Prediction of methylene blue dye sorption to sulfonated date palm kernel biochar using statistical regression and machine learning methods and DFT studies

IF 5.3 2区化学 Q2 CHEMISTRY, PHYSICAL

Journal of Molecular Liquids Pub Date : 2025-04-05 DOI:10.1016/j.molliq.2025.127547

Uyiosa Osagie Aigbe , Kingsley Eghonghon Ukhurebor , Robert Birundu Onyancha , Adelaja Otolorin Osibote , Mohamed A. Hassaan , Marwa R. ElKatory , Ahmed El Nemr

{"title":"Prediction of methylene blue dye sorption to sulfonated date palm kernel biochar using statistical regression and machine learning methods and DFT studies","authors":"Uyiosa Osagie Aigbe , Kingsley Eghonghon Ukhurebor , Robert Birundu Onyancha , Adelaja Otolorin Osibote , Mohamed A. Hassaan , Marwa R. ElKatory , Ahmed El Nemr","doi":"10.1016/j.molliq.2025.127547","DOIUrl":null,"url":null,"abstract":"<div><div>In this study, methylene blue (MB) dye adsorption to synthesised sulfonated date palm kernel biochar (SDPKB) was predicted and optimized using statistical-based regression approach (response surface methodology (RSM), machine-learning algorithms (artificial-neural-network (ANN), and adaptive-neuro-fuzzy-inference-system (ANFIS) models), and quantum chemistry calculations performed using density function theory (DFT) to link the electrical properties of the MB dye with the experimental findings. The percentage (%) of MB dye removed using SDPKB was found to be proportional to the biosorbent dosage and interaction time and inversely proportional to the solution pH and initial concentrations based on different used models results. It was observed that these models were accurate and comparable for the prediction of the removal of MB with coefficient of regression (R<sup>2</sup>) values of 0.9174, 0.9742, and 0.9999, mean square error (MSE) values of 181.71, 94.50, and 0.00000049, and root MSE (RMSE) values of 13.48, 9.72, and 0.0007 for the RSM, ANN, and ANFIS, respectively. The ANFIS model was found to be more effective in the prediction of MB sorption to SDPKB than the other models (ANFIS > ANN > RSM), and it was highly applicable in the sorption process. This study has revealed that the SDPKB can serve as a better biosorbent for MB adsorption. Therefore, this study will serve as a first reference point data that will be of great assistance in industrial effluent management as well as decision-making on the adoption of statistical and machine learning models for adsorption study.</div></div>","PeriodicalId":371,"journal":{"name":"Journal of Molecular Liquids","volume":"429 ","pages":"Article 127547"},"PeriodicalIF":5.3000,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Molecular Liquids","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167732225007147","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}

引用次数: 0

Abstract

In this study, methylene blue (MB) dye adsorption to synthesised sulfonated date palm kernel biochar (SDPKB) was predicted and optimized using statistical-based regression approach (response surface methodology (RSM), machine-learning algorithms (artificial-neural-network (ANN), and adaptive-neuro-fuzzy-inference-system (ANFIS) models), and quantum chemistry calculations performed using density function theory (DFT) to link the electrical properties of the MB dye with the experimental findings. The percentage (%) of MB dye removed using SDPKB was found to be proportional to the biosorbent dosage and interaction time and inversely proportional to the solution pH and initial concentrations based on different used models results. It was observed that these models were accurate and comparable for the prediction of the removal of MB with coefficient of regression (R²) values of 0.9174, 0.9742, and 0.9999, mean square error (MSE) values of 181.71, 94.50, and 0.00000049, and root MSE (RMSE) values of 13.48, 9.72, and 0.0007 for the RSM, ANN, and ANFIS, respectively. The ANFIS model was found to be more effective in the prediction of MB sorption to SDPKB than the other models (ANFIS > ANN > RSM), and it was highly applicable in the sorption process. This study has revealed that the SDPKB can serve as a better biosorbent for MB adsorption. Therefore, this study will serve as a first reference point data that will be of great assistance in industrial effluent management as well as decision-making on the adoption of statistical and machine learning models for adsorption study.

查看原文本刊更多论文

利用统计回归、机器学习方法和DFT研究预测磺化椰枣仁生物炭对亚甲基蓝染料的吸附

在这项研究中，利用基于统计的回归方法（响应面法（RSM））、机器学习算法（人工神经网络（ANN）和自适应神经模糊推理系统（ANFIS）模型）预测和优化亚甲基蓝（MB）染料对合成磺化枣棕榈仁生物炭（SDPKB）的吸附，并利用密度泛函理论（DFT）进行量子化学计算，将亚甲基蓝染料的电学性质与实验结果联系起来。根据不同使用的模型结果，发现使用SDPKB去除MB染料的百分比（%）与生物吸附剂用量和相互作用时间成正比，与溶液pH和初始浓度成反比。RSM、ANN和ANFIS的回归系数（R2）分别为0.9174、0.9742和0.9999，均方误差（MSE）分别为181.71、94.50和0.00000049，均方根误差（RMSE）分别为13.48、9.72和0.0007，具有较好的准确性和可比性。发现ANFIS模型比其他模型更有效地预测MB对SDPKB的吸附(ANFIS >；安比;RSM)，在吸附过程中具有很高的适用性。研究表明，SDPKB是一种较好的吸附MB的生物吸附剂。因此，本研究将作为第一个参考点数据，对工业废水管理以及采用统计和机器学习模型进行吸附研究的决策有很大的帮助。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Molecular Liquids 化学-物理：原子、分子和化学物理

CiteScore

10.30

自引率

16.70%

发文量

2597

审稿时长

78 days

期刊介绍： The journal includes papers in the following areas: – Simple organic liquids and mixtures – Ionic liquids – Surfactant solutions (including micelles and vesicles) and liquid interfaces – Colloidal solutions and nanoparticles – Thermotropic and lyotropic liquid crystals – Ferrofluids – Water, aqueous solutions and other hydrogen-bonded liquids – Lubricants, polymer solutions and melts – Molten metals and salts – Phase transitions and critical phenomena in liquids and confined fluids – Self assembly in complex liquids.– Biomolecules in solution The emphasis is on the molecular (or microscopic) understanding of particular liquids or liquid systems, especially concerning structure, dynamics and intermolecular forces. The experimental techniques used may include: – Conventional spectroscopy (mid-IR and far-IR, Raman, NMR, etc.) – Non-linear optics and time resolved spectroscopy (psec, fsec, asec, ISRS, etc.) – Light scattering (Rayleigh, Brillouin, PCS, etc.) – Dielectric relaxation – X-ray and neutron scattering and diffraction. Experimental studies, computer simulations (MD or MC) and analytical theory will be considered for publication; papers just reporting experimental results that do not contribute to the understanding of the fundamentals of molecular and ionic liquids will not be accepted. Only papers of a non-routine nature and advancing the field will be considered for publication.