EUVIMEDEUVIMED entdecken
Crossref

Machine Learning-Assisted Prediction of Mercury Removal Efficiency of Carbon-Based Adsorbents

Shilin Zhao iD, Qi Liu, Yuchen Wang, Lidong Wang iD, Jun Zhang iD, Zhiqiang Sun iD

Environmental Science & Technology · 2025

DOI: 10.1021/acs.est.5c03148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Science & Technology, 2025. Verfasst von Shilin Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hunan Engineering Research Center of Clean and Low-Carbon Energy Technology, School of Energy Science and Engineering, Central South University, Chan…. Hauptthemen laut MEDLINE: Machine Learning, Mercury, Carbon. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Central South University, Natural Science Foundation of Hunan Province, Natural Science Foundation of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adsorbent injection is the most promising technology for solving anthropogenic mercury (mainly Hg0) emission from stationary sources. Carbon-based adsorbents have strong potential for Hg0 removal due to their high specific surface area and abundant functional groups. However, traditional experimental methods focus on a single adsorbent under specific mercury removal conditions, making it difficult to obtain universal influencing laws and optimal preparation methods for the adsorbents. This study used machine learning (ML) to predict Max. Hg0 removal efficiency based on the experimental data including adsorbent parameters and removal conditions published over the past 25 years. It shows that the gradient boosting decision tree (GBDT) model has the best prediction effect (test R2 = 0.87). The Brunauer-Emmett-Teller (BET) surface area and Cl are important factors affecting the Max. Hg0 removal efficiency, especially within a certain range. By adjusting the BET surface area and the halogen (Cl, Br, and I) ratio, the Max. Hg0 removal efficiencies of carbon-based adsorbents can be improved from 85 to 98.4, 90.7, and 88.6%, respectively. The maximum error between the experimental and predicted values is within 10%, proving the accuracy of the ML model prediction. The finding has important guiding significance for the design and development of high-performance mercury removal adsorbents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMercuryCarbonAdsorption

Stichwörter der Autor:innen

GBDTcarbon-based adsorbentengineering validationmachine learningmercury removal

Substanzen

MercuryCarbon

Autor:innen und Institutionen

  • Hunan Engineering Research Center of Clean and Low-Carbon Energy Technology, School of Energy Science and Engineering, Central South University, Changsha 410083, China.
  • School of Environmental Science and Engineering, North China Electric Power University, Baoding 071003, China.
  • School of Electronic Information, Nanjing Vocational College of Information Technology, Nanjing 210023, China.

ORCID-Profile: Shilin Zhao, Lidong Wang, Jun Zhang, Zhiqiang Sun

Förderung

  • Central South University
  • Natural Science Foundation of Hunan Province
  • Natural Science Foundation of Jiangsu Province
  • Science and Technology Program of Hunan Province
  • National Natural Science Foundation of China
  • MOE Key Laboratory of Resources and Environmental System Optimization, North China Electric Power University

Zitieren

APA

Zhao, S., Liu, Q., Wang, Y., Wang, L., Zhang, J., & Sun, Z. (2025). Machine Learning-Assisted Prediction of Mercury Removal Efficiency of Carbon-Based Adsorbents. Environmental Science & Technology. https://doi.org/10.1021/acs.est.5c03148

Vancouver

Zhao S, Liu Q, Wang Y, Wang L, Zhang J, Sun Z. Machine Learning-Assisted Prediction of Mercury Removal Efficiency of Carbon-Based Adsorbents. Environmental Science & Technology. 2025. doi:10.1021/acs.est.5c03148

BibTeX
@article{Zhao2025,
  author = {Zhao, Shilin and Liu, Qi and Wang, Yuchen and Wang, Lidong and Zhang, Jun and Sun, Zhiqiang},
  title = {Machine Learning-Assisted Prediction of Mercury Removal Efficiency of Carbon-Based Adsorbents},
  journal = {Environmental Science & Technology},
  year = {2025},
  doi = {10.1021/acs.est.5c03148}
}
Kostenlos starten →