Prof. Berend Smit and Prof. Susana Garcia gave a talk at Lawrence Berkeley National Laboratory on September 13, 2023.
Metal-organic frameworks (MOFs) are the ideal playground for data science in Chemistry and Chemical Engineering. MOFs are crystalline materials consisting of a metal node and an organic linker. By combining different metal nodes and organic linkers, chemists can synthesize infinite materials for applications ranging from gas separation, gas storage, sensing, catalysis, etc. The holy grain of MOF synthesis is to design an optimal MOF for a given application. There are some fundamental reasons why we are still far from this goal. Chemical design space is infinite, and all possible MOFs are impossible to screen, experimentally or computationally. In addition, we need to find out the optimal materials for the whole design space. And, once we have designed our optimal MOF, we do not have a guarantee that we can synthesize this material. In this lecture, we show how data-science methods1 can be used to obtain insights into questions for which conventional theory does not answer, such as the oxidation state of a metal in a MOF2 or the heat capacity.3 We also show how data science can help us identify the characteristics of the top-performing materials for a carbon capture process.4 How large-language models can help us find the optimal synthesis conditions.5 In addition, we discuss some other machine-learning applications in chemical engineering applications.
References
1. S. M. Moosavi, K. M. Jablonka, and B. Smit, The Role of Machine Learning in the Understanding and Design of Materials J. Am. Chem. Soc. 142 (48), 20273 (2020) http://dx.doi.org/10.1021/jacs.0c09105
2. K. M. Jablonka, D. Ongari, S. M. Moosavi, and B. Smit, Using collective knowledge to assign oxidation states of metal cations in metal-organic frameworks Nat. Chem. 13, 771 (2021) http://dx.doi.org/10.1038/s41557-021-00717-y
3. S. M. Moosavi, B. Á. Novotny, D. Ongari, E. Moubarak, M. Asgari, Ö. Kadioglu, C. Charalambous, A. Ortega-Guerrero, A. H. Farmahini, L. Sarkisov, S. Garcia, F. Noé, and B. Smit, A data-science approach to predict the heat capacity of nanoporous materials Nat Mater 21, 1419 (2022) http://dx.doi.org/10.1038/s41563-022-01374-3
4. C. Charalambous, E. Moubarak, J. Schilling, E. Sanchez Fernandez, J.-Y. Wang, L. Herraiz, F. Mcilwaine, K. M. Jablonka, S. M. Moosavi, J. Van Herck, G. Mouchaham, C. Serre, A. Bardow, B. Smit, and S. Garcia, Shedding Light on the Stakeholders’ Perspectives for Carbon Capture. ChemRxiv (2023) http://dx.doi.org/10.26434/chemrxiv-2023-sn90q
5. K. M. Jablonka, P. Schwaller, A. Ortega-Guerrero, and B. Smit, Is GPT-3 All You Need for Low-Data Discovery in Chemistry? ChemRvix (2023) http://dx.doi.org/10.26434/chemrxiv-2023-fw8n4
6. K. M. Jablonka, C. Charalambous, E. Sanchez Fernandez, G. Wiechers, J. Monteiro, P. Moser, B. Smit, and S. Garcia, Machine learning for industrial processes: Forecasting amine emissions from a carbon capture plant Sci Adv 9 (1), eadc9576 (2023) http://dx.doi.org/10.1126/sciadv.adc9576
