TY - JOUR
T1 - Machine learning using random forest to model heavy metals removal efficiency using a zeolite-embedded sheet in water
AU - Takarina, N. D.
AU - Matsue, N.
AU - Johan, E.
AU - Adiwibowo, A.
AU - Rahmawati, M. F.N.K.
AU - Pramudyawardhani, S. A.
AU - Wukirsari, T.
N1 - Publisher Copyright:
© 2024 © 2024 The author(s). This article is licensed under a Creative Commons Attribution 4.0 International License
PY - 2024/12
Y1 - 2024/12
N2 - 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.
AB - 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.
KW - Adsorbent
KW - Heavy metals
KW - Random forest
KW - Removal efficiency
KW - Zeolite
UR - http://www.scopus.com/inward/record.url?scp=85174357951&partnerID=8YFLogxK
U2 - 10.22034/gjesm.2024.01.20
DO - 10.22034/gjesm.2024.01.20
M3 - Article
AN - SCOPUS:85174357951
SN - 2383-3572
VL - 10
SP - 321
EP - 336
JO - Global Journal of Environmental Science and Management
JF - Global Journal of Environmental Science and Management
IS - 1
ER -