Screening of low-temperature hydrogen storage MOFs via data-driven approaches and material fingerprints

CAI Jiachun; HUANG He; TIAN Jitong; GONG Lingtao; HUANG Xiaoshan; LIN Yingtong; LI Shuhua; LIANG Hong; SHI Junyue; WU Yufang; QIAO Zhiwei

doi:10.11949/0438-1157.20260495

您当前的位置：

首页 >

文章列表页 >

Screening of low-temperature hydrogen storage MOFs via data-driven approaches and material fingerprints

更新时间：2026-05-19

- Screening of low-temperature hydrogen storage MOFs via data-driven approaches and material fingerprints
- CIESC Journal (2026)
- 作者机构：
  
  广州大学化学化工学院，广东广州 510006
- 作者简介：
- 基金信息：
- DOI：10.11949/0438-1157.20260495
  CLC： TP181;TG174.42
- Received：10 April 2026，
  
  Revised：2026-05-18，
  
  Accepted：19 May 2026，
- 稿件说明：
移动端阅览
CAI Jiachun, HUANG He, TIAN Jitong, et al. Screening of low-temperature hydrogen storage MOFs via data-driven approaches and material fingerprints[J/OL]. CIESC Journal, 2026.
DOI：

CAI Jiachun, HUANG He, TIAN Jitong, et al. Screening of low-temperature hydrogen storage MOFs via data-driven approaches and material fingerprints[J/OL]. CIESC Journal, 2026. DOI： 10.11949/0438-1157.20260495.

摘要

为利用大数据精准分析与开发高性能低温储氢吸附材料，本研究利用MACCS指纹将数万个已合成金属-有机框架（Metal-Organic Framework

MOF）数据化，基于SHAP技术和5种机器学习算法构建预测模型，结合高通量分子模拟结果，揭示了MOF材料在低温高压环境（159K、30bar）存储氢气的构效关系，其中分类提升算法（Categorical Boosting

CatBoost）的预测效果最好（

可达0.951）。MOF材料指纹对工作容量（Δ

）贡献度的研究结果表明，第99、62、45、65号指纹是提升MOF低温储氢吸附能力的关键子结构，其中第65号指纹代表芳香碳氮杂环（如咪唑、吡啶等），证实当MOF性能已达到TOP10%时，通过引入芳香碳氮杂环，可在低温下局部形成“类氢键”，再次突破MOF储氢性能（可达TOP5%）。

Abstract

This study employs a data-driven strategy to enable precise analysis and the development of high-performance cryogenic hydrogen storage adsorbent materials. In this work

thousands of Computation-Ready Experimental MOF (CoRE-MOF) were digitized using molecular fingerprints. Predictive models were constructed based on SHAP technology and five machine learning algorithms

and integrated with high-throughput molecular simulation results to elucidate the structure–property relationship of MOF materials for hydrogen storage under cryogenic high-pressure conditions(159K and 30bar). Among the models

the categorical boosting algorithm(CatBoost) achieved the best predictive performance

with

of 0.951. The results indicate that three descriptors—a

dsorption heat (

)

density (

)

and porosity (

)—are critical for enhancing material adsorption performance. Specifically

when

15kJ·mol

-1

1000kg·m

-3

and

0.7

MOFs exhibit a high level of adsorption performance. Analysis of the variation in RI across different datasets reveals that as material performance reaches the top 20% or top 10%

the influence of descriptors such as

on MOF adsorption performance gradually diminishes

while the contribution of molecular fingerprints to Δ

becomes increasingly significant. Therefore

this study employs SHAP analysis to interpret the model constructed using the CatBoost algorithm

quantifying the contribution of each molecular fingerprint to cryogenic hydrogen storage performance (Δ

). The final results identify fingerprints 99

and 65 as key substructures for enhancing hydrogen storage capacity in MOFs. Among these

fingerprint 65 corresponds to aromatic nitrogen-containing heterocycles (such as imidazole

pyridine)

confirming that when MOF performance reaches the top 10%

the introduction of such aromatic nitrogen heterocycles facilitates the formation of local hydrogen bond-like interactions under cryogenic conditions

further boosting hydrogen storage performance to the top 5%. Through this data-driven strategy

this study precisely identifies the key substructures governing the cryogenic hydrogen storage performance of MOFs

laying a solid foundation for the design of high-performance cryogenic hydrogen storage materials.

关键词

Keywords

references

赵赏鑫 . “双碳” 目标下氢能产业高质量发展的管输战略与关键技术突破 [J ] . 油气储运 , 2026 , 45 ( 1 ): 1 - 11 .

Zhao S X . Pipeline transportation strategy and key technological breakthroughs for the high-quality development of the hydrogen energy industry under the “dual carbon” goals [J ] . Oil & Gas Storage and Transportation , 2026 , 45 ( 1 ): 1 - 11 .

Odenweller A , Ueckerdt F . The green hydrogen ambition and implementation gap [J ] . Nature Energy , 2025 , 10 ( 1 ): 110 - 123 .

刘佳育 , 罗纳 , 李俊辰 , 等 . 氢能航空发动机研究现状及发展制约因素 [J ] . 材料研究与应用 , 2024 , 18 ( 2 ): 299 - 308 .

Liu J Y , Luo N , Li J C , et al . Research status and development constraints of hydrogen aero engines [J ] . Materials Research and Application , 2024 , 18 ( 2 ): 299 - 308 .

屈少鹏 , 张海强 , 杨璐嘉 , 等 . 海上风电制氢输运材料的研发现状及趋势 [J ] . 材料导报 , 2026 , 40 ( 2 ): 5 - 15 .

Qu S P , Zhang H Q , Yang L J , et al . Research status and development trends of transport materials for offshore wind to hydrogen [J ] . Materials Reports , 2026 , 40 ( 2 ): 5 - 15 .

杨卫平 , 杨浩坤 , 曹树岭 , 等 . 面向氢能源安全领域的抗氢脆高强钢研究进展 [J ] . 材料研究与应用 , 2025 , 19 ( 5 ): 983 - 991, I 0005 .

Yang W P , Yang H K , Cao S L , et al . Research progress on hydrogen embrittlement-resistant high-strength steel for hydrogen energy safety [J ] . Materials Research and Application , 2025 , 19 ( 5 ): 983 - 991, I 0005 .

Zhou D S , Zheng C L , Zhang Y H , et al . An overview of RE-Mg-based alloys for hydrogen storage: Structure, properties, progresses and perspectives [J ] . Journal of Magnesium and Alloys , 2025 , 13 ( 1 ): 41 - 70 .

Kamran M , Turzyński M . Exploring hydrogen energy systems: a comprehensive review of technologies, applications, prevailing trends, and associated challenges [J ] . Journal of Energy Storage , 2024 , 96 : 112601 .

Hui Y Z , Wang M T , Guo S R , et al . Comprehensive review of development and applications of hydrogen energy technologies in China for carbon neutrality: Technology advances and challenges [J ] . Energy Conversion and Management , 2024 , 315 : 118776 .

Wang X Y , Peng P , Witman M D , et al . Technoeconomic insights into metal hydrides for stationary hydrogen storage [J ] . Advanced Science , 2025 , 12 ( 21 ): 2415736 .

Yang Z X , Wang Y Z , Lin X , et al . Vanadium induces Ni-Co MOF formation from a NiCo LDH to catalytically enhance the MgH 2 hydrogen storage performance [J ] . Journal of Magnesium and Alloys , 2025 , 13 ( 8 ): 4020 - 4031 .

Ge L X , Qiu M H , Zhu Y F , et al . Synergistic catalysis of Ru single-atoms and zeolite boosts high-efficiency hydrogen storage [J ] . Applied Catalysis B: Environmental , 2022 , 319 : 121958 .

Morandé A , Lillo P , Blanco E , et al . Modification of a commercial activated carbon with nitrogen and boron: Hydrogen storage application [J ] . Journal of Energy Storage , 2023 , 64 : 107193 .

Moghadam P Z , Chung Y G , Snurr R Q . Progress toward the computational discovery of new metal-organic framework adsorbents for energy applications [J ] . Nature Energy , 2024 , 9 ( 2 ): 121 - 133 .

Alezi D , Belmabkhout Y , Suyetin M , et al . MOF crystal chemistry paving the way to gas storage needs: aluminum-based soc-MOF for CH 4 , O 2 , and CO 2 storage [J ] . Journal of the American Chemical Society , 2015 , 137 ( 41 ): 13308 - 13318 .

Connolly B M , Madden D G , Wheatley A E H , et al . Shaping the future of fuel: monolithic metal–organic frameworks for high-density gas storage [J ] . Journal of the American Chemical Society , 2020 , 142 ( 19 ): 8541 - 8549 .

Wang P F , Teng Y , Zhu J L , et al . Review on the synergistic effect between metal-organic frameworks and gas hydrates for CH 4 storage and CO 2 separation applications [J ] . Renewable and Sustainable Energy Reviews , 2022 , 167 : 112807 .

Hu A Q , Xie Q Y , Chen L Y , et al . Hierarchically ordered meso-/ macroporous MOF-based materials for catalysis and energy applications [J ] . EnergyChem , 2024 , 6 ( 6 ): 100137 .

Wang Y , Jiang Z J , Lu W G , et al . Machine learning-assisted exploration of chemical space of MOF-5 analogs for enhanced C 2 H 6 /C 2 H 4 separation [J ] . Angewandte Chemie International Edition , 2025 , 64 ( 21 ): e202500783 .

Ma X , Sun N , Li Z G , et al . Highly flexible and self-standing covalent organic framework-metal-organic framework (COF-MOF) composite crystalline porous material (CPM) membrane for molecular separation [J ] . Advanced Functional Materials , 2024 , 34 ( 19 ): 2312203 .

Cong S Z , Zhou Y Z , Luo C L , et al . Designing metal-organic framework (MOF) membranes for isomer separation [J ] . Angewandte Chemie International Edition , 2024 , 63 ( 15 ): e202319894 .

Liu S Y , Zhang Y , Zhu F Z , et al . Mg-MOF-74 derived defective framework for hydrogen storage at above-ambient temperature assisted by Pt catalyst [J ] . Advanced Science , 2024 , 11 ( 18 ): 2401868 .

Chen J , Tang Z Z , Zhu D , et al . Charge-induced defective MOF-801 with enhanced sorption heat for efficient hydrogen storage [J ] . Small , 2025 , 21 ( 23 ): 2502860 .

Zhao H Q , Zhang H M , Wang J S , et al . Theoretical calculation and tests of hydrogen storage properties of Nano MoS 2 doped Ce-MOF-808 [J ] . Journal of Energy Storage , 2024 , 88 : 111526 .

Moghadam P Z , Li A , Wiggin S B , et al . Development of a Cambridge structural database subset: a collection of metal–organic frameworks for past, present, and future [J ] . Chemistry of Materials , 2017 , 29 ( 7 ): 2618 - 2625 .

Han Z S , Yang Y H , Rushlow J , et al . Development of the design and synthesis of metal-organic frameworks (MOFs)-from large scale attempts, functional oriented modifications, to artificial intelligence (AI) predictions [J ] . Chemical Society Reviews , 2025 , 54 ( 1 ): 367 - 395 .

Daglar H , Gulbalkan H C , Avci G , et al . Effect of metal-organic framework (MOF) database selection on the assessment of gas storage and separation potentials of MOFs [J ] . Angewandte Chemie International Edition , 2021 , 60 ( 14 ): 7828 - 37 .

程洪 , 葛美伶 , 司天宇 , 等 . 机器学习辅助金属材料力学性能预测 [J ] . 材料研究与应用 , 2023 , 17 ( 6 ): 1070 - 1077 .

Cheng H , Ge M L , Si T Y , et al . Machine learning-assisted prediction of mechanical properties of metallic materials [J ] . Materials Research and Application , 2023 , 17 ( 6 ): 1070 - 1077 .

Jang J , Gu G H , Noh J , et al . Structure-based synthesizability prediction of crystals using partially supervised learning [J ] . Journal of the American Chemical Society , 2020 , 142 ( 44 ): 18836 - 18843 .

Kim W T , Lee W G , An H E , et al . Machine learning-assisted design of metal-organic frameworks for hydrogen storage: a high-throughput screening and experimental approach [J ] . Chemical Engineering Journal , 2025 , 507 : 160766 .

Wang X Y , Breunig H M , Peng P . Broad range material-to-system screening of metal–organic frameworks for hydrogen storage using machine learning [J ] . Applied Energy , 2025 , 383 : 125346 .

胡嘉朗 , 姜明源 , 金律铭 , 等 . 机器学习辅助MOFs高通量计算筛选及气体分离研究进展 [J ] . 化工学报 , 2025 , 76 ( 5 ): 1973 - 1996 .

Hu J L , Jiang M Y , Jin L M , et al . Machine learning-assisted high-throughput computational screening of MOFs and advances in gas separation research [J ] . CIESC Journal , 2025 , 76 ( 5 ): 1973 - 1996 .

高正 , 汪辉 , 屈治国 . 数据驱动辅助高通量筛选阴离子柱撑金属有机框架储氢 [J ] . 化工学报 , 2025 , 76 ( 8 ): 4259 - 4272 .

Gao Z , Wang H , Qu Z G . Data-driven high-throughput screening of anion-pillared metal-organic frameworks for hydrogen storage [J ] . CIESC Journal , 2025 , 76 ( 8 ): 4259 - 4272 .

Chung Y G , Haldoupis E , Bucior B J , et al . Advances, updates, and analytics for the computation-ready, experimental metal-organic framework database: core MOF 2019 [J ] . Journal of Chemical & Engineering Data , 2019 , 64 ( 12 ): 5985 - 5998 .

Dubbeldam D , Calero S , Ellis D E , et al . RASPA: molecular simulation software for adsorption and diffusion in flexible nanoporous materials [J ] . Molecular Simulation , 2016 , 42 ( 2 ): 81 - 101 .

Rappe A K , Casewit C J , Colwell K S , et al . UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations [J ] . Journal of the American Chemical Society , 1992 , 114 ( 25 ): 10024 - 10035 .

Li Y , Situ Y , Guan K X , et al . High dynamic separation performance of metal-organic framewo rks for D 2 /H 2 : Independent or competitive adsorption [J ] . AIChE Journal , 2024 , 70 ( 1 ): e18283 .

Darkrim F , Levesque D . Monte Carlo simulations of hydrogen adsorption in single-walled carbon nanotubes [J ] . The Journal of Chemical Physics , 1998 , 109 ( 12 ): 4981 - 4984 .

Cao D W , Ren J H , Gong Y , et al . Quantum sieving of H 2 /D 2 in MOFs: a study on the correlation between the separation performance, pore size and temperature [J ] . Journal of Materials Chemistry A , 2020 , 8 ( 13 ): 6319 - 6327 .

Zhao F J , Tan Y X , Wang W J , et al . Optimizing H 2 , D 2 , and C 2 H 2 sorption properties by tuning the pore apertures in metal-organic frameworks [J ] . Inorganic Chemistry , 2018 , 57 ( 21 ): 13312 - 7 .

O’Boyle N M , Banck M , James C A , et al . Open Babel: an open chemical toolbox [J ] . Journal of Cheminformatics , 2011 , 3 ( 1 ): 33 .

Yap C W . PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints [J ] . Journal of Computational Chemistry , 2011 , 32 ( 7 ): 1466 - 1474 .

Durant J L , Leland B A , Henry D R , et al . Reoptimization of MDL keys for use in drug discovery [J ] . Journal of Chemical Information and Computer Sciences , 2002 , 42 ( 6 ): 1273 - 1280 .

Tan H Y , Teng Y K , Shan G C . High throughput computational screening and interpretable machine learning for iodine capture of metal-organic frameworks [J ] . npj Computational Materials , 2025 , 11 : 115 .

Lin Z H , Cai H , Peng H J , et al . Enhancing arsenate removal through interpretable machine learning guiding the modular design of metal-organic frameworks [J ] . Chemical Engineering Journal , 2024 , 497 : 155058 .

Ming Z Y , Zhang M , Zhang S X , et al . A multi-method approach to analyzing MOFs for chemical warfare simulant capture: molecular simulation, machine learning, and molecular fingerprints [J ] . Nanomaterials , 2025 , 15 ( 3 ): 183 - 183 .

Xian J Y , Xie X X , Huang Z Y , et al . Structure and properties of a mixed-ligand co-MOF that was synthesized in situ from a single imidazole-pyridyl-tetrazole trifunctional ligand [J ] . Crystal Growth & Design , 2023 , 23 ( 3 ): 1448 - 1454 .

Chen D M , Xu N , Qiu X H , et al . Functionalization of metal-organic framework via mixed-ligand strategy for selective CO 2 sorption at ambient conditions [J ] . Crystal Growth & Design , 2015 , 15 ( 2 ): 961 - 965 .

Qiao Z W , Xu Q S , Jiang J W . Computational screening of hydrophobic metal-organic frameworks for the separation of H2S and CO 2 from natural gas [J ] . Journal of Materials Chemistry A , 2018 , 6 ( 39 ): 18898 - 18905 .

翁惠琼 , 黄河 , 王雯菲 , 等 . 基于MOFid赋能下的AI大数据挖掘高性能化学战剂吸附材料 [J ] . 化学学报 , 2026 , 84 ( 1 ): 8 - 19 .

Weng H Q , Huang H , Wang W F , et al . AI big-data mining empowered by MOFid for high-performance chemical warfare agent adsorbents [J ] . Acta Chimica Sinica , 2026 , 84 ( 1 ): 8 - 19 .

Sengupta D , Melix P , Bose S , et al . Air-stable Cu(I) metal-organic framework for hydrogen storage [J ] . Journal of the American Chemical Society , 2023 , 145 ( 37 ): 20492 - 20502 .

Nguyen-Thuy T , Le-Hoang P , Hoang Vu N , et al . Hydrogen adsorption mechanism of MOF-74 metal-organic frameworks: an insight from first principles calculations [J ] . RSC Advances , 2020 , 10 ( 72 ): 43940 - 43949 .

Fan C B , Wei Y Y , Wang L L , et al . Design and construction of cobalt-organic framework with outstanding adsorption properties assembled by 3-(3, 5-dicarboxylphenoxy)pyridine [J ] . Journal of Molecular Structure , 2023 , 1288 : 135733 .

Meng Z S , Li Q Y , Sun H L , et al . Tricycloquinazoline-based monolayer conjugated metal-organic frameworks as promising hydrogen storage media: a theoretical investigation [J ] . Green Energy & Environment , 2025 , 10 ( 6 ): 1326 - 1336 .

Bag A , Sinha S , Das H S , et al . Hydrogen storage efficiency of the Ag (I)/Au (I) decorated five-member aromatic heterocyclic (AH) compounds: a theoretical investigation [J ] . Engineered Science , 2023 : 1062 - 1062 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Data-driven high-throughput screening of anion-pillared metal-organic frameworks for hydrogen storage

Machine learning-assisted high-throughput screening of high-performance zeolites for CO2 adsorption

Molecular simulation study on adsorption behavior of K⁺ and NH4+ by biomass ash

Metal-organic framework encapsulating carbon nanotubes for trace CO2 separation

Multi-channel CNN predicts the adsorption performance of MOFs for C3F6/C3F8

Related Author

GAO Zheng

WANG Hui

QU Zhiguo

WANG Ning

LU Jiarong

LIU Yihang

WEN Jiapeng

DU Ding

Related Institution

Key Laboratory of Thermo-Fluid Science and Engineering of MDE, School of Energy and Power Engineering, Xi'an Jiaotong University

China Petroleum Pipeline Engineering Corporation

State Key Laboratory of Heavy Oil Processing, China University of Petroleum

School of Energy and Power Engineering, Northeast Electric Power University

Huaneng Jilin Power Generation Co., Ltd.

⁰