Enhanced Prediction of CO2–Brine Interfacial Tension at Varying Temperature Using a Multibranch-Structure-Based Neural Network Approach

IF 3.7 2区 化学 Q2 CHEMISTRY, MULTIDISCIPLINARY
Jiarui Fan, Yimin Jiang, Zhiqiang Fan, Chunlong Yang, Kun He, Dayong Wang
{"title":"Enhanced Prediction of CO2–Brine Interfacial Tension at Varying Temperature Using a Multibranch-Structure-Based Neural Network Approach","authors":"Jiarui Fan, Yimin Jiang, Zhiqiang Fan, Chunlong Yang, Kun He, Dayong Wang","doi":"10.1021/acs.langmuir.4c03366","DOIUrl":null,"url":null,"abstract":"Interfacial tension (<i>IFT</i><sub><i>C–B</i></sub>) between CO<sub>2</sub> and brine depends on chemical components in multiphase systems, intricately evolving with a change in temperature. In this study, we developed a convolutional neural network with a multibranch structure (MBCNN), which, in combination with a compiled data set containing measurement data of 1716 samples from 13 available literature sources at wide temperature and pressure ranges (273.15–473.15 K and 0–70 MPa), was used to quantitatively explore the correlation of various chemical components with <i>IFT</i><sub><i>C–B</i></sub> at varying temperature, aiming to achieve accurate predictions of <i>IFT</i><sub><i>C–B</i></sub> under complex conditions. Our multibranch neural network analysis yielded some important insights: (1) Leveraging the convolutional and multibranch structure, MBCNN effectively mitigates the adverse effects of sparse matrices resulting from the absence of certain basic components, exhibiting higher prediction accuracy particularly for low <i>IFT</i><sub><i>C–B</i></sub> scenarios (MAE = 0.47, and R<sup>2</sup> = 0.9921) than other AI models. (2) The multibranch structure allows MBCNN to additionally capture the interattribute relationship between temperature and each chemical component. Such interattribute relationships are quantitatively correlated with <i>IFT</i><sub><i>C–B</i></sub>, demonstrating that varying temperature significantly influences the dependence of <i>IFT</i><sub><i>C–B</i></sub> on chemical components in gas and brine by causing the variation in their solubility. Specifically, the ratio of <i>IFT</i><sub><i>C–B</i></sub> to the molality of monovalent cations (Na<sup>+</sup> and K<sup>+</sup>) and bivalent cations (Ca<sup>2+</sup> and Mg<sup>2+</sup>) in brine, as well as to the mole fraction of non-CO<sub>2</sub> components (CH<sub>4</sub> and N<sub>2</sub>) in the gas phase, varies with increasing temperature, approximately following a quadratic function. (3) By formulating the effect of each attribute on <i>IFT</i><sub><i>C–B</i></sub> and quantifying their respective weight, we derived a new piecewise function for predicting <i>IFT</i><sub><i>C–B</i></sub> at three temperature intervals (<i>T</i> ≤ 293.15 K, 293.15 K &lt; <i>T</i> ≤ 324.4 K, and <i>T</i> &gt; 324.4 K), with high prediction performance (MAE = 2.3672, R<sup>2</sup> = 0.9263) across a wide temperature range in saline aquifers.","PeriodicalId":50,"journal":{"name":"Langmuir","volume":"53 1","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Langmuir","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1021/acs.langmuir.4c03366","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Interfacial tension (IFTC–B) between CO2 and brine depends on chemical components in multiphase systems, intricately evolving with a change in temperature. In this study, we developed a convolutional neural network with a multibranch structure (MBCNN), which, in combination with a compiled data set containing measurement data of 1716 samples from 13 available literature sources at wide temperature and pressure ranges (273.15–473.15 K and 0–70 MPa), was used to quantitatively explore the correlation of various chemical components with IFTC–B at varying temperature, aiming to achieve accurate predictions of IFTC–B under complex conditions. Our multibranch neural network analysis yielded some important insights: (1) Leveraging the convolutional and multibranch structure, MBCNN effectively mitigates the adverse effects of sparse matrices resulting from the absence of certain basic components, exhibiting higher prediction accuracy particularly for low IFTC–B scenarios (MAE = 0.47, and R2 = 0.9921) than other AI models. (2) The multibranch structure allows MBCNN to additionally capture the interattribute relationship between temperature and each chemical component. Such interattribute relationships are quantitatively correlated with IFTC–B, demonstrating that varying temperature significantly influences the dependence of IFTC–B on chemical components in gas and brine by causing the variation in their solubility. Specifically, the ratio of IFTC–B to the molality of monovalent cations (Na+ and K+) and bivalent cations (Ca2+ and Mg2+) in brine, as well as to the mole fraction of non-CO2 components (CH4 and N2) in the gas phase, varies with increasing temperature, approximately following a quadratic function. (3) By formulating the effect of each attribute on IFTC–B and quantifying their respective weight, we derived a new piecewise function for predicting IFTC–B at three temperature intervals (T ≤ 293.15 K, 293.15 K < T ≤ 324.4 K, and T > 324.4 K), with high prediction performance (MAE = 2.3672, R2 = 0.9263) across a wide temperature range in saline aquifers.

Abstract Image

基于多分支结构的神经网络方法对变温co2 -盐水界面张力的增强预测
CO2和盐水之间的界面张力(IFTC-B)取决于多相体系中的化学成分,并随着温度的变化而复杂地演变。在本研究中,我们构建了一个多分支结构卷积神经网络(MBCNN),结合13个文献来源的1716个样品在宽温度和压力范围(273.15-473.15 K和0-70 MPa)的测量数据集,定量探讨了不同温度下各种化学成分与IFTC-B的相关性,旨在实现复杂条件下IFTC-B的准确预测。我们的多分支神经网络分析得出了一些重要的见解:(1)利用卷积和多分支结构,MBCNN有效地减轻了稀疏矩阵由于缺乏某些基本成分而产生的不利影响,特别是在低IFTC-B场景下(MAE = 0.47, R2 = 0.9921)比其他人工智能模型具有更高的预测精度。(2)多分支结构允许MBCNN额外捕获温度与每种化学成分之间的属性间关系。这种属性间关系与IFTC-B进行了定量关联,表明温度的变化通过引起IFTC-B溶解度的变化,显著影响了IFTC-B对气体和盐水中化学成分的依赖性。具体来说,IFTC-B与盐水中一价阳离子(Na+和K+)和二价阳离子(Ca2+和Mg2+)的摩尔浓度之比,以及与气相中非co2组分(CH4和N2)的摩尔分数之比,随着温度的升高而变化,近似遵循二次函数。(3)通过阐述各属性对IFTC-B的影响,并量化其权重,推导出预测三个温度区间(T≤293.15 K, 293.15 K <;T≤324.4 K, T >;324.4 K),在较宽的温度范围内具有较高的预测性能(MAE = 2.3672, R2 = 0.9263)。
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
Langmuir
Langmuir 化学-材料科学:综合
CiteScore
6.50
自引率
10.30%
发文量
1464
审稿时长
2.1 months
期刊介绍: Langmuir is an interdisciplinary journal publishing articles in the following subject categories: Colloids: surfactants and self-assembly, dispersions, emulsions, foams Interfaces: adsorption, reactions, films, forces Biological Interfaces: biocolloids, biomolecular and biomimetic materials Materials: nano- and mesostructured materials, polymers, gels, liquid crystals Electrochemistry: interfacial charge transfer, charge transport, electrocatalysis, electrokinetic phenomena, bioelectrochemistry Devices and Applications: sensors, fluidics, patterning, catalysis, photonic crystals However, when high-impact, original work is submitted that does not fit within the above categories, decisions to accept or decline such papers will be based on one criteria: What Would Irving Do? Langmuir ranks #2 in citations out of 136 journals in the category of Physical Chemistry with 113,157 total citations. The journal received an Impact Factor of 4.384*. This journal is also indexed in the categories of Materials Science (ranked #1) and Multidisciplinary Chemistry (ranked #5).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信