydrogen peroxide for decreasing chemical oxygen demand during treatment of livestock wastewater.

Section: Methodsmentioning

confidence: 99%

Hydrogen peroxide interference in chemical oxygen demand during ozone based advanced oxidation of anaerobically digested livestock wastewater

Lee

Kim

et al. 2011

“…In recent years, ANN are increasingly used for prediction and pattern recognition problems in various fields of water and environmental science and technology such as total ozone forecasting (Bandyopadhyay and Chattopadhyay 2007), sea level prediction (Altunkaynak 2007, Imani et al 2013, rainfallrunoff modeling (De Vos and Rientjes 2005, Kuok et al 2010, Nourani et al 2011), water quality prediction (Emamgholizadeh et al 2013). A comprehensive literature review about the application of ANN in river forecasting was presented by Abrahart et al (2012).…”

Section: Introductionmentioning

confidence: 99%

Successive-station monthly streamflow prediction using different artificial neural network algorithms

Mehr

Kahya

ŞAHİN

et al. 2014

In this study, applicability of successive-station prediction models, as a practical alternative to streamflow prediction in poor rain gauge catchments, has been investigated using monthly streamflow records of two successive stations on Ç oruh River, Turkey. For this goal, at the first stage, based on eight different successive-station prediction scenarios, feed-forward back-propagation (FFBP) neural network algorithm has been applied as a brute search tool to find out the best scenario for the river. Then, two other artificial neural network (ANN) techniques, namely generalized regression neural network (GRNN) and radial basis function (RBF) algorithms, were used to generate two new ANN models for the selected scenario. Ultimately, a comparative performance study between the different algorithms has been performed using Nash-Sutcliffe efficiency, squared correlation coefficient, and root-meansquare error measures. The results indicated a promising role of successive-station methodology in monthly streamflow prediction. Performance analysis showed that only 1-month-lagged record of both stations was satisfactory to achieve accurate models with high-efficiency value. It is also found that the RBF network resulted in higher performance than FFBP and GRNN in our study domain.

“…The interaction via complexation and precipitation is created by organic pollutants. Due to the hydrophobic forces on the soil surface, organic pollutants are absorbed physically (Paria, 2008;Bandyopadhyay and Chattopadhyay, 2007;Harikumar et al, 2009). Organic pollutants, like oil hydrocarbons, colorized pesticides etc., having limited solubility in water, are usually absorbed into soil organic material and clay particles.…”

Section: Introductionmentioning

confidence: 99%

Response surface methodology approach to the optimization of oil hydrocarbon polluted soil remediation using enhanced soil washing

Kalali

Ebadi

Rabbani

et al. 2011

ABSTRACT:One of the environmental concerns in recent decades is the prevalence of different pollutants in soil. Hence, the importance of remediation has led to the development of various methods to remediate polluted soil. Among these methods, soil washing has gained significant attention to treat polluted soils. In this paper, the response surface methodology was applied in order to determine the optimal conditions for total petroleum hydrocarbon remediation using nonionic surfactant Brij35 in soil environment. The effect of different factors in soil washing process including surfactant solution concentration and volume, washing time, age of pollution and frequency of washing are evaluated.The predicted values for total petroleum hydrocarbon remediation efficiency by the response functions are in a very close agreement with experimental data (R -2 = 98.75 %). The second order model was developed as experimented response and optimal conditions were obtained by analyzing the contour and surface plots and also by solving the regression equation using LINGO 9.0 software. The optimal concentrations (8 g/L), volume of surfactant solution (500 mL), washing time (75 min), age of pollution (29 days) and frequency of washing (three times) are determined. In this optimal condition, the removal efficiency has been observed to be 93.54 % which conforms to the results of process optimization using response surface methodology. Based on the results, it can be concluded that the response surface methodology is a suitable approach to determine the optimal conditions of soil washing to remediate organic hydrophobic pollutants using the nonionic surfactant Brij35 from the soil.