Machine learning and modelling approach for removing methylene blue from aqueous solutions: Optimization, kinetics and thermodynamics studies

IF 5.5 3区工程技术 Q1 ENGINEERING, CHEMICAL

Journal of the Taiwan Institute of Chemical Engineers Pub Date : 2025-01-01 DOI:10.1016/j.jtice.2024.105361

Sheetal Kumari , Seema Singh , Shang-Lien Lo , Pinki Sharma , Smriti Agarwal , Manoj Chandra Garg

{"title":"Machine learning and modelling approach for removing methylene blue from aqueous solutions: Optimization, kinetics and thermodynamics studies","authors":"Sheetal Kumari , Seema Singh , Shang-Lien Lo , Pinki Sharma , Smriti Agarwal , Manoj Chandra Garg","doi":"10.1016/j.jtice.2024.105361","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>The present study employs the <em>Juglans Regia</em>, a natural adsorbent, to investigate its efficiency in methylene blue (MB) removal from aqueous solutions. Advanced techniques like Artificial Neural Networks (ANN) and Response Surface Methodologies (RSM) are applied to model and predict the adsorptive behaviour of MB using <em>Juglans Regia</em> adsorbent. Different characterization techniques are utilised to understand the morphology and structure of the catalyst to provide insights into its potential adsorption capabilities.</div></div><div><h3>Methods</h3><div>The study uses ANN and RSM for predictive modelling, enabling a comprehensive comparison of their effectiveness in describing MB adsorption onto <em>Juglans Regia</em>. Kinetic analysis employing pseudo-2nd order kinetics and isotherm studies based on the Langmuir isotherm model are conducted to understand the kinetics and equilibrium behaviour of the adsorption process. The thermodynamics of the adsorption process are investigated to ascertain the spontaneity and exothermic nature of MB dye removal by <em>Juglans Regia</em>.</div></div><div><h3>Significant Findings</h3><div>Both ANN and RSM models are predicted the high adsorption efficiency, reaching up to 94.6 and 93.2 %, demonstrating the effectiveness of <em>Juglans Regia</em> as an adsorbent for MB removal. RSM and ANN models are strongly associated with R<sup>2</sup> values of 0.9117 and 0.9373, respectively. Low Root mean square error (RMSE) and Hybrid fractional error function (HYBRID) computed error function values revealed good agreement between experimental results and model predictions. The study successfully validates the optimization process, leading to the maximum predicted adsorption efficiency values, and providing insights into optimal conditions for efficient MB removal. Thermodynamic analysis confirms that the adsorption process is exothermic and spontaneous, further supporting the potential of <em>Juglans Regia</em> in wastewater remediation of organic pollutants.</div></div>","PeriodicalId":381,"journal":{"name":"Journal of the Taiwan Institute of Chemical Engineers","volume":"166 ","pages":"Article 105361"},"PeriodicalIF":5.5000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Taiwan Institute of Chemical Engineers","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1876107024000208","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background

The present study employs the Juglans Regia, a natural adsorbent, to investigate its efficiency in methylene blue (MB) removal from aqueous solutions. Advanced techniques like Artificial Neural Networks (ANN) and Response Surface Methodologies (RSM) are applied to model and predict the adsorptive behaviour of MB using Juglans Regia adsorbent. Different characterization techniques are utilised to understand the morphology and structure of the catalyst to provide insights into its potential adsorption capabilities.

Methods

The study uses ANN and RSM for predictive modelling, enabling a comprehensive comparison of their effectiveness in describing MB adsorption onto Juglans Regia. Kinetic analysis employing pseudo-2nd order kinetics and isotherm studies based on the Langmuir isotherm model are conducted to understand the kinetics and equilibrium behaviour of the adsorption process. The thermodynamics of the adsorption process are investigated to ascertain the spontaneity and exothermic nature of MB dye removal by Juglans Regia.

Significant Findings

Both ANN and RSM models are predicted the high adsorption efficiency, reaching up to 94.6 and 93.2 %, demonstrating the effectiveness of Juglans Regia as an adsorbent for MB removal. RSM and ANN models are strongly associated with R² values of 0.9117 and 0.9373, respectively. Low Root mean square error (RMSE) and Hybrid fractional error function (HYBRID) computed error function values revealed good agreement between experimental results and model predictions. The study successfully validates the optimization process, leading to the maximum predicted adsorption efficiency values, and providing insights into optimal conditions for efficient MB removal. Thermodynamic analysis confirms that the adsorption process is exothermic and spontaneous, further supporting the potential of Juglans Regia in wastewater remediation of organic pollutants.

Abstract Image

查看原文本刊更多论文

从水溶液中去除亚甲基蓝的机器学习和建模方法：优化、动力学和热力学研究

背景本研究采用一种天然吸附剂--王不留行树（Juglans Regia）来研究其从水溶液中去除亚甲基蓝（MB）的效率。研究采用了人工神经网络（ANN）和响应面方法（RSM）等先进技术来建模和预测瑞香树吸附剂对甲基溴的吸附行为。该研究使用 ANN 和 RSM 进行预测建模，从而能够全面比较这两种方法在描述甲基溴在胡枝子吸附上的有效性。为了解吸附过程的动力学和平衡行为，采用伪 2 阶动力学进行了动力学分析，并根据 Langmuir 等温线模型进行了等温线研究。对吸附过程的热力学进行了研究，以确定 Juglans Regia 去除甲基溴染料的自发性和放热性。重要发现ANN 和 RSM 模型都预测出了较高的吸附效率，分别达到 94.6% 和 93.2%，这表明 Juglans Regia 作为一种吸附剂去除甲基溴的有效性。RSM 模型和 ANN 模型的 R2 值分别为 0.9117 和 0.9373，具有很强的相关性。低均方根误差（RMSE）和混合分数误差函数（HYBRID）计算出的误差函数值表明，实验结果与模型预测之间具有良好的一致性。这项研究成功地验证了优化过程，使预测的吸附效率值达到最大，并为高效去除甲基溴提供了最佳条件。热力学分析证实，吸附过程是放热和自发的，这进一步证明了 Juglans Regia 在废水处理有机污染物方面的潜力。

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 the Taiwan Institute of Chemical Engineers 工程技术-工程：化工

CiteScore

9.10

自引率

14.00%

发文量

362

审稿时长

35 days

期刊介绍： Journal of the Taiwan Institute of Chemical Engineers (formerly known as Journal of the Chinese Institute of Chemical Engineers) publishes original works, from fundamental principles to practical applications, in the broad field of chemical engineering with special focus on three aspects: Chemical and Biomolecular Science and Technology, Energy and Environmental Science and Technology, and Materials Science and Technology. Authors should choose for their manuscript an appropriate aspect section and a few related classifications when submitting to the journal online.