A1 Journal article (refereed)
Accelerated dinuclear palladium catalyst identification through unsupervised machine learning (2021)


Hueffel, J. A., Sperger, T., Funes-Ardoiz, I., Ward, J. S., Rissanen, K., & Schoenebeck, F. (2021). Accelerated dinuclear palladium catalyst identification through unsupervised machine learning. Science, 374(6571), 1134-1140. https://doi.org/10.1126/science.abj0999


JYU authors or editors


Publication details

All authors or editors: Hueffel, Julian A.; Sperger, Theresa; Funes-Ardoiz, Ignacio; Ward, Jas S.; Rissanen, Kari; Schoenebeck, Franziska

Journal or series: Science

ISSN: 0036-8075

eISSN: 1095-9203

Publication year: 2021

Publication date: 26/11/2021

Volume: 374

Issue number: 6571

Pages range: 1134-1140

Publisher: American Association for the Advancement of Science (AAAS)

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1126/science.abj0999

Publication open access: Not open

Publication channel open access: Channel is not openly available

Additional information: Data and materials availability: ML algorithm and python code are available online at GitHub (40). Crystallographic data are available at the Cambridge Crystallographic Data Center (www.ccdc.cam.ac.uk) under reference numbers CCDC 2055171 (D3), 2064562 (D4), 2055172 (D8), 2055173 (D10), 2055174 (D11), and 2064863 (D23). All other data are available in the main text or the supplementary materials.


Abstract

Although machine learning bears enormous potential to accelerate developments in homogeneous catalysis, the frequent need for extensive experimental data can be a bottleneck for implementation. Here, we report an unsupervised machine learning workflow that uses only five experimental data points. It makes use of generalized parameter databases that are complemented with problem-specific in silico data acquisition and clustering. We showcase the power of this strategy for the challenging problem of speciation of palladium (Pd) catalysts, for which a mechanistic rationale is currently lacking. From a total space of 348 ligands, the algorithm predicted, and we experimentally verified, a number of phosphine ligands (including previously never synthesized ones) that give dinuclear Pd(I) complexes over the more common Pd(0) and Pd(II) species.


Keywords: machine learning; catalysis; palladium; algorithms


Contributing organizations


Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 3


Last updated on 2022-19-08 at 19:16