Machine-learning-assisted intelligent synthesis of UiO-66(Ce): Balancing the trade-off between structural defects and thermal stability for efficient hydrogenation of Dicyclopentadiene

Abstract

Metal-organic frameworks (MOFs), renowned for structural diversity and design flexibility , exhibit potential in catalysis. However, the pursuit of higher catalytic activity through defects often compromises stability, requiring a delicate balance. Traditional trial-and-error method for optimizing synthesis parameters within the complex chemical space is inefficient. Herein, taking the typical MOF UiO-66(Ce) as an illustrative example, a closed loop workflow is built, which integrates machine learning (ML)-assissted prediction, multi-objective optimization (MOO) and experimental preparation to synergistically optimize the defect content and thermal stability of UiO-66(Ce) for efficient hydrogenation of dicyclopentadiene (DCPD). An automatic data extraction program ensures data accuracy, establishing a highquality database. ML is employed to explore the intricate synthesis-structureproperty correlations, enabling precise delineation of pure-phase subspace and accurate predictions of properties. After two iterations, MOO model identifies optimal protocols for high defect content (>40%) and thermal stability (>300°C). The optimized UiO-66(Ce) exhibits superior catalytic performance in hydrogenation of DCPD, validating the precision and reliability of our methodology. This ML-assisted approach offers a valuable paradigm for solving the trade-off riddle in materials field.

Keywords

defect content / machine learning / metal-organic frameworks / multi-objective optimization / thermal stability

References

1	Huang NY, Li B, Wu D, et al. Crystal engineering of MOF-derived bimetallic oxide solid solution anchored with Au nanoparticles for photocatalytic CO2 reduction to syngas and C2 hydrocarbons. Angew Chem Int Ed Engl. 2024;63(21):e202319177.
2	Sun L, Pan X, Xie YN, et al. Accelerated dynamic reconstruction in metal-organic frameworks with ligand defects for selective electrooxidation of amines to azos coupling with hydrogen production. Angew Chem Int Ed Engl. 2024;63(21):e202402176.
3	Cho JH, Kim Y, Yu HK, Kim SY. Advancements in two-dimensional covalent organic framework nanosheets for electrocatalytic energy conversion: current and future prospects. Energy Mater. 2024;4(2).
4	Ahmad M, Chen J, Liu J, et al. Metal-organic framework-based single-atom electro-/photocatalysts: synthesis, energy applications, and opportunities. Carbon Energy. 2023;6(1).
5	Wang J, Liu J, Wang H, et al. A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metalorganic frameworks. Nat Commun. 2024;15(1):1904.
6	Cong S, Zhou Y, Luo C, et al. Designing metal-organic framework (MOF) membranes for isomer separation. Angew Chem Int Ed Engl 2024;63(15):e202319894.
7	Wang G, Tang Z, Gao Y, et al. Phase change thermal storage materials for interdisciplinary applications. Chem Rev. 2023;123(11):6953-7024.
8	Liu P, Huang M, Chen X, et al. Polypyrrole-boosted photothermal energy storage in MOF-based phase change materials. Interdiscip Mater. 2023;2(3):423-433.
9	Wang SQ, Gu X, Wang X, et al. Defect-engineering of Zr(IV)-based metal-organic frameworks for regulating CO2 photoreduction. Chem Eng J. 2022;429:132157.
10	Ren J, Ledwaba M, Musyoka NM, et al. Structural defects in metalorganic frameworks (MOFs): formation, detection and control towards practices of interests. Coord Chem Rev. 2017;349:169-197.
11	Li RS, Wang LM, Zhou PY, et al. Electronic state, abundance and microenvironment modulation of Ru nanoclusters within hierarchically porous UiO-66 (Ce) for efficient hydrogenation of dicyclopentadiene. Chin J Catal. 2024;56:150-165.
12	Chu L, Guo J, Wang L, et al. Synthesis of defected UiO-66 with boosting the catalytic performance via rapid crystallization. Appl Organomet Chem. 2021;36(3).
13	Moore SC, Smith MR, Trettin JL, Yang RA, Sarazen ML. Kinetic impacts of defect sites in metal-organic framework catalysts under varied driving forces. ACS Energy Lett. 2023;8(3):1397-1407.
14	Liu S, Zhang Y, Zhu F, et al. Mg-MOF-74 derived defective framework for hydrogen storage at above-ambient temperature assisted by Pt catalyst. Adv Sci. 2024;11(18):e2401868.
15	Taddei M. When defects turn into virtues: the curious case of zirconiumbased metal-organic frameworks. Coord Chem Rev. 2017;343:1-24.
16	Younis SA, Bhardwaj N, Bhardwaj SK, Kim KH, Deep A. Rare earth metal-organic frameworks (RE-MOFs): synthesis, properties, and biomedical applications. Coord Chem Rev. 2021;429:213620.
17	Li S, Dong Z, Jin J, et al. Optimal design of high-performance rareearth-free wrought magnesium alloys using machine learning. Mat Genome Eng Adv. 2024;2(2):e45.
18	Burger B, Maffettone PM, Gusev VV, et al. A mobile robotic chemist. Nature. 2020;583(7815):237-241.
19	Wang CA, An G, Lin J, et al. Aromatic compounds-mediated synthesis of anatase-free hierarchical TS-1 zeolite: exploring design strategies via machine learning and enhanced catalytic performance. Aggregate. 2023;4(4).
20	Lin J, Liu Z, Guo Y, et al. Machine learning accelerates the investigation of targeted MOFs: performance prediction, rational design and intelligent synthesis. Nano Today. 2023;49:101802.
21	Moosavi SM, Chidambaram A, Talirz L, Haranczyk M, Stylianou KC, Smit B. Capturing chemical intuition in synthesis of metal-organic frameworks. Nat Commun. 2019;10(1):539.
22	Chen P, Tang Z, Zeng Z, et al. Machine-learning-guided morphology engineering of nanoscale metal-organic frameworks. Matter. 2020;2(6):1651-1666.
23	Xie Y, Zhang C, Deng H, et al. Accelerate synthesis of metal-organic frameworks by A robotic platform and bayesian optimization. ACS Appl Mater Interfaces. 2021;13(45):53485-53491.
24	Gou W, Shi ZZ, Zhu Y, et al. Multi-objective optimization of three mechanical properties of Mg alloys through machine learning. Mat. Genome Eng Adv. 2024;e54.
25	Lammert M, Wharmby MT, Smolders S, et al. Cerium-based metal organic frameworks with UiO-66 architecture: synthesis, properties and redox catalytic activity. Chem Commun. 2015;51(63):12578-12581.
26	Yang J, Li K, Li C, Gu J. Intrinsic apyrase-like activity of cerium-based metal-organic frameworks (MOFs): dephosphorylation of adenosine tri-and diphosphate. Angew Chem Int Ed Engl. 2020;59(51):22952-22956.
27	Chen H, Liu C, Guo W, et al. Functionalized UiO-66(Ce) for photocatalytic organic transformation: the role of active sites modulated by ligand functionalization. Catal Sci Technol. 2022;12(6):1812-1823.
28	Hanaoka K. Bayesian optimization for goal-oriented multi-objective inverse material design. iScience. 2021;24(7):102781.
29	Nandy A, Duan C, Kulik HJ. Using machine learning and data mining to leverage community knowledge for the engineering of stable metalorganic frameworks. J Am Chem Soc. 2021;143(42):17535-17547.
30	Shearer GC, Forselv S, Chavan S, et al. In situ infrared spectroscopic and gravimetric characterisation of the solvent removal and dehydroxylation of the metal organic frameworks UiO-66 and UiO-67. Top Catal. 2013;56(9-10):770-782.
31	Sannes DK, Øien-Ødegaard S, Aunan E, Nova A, Olsbye U. Quantification of linker defects in UiO-type metal-organic frameworks. Chem Mater. 2023;35(10):3793-3800.
32	Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321-357.
33	Altmann A, Tolosi L, Sander O, Lengauer T. Permutation importance: a corrected feature importance measure. Bioinformatics. 2010;26(10):1340-1347.
34	Lundberg SM, Lee SIA. Unified approach to interpreting model predictions. NIPS (News Physiol Sci). 2017;30.
35	Jin HG, Wang M, Wen JX, et al. Oxygen vacancy-rich mixed-valence cerium MOF: an efficient separator coating to high-performance lithium-sulfur batteries. ACS Appl Mater Interfaces. 2021;13(3):3899-3910.
36	Paszkowicz W. Genetic algorithms, a nature-inspire. tool: survey of applications in materials science and related fields. Mat. Manuf. Process. 2009;24(2):174-197.
37	Li DQ, Liu JC, Liu DZ, Wang FA. Solubilities of terephthalaldehydic, Ptoluic, benzoic, terephthalic and isophthalic acids in N, Ndimethylformamide from 294.75 to 370.45 K. Fluid Phase Equil. 2002;200(1):69-74.
38	Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:11.
39	Sun J, Wen J, Wu G, et al. Harmonizing the electronic structures on BiOI with active oxygen vacancies toward facet-dependent antibacterial photodynamic therapy. Adv Funct Mater. 2020;30(42).
40	Ren Y, Guo D, Zhao Z, et al. Singlet oxygen mediated photocatalytic antimonite decontamination in water using nanoconfined TiO2. Chem Eng J. 2022;435:134832.
41	Liu C, Shi YZ, Chen Q, et al. The defect-modulated UiO-66(Ce) MOFs for enhancing photocatalytic selective organic oxidations. Rare Met. 2024:1-12.
42	Feng X, Jena HS, Krishnaraj C, et al. Creation of exclusive artificial cluster defects by selective metal removal in the (Zn, Zr) mixed-metal UiO-66. J Am Chem Soc. 2021;143(51):21511-21518.
43	Liu L, Chen Z, Wang J, et al. Imaging defects and their evolutionin a metal-organic framework at sub-unit-cell resolution. Nat Chem. 2019;11(7):622-628.
44	Wu ZL, Tian B, Xu HJ. Improving color rendering index of Mn-doped ZnO nanorods on silicon-based substrate. Rare Met. 2016;36(9):711-717.
45	Kim M, Park G, Jo K, Lee H. Enhanced redox properties of Gd-doped CeO2-TiO2 induced by oxygen vacancies and disordered structure. Mat. Today Chem. 2023;29:101440.
46	Chaemchuen S, Heynderickx PM, Verpoort F. Kinetic modeling of oleic acid esterification with UiO-66: from intrinsic experimental data to kinetics via elementary reaction steps. Chem Eng J. 2020;394:124816.
47	Liang W, Wang X, Yang W, et al. Tailoring and identifying bronsted acid sites on metal oxo-clusters of metal-organic frameworks for catalytic transformation. ACS Cent Sci. 2023;9(1):27-35.
48	Liu Z, Wang L, Wang C, et al. Modulating the strong metal-support interactions by regulating the chemical microenvironment of Pt confined in MOFs for low temperature hydrogenation of DCPD. Chem Eng J. 2024;479:147601.