基于机器学习根据合成条件预测金属有机框架的结构特性

张华方; 潘春键; 季怡浩; 梁琦; 钟隆春

doi:10.12434/j.issn.2097-2547.20250365

您当前的位置：

首页 >

文章列表页 >

基于机器学习根据合成条件预测金属有机框架的结构特性

更新时间：2026-01-12

- 基于机器学习根据合成条件预测金属有机框架的结构特性
- Prediction of structural properties of metal-organic frameworks based on synthesis conditions by machine learning
- 低碳化学与化工 2026: 1-12.
- 作者机构：
  
  1.北京工商大学轻工科学与工程学院，北京 100048
  2.上海电力大学自动化工程学院，上海 200090
  3.华电青岛环保技术有限公司，山东青岛 266000
- 作者简介：
  
  张华方（2000—），硕士研究生，研究方向为材料化学，E-mail：15235755838@163.com。
  潘春键（1986—），博士，讲师，研究方向为物理信息机器学习，E-mail：cjpan2019@outlook.com；
  钟隆春（1990—），博士，讲师，研究方向为重金属污染监测与控制技术，E-mail：zhonglongchun@btbu.edu.cn。
- 基金信息：
  
  北京工商大学青年教师培育专项计划(RFYS2025)
- DOI：10.12434/j.issn.2097-2547.20250365
  中图分类号： TB303;TQ424
- 收稿：2025-09-05，
  
  修回：2025-10-15，
  
  网络出版：2026-01-12，
- 稿件说明：
移动端阅览
张华方,潘春键,季怡浩等.基于机器学习根据合成条件预测金属有机框架的结构特性[J].低碳化学与化工,

ZHANG Huafang,PAN Chunjian,JI Yihao,et al.Prediction of structural properties of metal-organic frameworks based on synthesis conditions by machine learning[J].Low-Carbon Chemistry and Chemical Engineering,
张华方,潘春键,季怡浩等.基于机器学习根据合成条件预测金属有机框架的结构特性[J].低碳化学与化工, DOI：10.12434/j.issn.2097-2547.20250365.

ZHANG Huafang,PAN Chunjian,JI Yihao,et al.Prediction of structural properties of metal-organic frameworks based on synthesis conditions by machine learning[J].Low-Carbon Chemistry and Chemical Engineering, DOI：10.12434/j.issn.2097-2547.20250365.

摘要

金属有机框架（MOFs）是一种重要的晶体结构多孔材料，在诸多领域具有广泛的应用前景。MOFs特定的应用性能与结构特性高度相关，且高度依赖合成条件，其逆向设计存在较大困难。为基于合成条件准确预测MOFs结构特性，基于MOFs合成数据库，开发了涵盖金属前驱体、有机配体、溶剂及反应条件等多维度特征的机器学习模型。通过特征优选与模型构建，对比了CatBoost、支持向量机及神经网络3种模型的预测性能。结果表明，基于SynMOF数据库的CatBoost模型预测效果最佳，其对比表面积和孔体积预测的决定系数分别达到0.71和0.76。有机配体是影响结构特性的最关键因素，其贡献度超过50%。以所构建机器学习模型预测ZIF-8时，模型对比表面积和孔体积的预测值接近实验值，相对误差分别为-7.0%和-1.0%。

Abstract

Metal organic frameworks (MOFs) are important crystalline porous materials with broad application prospects in many fields. The specific application performance and structural characteristics of MOFs are highly correlated and heavily dependent on synthesis conditions

making their inverse design considerably challenging. To accurately predict the structural properties of MOFs based on synthesis conditions

machine learning models incorporating multi-dimensional features including metal precursors

organic ligands

solvents and reaction conditions was developed using the MOF synthesis database. Through feature selection and model construction

the predictive performances of three models (CatBoost

support vector machine and neural network) were compared. The results show that the CatBoost model based on the SynMOF database achieves the best prediction performance

with coefficients of determination for specific surface area and pore volume predictions reaching 0.71 and 0.76

respectively. Organic ligands are identified as the most critical factor influencing structural properties

with the contribution exceeding 50%. When applying the constructed machine learning model to predict ZIF-8

the predicted values for specific surface area and pore volume are close to the experimental values

with relative errors of -7.0% and -1.0%

respectively.

关键词

Keywords

references

DEMIR H , DAGLAR H , GULBALKAN H C , et al . Recent advances in computational modeling of MOFs: From molecular simulations to machine learning [J ] . Coordination Chemistry Reviews , 2023 , 484 : 215112 .

AHMED A , SIEGEL D J . Predicting hydrogen storage in MOFs via machine learning [J ] . Patterns , 2021 , 2 : 100291 .

于天鑫 , 彭璇 . 基于机器学习高通量筛选吸附甲烷的金属有机框架材料 [J ] . 北京化工大学学报（自然科学版） , 2021 , 48 ( 2 ): 100 - 107 .

YU T X , PENG X . High throughput screening of metal-organic framework materials based on machine learning [J ] . Journal of Beijing University of Chemical Technology (Natural Science Edition) , 2021 , 48 ( 2 ): 100 - 107 .

于萍 , 马馥颖 , 刘子晴 . 提高金属有机框架电催化材料性能策略 [J ] . 塑料科技 , 2025 , 53 ( 2 ): 174 - 179 .

YU P , MA F Y , LIU Z Q . Performance improving strategies of metal-organic frame electrocatalytic materials [J ] . Plastics Science and Technology , 2025 , 53 ( 2 ): 174 - 179 .

刘琪 , 黄剑 , 汪力 , 等 . 金属有机框架材料（MOFs）催化二氧化碳转化的研究进展 [J ] . 现代化工 , 2025 , 45 ( 4 ): 69 - 73 .

LIU Q , HUANG J , WANG L , et al . Research progress on metal-organic framework materials for catalyzing carbon dioxide conversion [J ] . Modern Chemical Industry , 2025 , 45 ( 4 ): 69 - 73 .

韩竹 , 杨欢 , 苏晓英 . 金属有机框架材料在药物递送领域的应用 [J ] . 当代化工研究 , 2025 , ( 2 ): 133 - 135 .

HAN Z , YANG H , SU X Y . Application of metal organic framework materials in the field of drug delivery [J ] . Modern Chemical Research , 2025 , ( 2 ): 133 - 135 .

WU M X , YANG Y W . Metal-organic framework (MOF)‐based drug/cargo delivery and cancer therapy [J ] . Advanced Materials , 2017 , 29 ( 23 ): 1606134 .

INDRA A , SONG T , PAIK U . Metal organic framework derived materials: Progress and prospects for the energy conversion and storage [J ] . Advanced Materials , 2018 , 30 ( 39 ): 1705146 .

AFRIN S , KHANM W , HAQUE E , et al . Recent advances in the tuning of the organic framework materials: The selections of ligands, reaction conditions, and post-synthesis approaches [J ] . Journal of Colloid and Interface Science , 2022 , 623 : 378 - 404 .

高明亮 , 薛天威 , 李江南 , 等 . 金属有机框架材料的合成、表征与性能 [J/OL ] . 科学通报 : 1 - 30 [ 2025-10-04 ] . DOI: 10.1360/TB-2024-1353 http://dx.doi.org/10.1360/TB-2024-1353 .

GAO M L , XUE T W , LI J N , et al . The synthesis, characterization and applications of metal-organic frameworks (in Chinese) [J ] . Chinese Science Bulletin: 1 - 30 [ 2025-10-04 ] . DOI: 10.1360/TB-2024-1353 http://dx.doi.org/10.1360/TB-2024-1353 .

钱旭 , 田子奇 . 材料基因方法在材料设计中的应用 [J ] . 数据与计算发展前沿 , 2020 , 2 ( 1 ): 128 - 141 .

QIAN X , TIAN Z Q . The application of materials genome approach in materials design [J ] . Frontiers of Data & Computing , 2020 , 2 ( 1 ): 128 - 141 .

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 M X , WANG S T , XU D P . Prediction of adsorption performance of MOFs for heavy metals in water based on machine learning [J ] . China Environmental Science , 2023 , 43 ( 5 ): 2319 - 2327 .

JABLONKA K M , ONGARI D , MOOSAVI S M , et al . Big-data science in porous materials: Materials genomics and machine learning [J ] . Chemical Reviews , 2020 , 120 ( 16 ): 8066 - 8129 .

CHONG S Y , LEE S W , KIM B J , et al . Applications of machine learning in metal-organic frameworks [J ] . Coordination Chemistry Reviews , 2020 , 423 : 213487 .

BAILEY T , JACKSON A , BERBECER A , et al . Gradient boosted machine learning model to predict H 2 , CH 4 , and CO 2 uptake in metal-organic frameworks using experimental data [J ] . Journal of Chemical Information and Modeling , 2023 , 63 ( 14 ): 4545 - 4551 .

WANG R H , ZOU Y R , ZHANG C C , et al . Combining crystal graphs and domain knowledge in machine learning to predict metal-organic frameworks performance in methane adsorption [J ] . Microporous and Mesoporous Materials , 2022 , 331 : 111666 .

JIA H X , YAO Y C , ZHAO J T , et al . A novel two-dimensional nickel phthalocyanine-based metal-organic framework for highly efficient water oxidation catalysis [J ] . Journal of Materials Chemistry A , 2018 , 6 ( 3 ): 1188 - 1195 .

HUANG X , SHENG P , TU Z , et al . A two-dimensional π-d conjugated coordination polymer with extremely high electrical conductivity and ambipolar transport behaviour [J ] . Nature Communications , 2015 , 6 : 7408 .

MOOSAVI S M , CHIDAMBARAM A , TALIRZ L , et al . Capturing chemical intuition in synthesis of metal-organic frameworks [J ] . Nature Communications , 2019 , 10 : 539 .

LIN J , BAN T , LI T , et al . Machine-learning-assisted intelligent synthesis of UiO‐66(Ce): Balancing the trade-off between structural defects and thermal stability for efficient hydrogenation of dicyclopentadiene [J ] . Materials Genome Engineering Advances , 2024 , 2 : e61 .

CHEN P , TANG Z , ZENG Z M , et al . Machine-learning-guided morphology engineering of nanoscale metal-organic frameworks [J ] . Matter , 2020 , 2 ( 6 ): 1651 - 1666 .

MORIKAWA Y , SHIN K , KUBOUCHI M , et al . Prediction of specific surface area of metal-organic frameworks by graph kernels [J ] . The Journal of Supercomputing , 2024 , 80 : 13027 - 13047 .

BATRA R , CHEN C , EVANS T G , et al . Prediction of water stability of metal-organic frameworks using machine learning [J ] . Nature Machine Intelligence , 2020 , 2 ( 11 ): 704 - 710 .

PÉTUYA R , DURDY S , ANTYPOV D , et al . Machine‐learning prediction of metal-organic framework guest accessibility from linker and metal chemistry [J ] . Angewandte Chemie International Edition , 2022 , 134 ( 14 ): e202114573 .

JALALI M , WONANKE A D D , WÖLL C . MOFGalaxyNet: A social network analysis for predicting guest accessibility in metal-organic frameworks utilizing graph convolutional networks [J ] . Journal of Cheminformatics , 2023 , 15 : 94 .

LARIONOV K P , EVTUSHOK V Y . From synthesis conditions to UiO-66 properties: Machine learning approach [J ] . Chemistry of Materials , 2024 , 36 ( 9 ): 4291 - 4302 .

LUO Y , BAG S , ZAREMBA O , et al . MOF synthesis prediction enabled by automatic data mining and machine learning [J ] . Angewandte Chemie International Edition , 2022 , 61 ( 16 ): e202200242 .

PARK H , KANG Y , CHOE W , et al . Mining insights on metal-organic framework synthesis from scientific literature texts [J ] . Journal of Chemical Information and Modeling , 2022 , 62 ( 5 ): 1190 - 1198 .

GLASBY L T , GUBSCH K , BENCE R , et al . DigiMOF: A database of metal-organic framework synthesis information generated via text mining [J ] . Chemistry of Materials , 2023 , 35 ( 11 ): 4510 - 4524 .

SWAIN M C , COLE J M . ChemDataExtractor: A toolkit for automated extraction of chemical information from the scientific literature [J ] . Journal of Chemical Information and Modeling , 2016 , 56 ( 10 ): 1894 - 1904 .

KIM S , CHEN J , CHENG T , et al . PubChem 2023 update [J ] . Nucleic Acids Research , 2023 , 51 ( 1 ): 1373 - 1380 .

MORIWAKI H , TIAN Y S , KAWASHITA N , et al . Mordred: A molecular descriptor calculator [J ] . Journal of Cheminformatics , 2018 , 10 : 4 .

WEININGER D . SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules [J ] . Journal of Chemical Information and Computer Sciences , 1988 , 28 ( 1 ): 31 - 36 .

CHANDRASHEKAR G , SAHIN F . A survey on feature selection methods [J ] . Computers & Electrical Engineering , 2014 , 40 ( 1 ): 16 - 28 .

PRIYATNO A M , WIDIYANINGTYAS T . A systematic literature review: Recursive feature elimination algorithms [J ] . Jurnal Ilmiah Teknologi dan Informasi , 2024 , 9 ( 2 ): 196 - 207 .

DOROGUSH A V , ERSHOV V , GULIN A . CatBoost: Gradient boosting with categorical features support [C ] //BENGIO S, WALLACH H M. Proceedings of the 32nd International Conference on Neural Information Processing Systems . Red Hook, NewYork : Curran Associates Inc. , 2018 : 6639 - 6649 .

BRYANT M L , GARBER F D . SVM classifier applied to the MSTAR public data set [C ] //SPIE. Proceedings of SPIE . Orlando : SPIE , 1999 : 355 - 360 .

BEBIS G , GEORGIOPOULOS M . Feed-forward neural networks [J ] . IEEE Potentials , 1994 , 13 ( 4 ): 27 - 31 .

AWAD M , KHANNA R . Support Vector Regression [M ] //AWAD M, KHANNA R. Efficient Learning Machines . Berkeley, CA : Academic Press , 2015 : 67 - 80 .

HAN S J , CAO Q B , HAN M . Parameter selection in SVM with RBF kernel function [C ] //IEEE. Proceedings of the World Automation Congress . Puerto Vallarta : IEEE , 2012 : 1 - 4 .

NAGELKERKE N J D . A note on a general definition of the coefficient of determination [J ] . Biometrika , 1991 , 78 ( 3 ): 691 - 692 .

WILLMOTT C , MATSUURA K . Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance [J ] . Climate Research , 2005 , 30 ( 1 ): 79 - 82 .

LUNDBERG S M , LEE S I . A unified approach to interpreting model predictions [C ] //LUXBURG U V, GUYON I. Proceedings of the 31st International Conference on Neural Information Processing Systems . Red Hook, NewYork : Curran Associates Inc. , 2017 : 4765 - 4774 .

PARK K S , NI Z , CÔTÉ A P , et al . Exceptional chemical and thermal stability of zeolitic imidazolate frameworks [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2006 , 103 ( 27 ): 10186 - 10191 .

LEE Y R , JANG M S , CHO H Y , et al . ZIF-8: A comparison of synthesis methods [J ] . Chemical Engineering Journal , 2015 , 271 : 276 - 280 .

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向轻烃分离的MOF材料设计：多尺度计算与机器学习应用进展

基于机器学习的CO₂催化加氢制航空煤油筒式反应器数学模拟分析与优化

基于IAO-PNN模型的天然气水合物生成条件预测研究