基于机器学习的金属有机框架吸附水中重金属性能预测

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1183 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为了能准确预测金属有机框架材料(MOFs)对水中重金属的吸附性能,收集了48篇文献中的MOFs结构特征和成分特性,以及吸附水中重金属的实验参数建立数据集,训练并评价了6种回归模型,包括支持向量回归(SVR)、K-最近邻(KNN)、提升法(AdaBoost)、梯度提升树(GBDT)、随机森林(RF)和袋装法(Bagging).结果表明:基于树的集成学习模型的预测性能表现优异,其中以GBDT算法训练的模型性能最佳;进一步应用该模型,证明了机器学习方法可以准确预测MOFs对水中重金属的吸附性能;排列重要性与部分依赖图(PDP)显示,除了可控的实验参数外,影响吸附量的重要因素是MOFs的孔径、比表面积、孔体积.本研究中的方法不仅能预测MOFs结构和性能的关系,还可以基于有效的实验参数模拟水中重金属的去除,进而为吸附材料的筛选优化提供参考.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	姜明星
	王斯坦
	许端平

关键词 ：水处理, 机器学习, 金属有机框架, 重金属吸附, 预测模型

Abstract：In order to accurately predict the adsorption performance of MOFs on heavy metals in water, the structural and compositional features of MOFs as well as their experimental parameters for adsorption of heavy metals were extracted to build a dataset, which were collected from the experimental results of 48 published papers. Six regression models were trained and evaluated, including SVR, KNN, AdaBoost, GBDT, RF and Bagging. The results showed that the tree-based ensemble learning models exhibited excellent prediction performance. Especially, the GBDT was determined as the optimal algorithm. With the further application of the model, it is demonstrated that the machine learning method can accurately predict the adsorption performance of MOFs for heavy metals in water. The feature importance ranking (FIR) and partial dependence plots (PDP) analyses revealed that, besides the controllable experimental parameters, the pore size, specific surface area and pore volume of MOFs were the key factors affecting the adsorption capacity. The method in this study not only predicts the structure-performance relationships, but also simulates the removal of heavy metals in water based on effective experimental parameters, which could provide guidance for screening and optimization of adsorbent materials.

Key words： water treatment machine learning metal-organic frameworks adsorption of heavy metals prediction model

收稿日期: 2022-09-13

PACS:

X703

基金资助:国家重点研发计划项目(2019YFC1803800);辽宁省教育厅科学研究项目(LJ2019QL009)

通讯作者: 王斯坦,副教授,wangsitan@lntu.edu.cn E-mail: wangsitan@lntu.edu.cn

作者简介: 姜明星(1997-),男,河南淇县人,辽宁工程技术大学硕士研究生,主要从事水污染吸附分离技术及机器学习应用研究.jiangmingxing97@163.com.

引用本文:

姜明星, 王斯坦, 许端平. 基于机器学习的金属有机框架吸附水中重金属性能预测[J]. 中国环境科学, 2023, 43(5): 2319-2327. JIANG Ming-xing, WANG Si-tan, XU Duan-ping. Prediction of adsorption performance of MOFs for heavy metals in water based on machine learning. CHINA ENVIRONMENTAL SCIENCECE, 2023, 43(5): 2319-2327.

链接本文:

http://www.zghjkx.com.cn/CN/ 或 http://www.zghjkx.com.cn/CN/Y2023/V43/I5/2319

[1]	Barakat M A. New trends in removing heavy metals from industrial wastewater[J]. Arabian Journal of Chemistry, 2011,4(4):361-377.
[2]	Saha D, Deng S. Ammonia adsorption and its effects on framework stability of MOF-5and MOF-177[J]. Journal of Colloid and Interface Science, 2010,348(2):615-620.
[3]	Ghanbari T, Abnisa F, Wan D, Wan M A. A review on production of metal organic frameworks (MOF) for CO2 adsorption[J]. Science of the Total Environment, 2020,707:135090.
[4]	Du C, Zhang Z, Yu G, et al. A review of metal organic framework (MOFs)-based materials for antibiotics removal via adsorption and photocatalysis[J]. Chemosphere, 2021,272:129501.
[5]	Zhang S, Wang J, Zhang Y, et al. Applications of water-stable metal-organic frameworks in the removal of water pollutants:A review[J]. Environmental Pollution, 2021,291:118076.
[6]	Rani L, Kaushal J, Srivastav A L, et al. A critical review on recent developments in MOF adsorbents for the elimination of toxic heavy metals from aqueous solutions[J]. Environmental Science and Pollution Research, 2020,27(36):44771-44796.
[7]	Kobielska P A, Howarth A J, Farha O K, et al. Metal-organic frameworks for heavy metal removal from water[J]. Coordination Chemistry Reviews, 2018,358:92-107.
[8]	王诗慧,薛小雨,程敏,等.机器学习与分子模拟协同的CH4/H2分离金属有机框架高通量计算筛选[J].化学学报, 2022,80(5):614-640. Wang S H, Xue X Y, Cheng M, et al. High-throughput computational screening of metal-organic frameworks for CH4/H2separation by synergizing machine learning and molecular simulation[J]. Acta Chimica Sinica, 2022,80(5):614-640.
[9]	Zhong S, Zhang K, Bagheri M, et al. Machine learning:New ideas and tools in environmental science and engineering[J]. Environmental Science & Technology, 2021,55(19):12741-12754.
[10]	Shi Z, Yang W, Deng X, et al. Machine-learning-assisted high-throughput computational screening of high performance metal-organic frameworks[J]. Molecular Systems Design & Engineering, 2020,5(4):725-742.
[11]	徐发昭,李净,褚馨德,等.基于MODIS数据与多机器学习法的日PM2.5模拟研究[J].中国环境科学, 2022,42(6):2523-2529. Xu F Z, Li J, Chu X D, et al. Simulation of daily PM2.5 based on MODIS data and multi-machine learning method[J]. China Environmental Science, 2022,42(6):2523-2529.
[12]	康俊锋,谭建林,方雷,等.XGBoost-LSTM变权组合模型支持下短期PM2.5浓度预测——以上海为例[J].中国环境科学, 2021,41(9):4016-4025. Kang J F, Tan J L, Fang L, et al. Short-term PM2.5 concentration prediction based on XGBoost and LSTM variable weight combination model:A case study of Shanghai[J]. China Environmental Science, 2021,41(9):4016-4025.
[13]	康俊锋,黄烈星,张春艳,等.多机器学习模型下逐小时PM2.5预测及对比分析[J].中国环境科学, 2020,40(5):1895-1905. Kang J F, Huang L X, Zhang C Y, et al. Hourly PM2.5 prediction and its comparative analysis under multi-machine learning model[J]. China Environmental Science, 2020,40(5):1895-1905.
[14]	Gülsoy Z, Sezginel K B, Uzun A, et al. Analysis of CH4 Uptake over metal-organic frameworks using data-mining tools[J]. ACS Combinatorial Science, 2019,21(4):257-268.
[15]	Nguyen X C, Ly Q V, Nguyen T T H, et al. Potential application of machine learning for exploring adsorption mechanisms of pharmaceuticals onto biochars[J]. Chemosphere, 2022,287:132203.
[16]	Lu C, Xu Z, Dong B, et al. Machine learning for the prediction of heavy metal removal by chitosan-based flocculants[J]. Carbohydrate Polymers, 2022,285:119240.
[17]	Smola A J, Schölkopf B. A tutorial on support vector regression[J]. Statistics and Computing, 2004,14(3):199-222.
[18]	Goldberger J, Hinton G E, Roweis S, et al. Neighbourhood components analysis[J]. Advances in neural information processing systems, 2004,17.
[19]	Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997,55(1):119-139.
[20]	Friedman J H. Greedy function approximation:A gradient boosting machine[J]. The Annals of Statistics, 2001,29(5):1189-1232.
[21]	Breiman L. Random forests[J]. Machine Learning, 2001,45(1):5-32.
[22]	Breiman L. Bagging predictors[J]. Machine Learning, 1996,24(2):123-140.
[23]	Liu Y, Mu Y, Chen K, et al. Daily activity feature selection in smart homes based on pearson correlation coefficient[J]. Neural Processing Letters, 2020,51(2):1771-1787.
[24]	Wang C, Pan Y, Chen J, et al. Indicator element selection and geochemical anomaly mapping using recursive feature elimination and random forest methods in the Jingdezhen region of Jiangxi Province, South China[J]. Applied Geochemistry, 2020,122:104760.
[25]	Yuan X, Suvarna M, Low S, et al. Applied machine learning for prediction of CO2 adsorption on biomass waste-derived porous carbons[J]. Environmental Science & Technology, 2021,55(17):11925-11936.
[26]	张瑞鸿,魏鑫,卢占会,等.基于机器学习训练金属离子吸附能预测模型的研究[J].无机材料学报, 2021,36(11):1178-1184. Zhang R H, Wei X, Lu Z H, et al. Training Model for Predicting Adsorption Energy of Metal Ions Based on Machine Learning[J]. Journal of Inorganic Materials, 2021,36(11):1178-1184.
[27]	Sundhararajan S, Pahwa A, Krishnaswami P. A comparative analysis of genetic algorithms and directed grid search for parametric optimization[J]. Engineering with Computers, 1998,14(3):197-205.
[28]	Li J, Pan L, Suvarna M, et al. Fuel properties of hydrochar and pyrochar:Prediction and exploration with machine learning[J]. Applied Energy, 2020,269:115166.
[29]	Kim S Y, Kim S I, Bae Y S. Machine-learning-based prediction of methane adsorption isotherms at varied temperatures for experimental adsorbents[J]. The Journal of Physical Chemistry C, 2020,124(36):19538-19547.
[30]	Tso G K F, Yau K K W. Predicting electricity energy consumption:A comparison of regression analysis, decision tree and neural networks[J]. Energy, 2007,32(9):1761-1768.
[31]	周志华.机器学习[M].北京:清华大学出版社, 2016:121-185. Zhou Z H. Machine Learning[M]. Beijing:Tsinghua University Press, 2016:121-185.
[32]	Kuhn M, Johnson K. Data pre-processing[M]. Applied predictive modeling. Springer, 2013:27-59.
[33]	薛薇. Python机器学习:数据建模与分析[M].北京:机械工业出版社, 2021:112-179. Xue W. Python Machine Learning:Data modeling and analysis[M]. Beijing:China Machine Press, 2021:112-179.
[34]	卢慧宫,吴一楠,李舒,等.铁掺杂沸石咪唑酯基金属有机框架材料ZIF-8及其热处理产物对洛克沙胂的吸附研究[J].山东化工, 2016, 45(2):32-35. Lu H G, Wu Y N, Li S, et al. Fe-doped Zeolitic Imidazolate Frameworks ZIF-8 and Adsorption Study for Roxarsone of Its Heat Treatment Products[J]. Shandong Chemical Industry, 2016,45(2):32-35.
[35]	Huang Z, Zhao M, Wang C, et al. Preparation of a novel Zn (II)-imidazole framework as an efficient and regenerative adsorbent for Pb, Hg, and As ion removal from water[J]. ACS Applied Materials & Interfaces, 2020,12(37):41294-41302.
[36]	Nasrollahpour A, Moradi S E. Hexavalent chromium removal from water by ionic liquid modified metal-organic frameworks adsorbent[J]. Microporous and Mesoporous Materials, 2017,243:47-55.
[37]	Wang C, Lin G, Xi Y, et al. Development of mercaptosuccinic anchored MOF through one-step preparation to enhance adsorption capacity and selectivity for Hg (II) and Pb (II)[J]. Journal of Molecular Liquids, 2020,317:113896.
[38]	Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn:Machine learning in python[J]. The Journal of Machine Learning Research, 2011,12:2825-2830.
[39]	Ouyang J, Zhou L, Liu Z, et al. Biomass-derived activated carbons for the removal of pharmaceutical mircopollutants from wastewater:A review[J]. Separation and Purification Technology, 2020,253:117536.