Environmental Engineering
N.D. Takarina; N. Matsue; E. Johan; A. Adiwibowo; M.F.N.K. Rahmawati; S.A. Pramudyawardhani; T. Wukirsari
Abstract
BACKGROUND AND OBJECTIVES: Zeolite has been recognized as a potential adsorbent for heavy metals in water. The form of zeolite that is generally available in powder has challenged the use of zeolite in the environment. Embedding powder zeolite in a nonwoven sheet, known as a zeolite-embedded sheet can ...
Read More
BACKGROUND AND OBJECTIVES: Zeolite has been recognized as a potential adsorbent for heavy metals in water. The form of zeolite that is generally available in powder has challenged the use of zeolite in the environment. Embedding powder zeolite in a nonwoven sheet, known as a zeolite-embedded sheet can be an alternative to solve that. Another challenge is that information and models of zeolite-embedded sheet removal efficiency are still limited. The novelty of this study is, first, the development of a zeolite-embedded sheet to remove heavy metals from water, and second, the use of the random forest method to model the heavy metal removal efficiency of a zeolite-embedded sheet in water.METHODS: The heavy metals studied were copper, lead and zinc, considering that those are common heavy metals found in water. For developing the zeolite-embedded sheet, the methods include fabrication of the zeolite-embedded sheet using a heating procedure and heavy metals adsorption treatment using the zeolite-embedded sheet. The machine learning analysis to model the heavy metal removal efficiency using zeolite-embedded sheet was performed using the random forest method. The random forest models were then validated using the root mean square error, mean square of residuals, percentage variable explained and graphs depicting out-of-bag error of a random forest.FINDINGS: The results show the heavy metal removal efficiency was 5.51-95.6 percent, 42.71-98.92 percent and 13.39-95.97 percent for copper, lead and zinc, respectively. Heavy metals were reduced to 50 percent at metal concentrations of 10.355 milligram per liter for copper, 171.615 milligram per liter for lead and 4.755 milligram per liter for zinc. Based on the random forest models, the important variables affecting copper removal efficiency using zeolite-embedded sheet were its contents in water, followed by water temperature and potential of hydrogen. Conversely, lead and zinc removal efficiency was influenced mostly by potential of hydrogen. The random forest model also confirms that the high efficiency of heavy metals removal (>60 percent) will be achieved at water potential of hydrogen ranges of 4.94–5.61 and temperatures equal to 29.1 degrees Celsius.CONCLUSION: In general, a zeolite-embedded sheet can adsorb diluted heavy metals from water because there are percentages of adsorbed heavy metals. The random forest model is very useful to provide information and determine the threshold of heavy metal contents, water potential of hydrogen and temperature to optimize the heavy metal removal efficiency using a zeolite-embedded sheet and reducing pollutants in the environment.
A. Masih
Abstract
In view of pollution prediction modeling, the study adopts homogenous (random forest, bagging, and additive regression) and heterogeneous (voting) ensemble classifiers to predict the atmospheric concentration of Sulphur dioxide. For model validation, results were compared against widely known single ...
Read More
In view of pollution prediction modeling, the study adopts homogenous (random forest, bagging, and additive regression) and heterogeneous (voting) ensemble classifiers to predict the atmospheric concentration of Sulphur dioxide. For model validation, results were compared against widely known single base classifiers such as support vector machine, multilayer perceptron, linear regression and regression tree using M5 algorithm. The prediction of Sulphur dioxide was based on atmospheric pollutants and meteorological parameters. While, the model performance was assessed by using four evaluation measures namely Correlation coefficient, mean absolute error, root mean squared error and relative absolute error. The results obtained suggest that 1) homogenous ensemble classifier random forest performs better than single base statistical and machine learning algorithms; 2) employing single base classifiers within bagging as base classifier improves their prediction accuracy; and 3) heterogeneous ensemble algorithm voting have the capability to match or perform better than homogenous classifiers (random forest and bagging). In general, it demonstrates that the performance of ensemble classifiers random forest, bagging and voting can outperform single base traditional statistical and machine learning algorithms such as linear regression, support vector machine for regression and multilayer perceptron to model the atmospheric concentration of sulphur dioxide.
