Yi Luo1,Saientan Bag2,Orysia Zaremba3,Adrian Cierpka4,Jacopo Andreo3,Stefan Wuttke3,Pascal Friederich4,Manuel Tsotsalas1
Institute of Functional Interfaces, Karlsruhe Institute of Technology1,Institute of Nanotechnology, Karlsruhe Institute of Technology2,Basque Center for Materials, Applications & Nanostructures3,Institute of Theoretical Informatics, Karlsruhe Institute of Technology4
Yi Luo1,Saientan Bag2,Orysia Zaremba3,Adrian Cierpka4,Jacopo Andreo3,Stefan Wuttke3,Pascal Friederich4,Manuel Tsotsalas1
Institute of Functional Interfaces, Karlsruhe Institute of Technology1,Institute of Nanotechnology, Karlsruhe Institute of Technology2,Basque Center for Materials, Applications & Nanostructures3,Institute of Theoretical Informatics, Karlsruhe Institute of Technology4
Metal–organic frameworks (MOFs) are porous materials formed via the connection between metal-centered nodes with organic linkers.<sup>1</sup> With the utilization of different metal nodes and linkers, the topology, pore size, and functional groups of MOFs can be adjusted for high specific surface area, numerous active sites, and mass transfer channels.<sup>2</sup> This flexibility in the MOF design allows great potential for MOF-based and MOF-derived material in the application in energy storage and conversion.<sup>3</sup> Computer-assisted methods have been applied in the acceleration for the design of MOF-based materials.<sup>4–6</sup> However, the potential of using machine learning (ML) methods to suggest parameters in MOF synthesis experiments is not well explored. Here, we show an approach of data mining and machine learning (ML) method for rationalization and acceleration of the MOF discovery process by directly predicting the synthesis condition of a new MOF based on its crystal structure.<sup>7</sup> There are three steps in our approach: 1) Creation of a MOF synthesis database (SynMOF) via automatic extraction of synthesis parameters from scientific literature; 2) Training of multiple ML models on the SynMOF database; 3) Prediction of synthesis conditions for new MOF structures by the ML models. These early-stage ML models, exhibit a good prediction performance, surpassing human expert predictions, which was shown through a synthesis survey from 11 MOF experts worldwide.<br/><br/>References<br/>(1) Furukawa, H.; Cordova, K. E.; O’Keeffe, M.; Yaghi, O. M. The Chemistry and Applications of Metal-Organic Frameworks. <i>Science</i> <b>2013</b>, <i>341</i> (6149). <br/>(2) Du, R.; Wu, Y.; Yang, Y.; Zhai, T.; Zhou, T.; Shang, Q.; Zhu, L.; Shang, C.; Guo, Z. Porosity Engineering of MOF-Based Materials for Electrochemical Energy Storage. <i>Advanced Energy Materials</i> <b>2021</b>, <i>11</i> (20), 2100154. <br/>(3) Adegoke, K. A.; Maxakato, N. W. Porous Metal-Organic Framework (MOF)-Based and MOF-Derived Electrocatalytic Materials for Energy Conversion. <i>Materials Today Energy</i> <b>2021</b>, <i>21</i>, 100816. <br/>(4) Moosavi, S. M.; Chidambaram, A.; Talirz, L.; Haranczyk, M.; Stylianou, K. C.; Smit, B. Capturing Chemical Intuition in Synthesis of Metal-Organic Frameworks. <i>Nat Commun</i> <b>2019</b>, <i>10</i> (1), 539. <br/>(5) Luo, Y.; Ahmad, M.; Schug, A.; Tsotsalas, M. Rising Up: Hierarchical Metal–Organic Frameworks in Experiments and Simulations. <i>Advanced Materials</i> <b>2019</b>, <i>31</i> (26), 1901744. <br/>(6) Ahmad, M.; Luo, Y.; Wöll, C.; Tsotsalas, M.; Schug, A. Design of Metal-Organic Framework Templated Materials Using High-Throughput Computational Screening. <i>Molecules</i> <b>2020</b>, <i>25</i> (21), 4875. <br/>(7) Luo, Y.; Bag, S.; Zaremba, O.; Cierpka, A.; Andreo, J.; Wuttke, S.; Friederich, P.; Tsotsalas, M. MOF Synthesis Prediction Enabled by Automatic Data Mining and Machine Learning**. <i>Angewandte Chemie International Edition</i> <b>2022</b>, <i>61</i> (19), e202200242.