Scholarlink

<p>Heavy metal pollution, such as lead ions, has attracted increasing attention. Here, we developed a low-cost zeolite adsorbent using coal fly ash (CFA) as raw material via alkaline fusion-hydrothermal method to capture Pb(II) from aqueous solution, evaluated its adsorption performance under influencing variables and predicted the adsorption of (CFAZ) using six machine learning models. The characterized techniques, including SEM, XRD and FT-IR, demonstrated the phase transformation from CFA to zeolite, which would be profitable to enhance adsorption performance for Pb(II). The Pb(II) adsorption capacity of CFA-based zeolite was about 500&#xa0;mg/g, outperforming CFA. The adsorption data were well defined by the Langmuir isotherm model and pseudo-second-order kinetic model, indicating the nature of monolayer and chemical adsorption. The MLR and RR exhibited excellent predictive capability for this study (<i>R</i><sup>2</sup> = 0.959 and RMSE = 33.7 for MLR; <i>R</i><sup>2</sup> = 0.959 and RMSE = 35.3 for RR). SHAP values showed that the influencing factor was initial concentration, followed by pH value, time and temperature. This work not only develops a low-cost zeolite adsorbent from CFA, with great potential for predicting the adsorption capacity of zeolite in the purification of heavy metal pollution, but also provides a reference for subsequent industrial application of zeolite.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adsorption Optimization of Pb(II) onto Fly Ash-Based Zeolite Using a Modeling Approach and Machine Learning Algorithms

  • 期刊论文

  • 发表日期：

    2025年1月13日

查看全文
  • Jingyu Sun,
  • Yuzhi Zhou,
  • Pian Hu,
  • Rui Duan,
  • Wenshuo Wang,
  • Yingze Ye,
  • Min Chen,
  • Xiaoyang Chen

摘要

Heavy metal pollution, such as lead ions, has attracted increasing attention. Here, we developed a low-cost zeolite adsorbent using coal fly ash (CFA) as raw material via alkaline fusion-hydrothermal method to capture Pb(II) from aqueous solution, evaluated its adsorption performance under influencing variables and predicted the adsorption of (CFAZ) using six machine learning models. The characterized techniques, including SEM, XRD and FT-IR, demonstrated the phase transformation from CFA to zeolite, which would be profitable to enhance adsorption performance for Pb(II). The Pb(II) adsorption capacity of CFA-based zeolite was about 500 mg/g, outperforming CFA. The adsorption data were well defined by the Langmuir isotherm model and pseudo-second-order kinetic model, indicating the nature of monolayer and chemical adsorption. The MLR and RR exhibited excellent predictive capability for this study (R2 = 0.959 and RMSE = 33.7 for MLR; R2 = 0.959 and RMSE = 35.3 for RR). SHAP values showed that the influencing factor was initial concentration, followed by pH value, time and temperature. This work not only develops a low-cost zeolite adsorbent from CFA, with great potential for predicting the adsorption capacity of zeolite in the purification of heavy metal pollution, but also provides a reference for subsequent industrial application of zeolite.