In a finding that could help pave the way toward cleaner fuels and a more sustainable chemical industry, University of Michigan researchers used machine learning to predict how the compositions of metal alloys and metal oxides would affect their electronic structures. The electronic structure is key to understand how the material acts as a mediator or catalyst for chemical reactions. “We’re learning to identify the fingerprints of materials and connect them with the material’s performance,” said Bryan Goldsmith, the Dow Corning Assistant Professor of Chemical Engineering. Better ability to predict which metal and metal oxide compositions are best to control which reactions could improve large-scale chemical processes like hydrogen production, the production of other fuels and fertilizers, and the production of household chemicals like dishwashing soaps.
“The objective of our research is to develop predictive models that will connect the geometry of a catalyst to its performance. Such models are central for the design of new catalysts for critical chemical transformations,” said Suljo Linic, the Martin Lewis Perl Collegiate Professor of Chemical Engineering.
One of the most important approaches to predict how a material will behave as a potential mediator of a chemical reaction is to analyze its electronic structure, in particular the density of states, which describes how many quantum states of electrons are available in the reaction molecules and the energies of these states. In general, the electron density of states is described with summary statistics, an average energy or a bias that shows whether more electronic states are above or below the average, and so on. just simple statistics.
“That’s OK, but those are just simple statistics. You might miss something. With principal component analysis, you just take in everything and find what’s important. You’re not just throwing away information,” Goldsmith said.
Principal component analysis is a classic machine learning method that is taught in introductory data science courses. They used the electron density of the states as an input to the model, since the density of states is a good predictor of how the surface of a catalyst adsorbs or bonds with atoms and molecules that serve as reactants. The model links the density of states with the composition of the material. “We can see systematically what is changing in the density of states and correlate that with geometric properties of the material,” said Jacques Esterhuizen, a doctoral student in chemical engineering and first author on the paper in Chem Catalysis. Chemical engineers design metal alloys to achieve the density of states they need for a chemical reaction. The model accurately reflected correlations already observed relationships between the composition of a material and its density of states as well as the emergence of new potential trends that need to be researched.
The model simplifies the density of states into two parts or main components. One piece basically covers how the metal atoms fit together. In a layered metal alloy, this includes whether the underground metal separates the atoms from the surface or compresses them and the number of electrons that the underground metal helps to bind. The other part is just the number of electrons the surface metal atoms can bind together. From these two main components you can reconstruct the density of states in the material. This concept also works for the reactivity of metal oxides. In this case, it is about the ability of oxygen to interact with atoms and molecules, which is related to the stability of oxygen on the surface. Stable surface oxygen is less likely to react, while unstable surface oxygen is more reactive. The model accurately captured the stability of oxygen in metal oxides and perovskites, a class of metal oxides. The study was supported by the Department of Energy and University of Michigan.
Source link
