skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation

Abstract

Metal–oxo moieties are important catalytic intermediates in the selective partial oxidation of hydrocarbons and in water splitting. Stable metal–oxo species have reactive properties that vary depending on the spin state of the metal, complicating the development of structure–property relationships. To overcome these challenges, we train machine-learning (ML) models capable of predicting metal–oxo formation energies across a range of first-row metals, oxidation states, and spin states. Using connectivity-only features tailored for inorganic chemistry as inputs to kernel ridge regression or artificial neural network (ANN) ML models, we achieve good mean absolute errors (4–5 kcal/mol) on set-aside test data across a range of ligand orientations. Analysis of feature importance for oxo formation energy prediction reveals the dominance of nonlocal, electronic ligand properties in contrast to other transition metal complex properties (e.g., spin-state or ionization potential). We enumerate the theoretical catalyst space with an ANN, revealing expected trends in oxo formation energetics, such as destabilization of the metal–oxo species with increasing d-filling, as well as exceptions, such as weak correlations with indicators of oxidative stability of the metal in the resting state or unexpected spin-state dependence in reactivity. We carry out uncertainty-aware evolutionary optimization using the ANN to explore a >37 000 candidatemore » catalyst space. New metal and oxidation state combinations are uncovered and validated with density functional theory (DFT), including counterintuitive oxo formation energies for oxidatively stable complexes. This approach doubles the density of confirmed DFT leads in originally sparsely populated regions of property space, highlighting the potential of ML-model-driven discovery to uncover catalyst design rules and exceptions.« less

Authors:
ORCiD logo [1];  [2]; ORCiD logo [1]; ORCiD logo [1];  [2]; ORCiD logo [1]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  2. Clemson Univ., Clemson, SC (United States)
Publication Date:
Research Org.:
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
OSTI Identifier:
1560618
Grant/Contract Number:  
SC0012702
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
ACS Catalysis
Additional Journal Information:
Journal Volume: 9; Journal Issue: 9; Journal ID: ISSN 2155-5435
Publisher:
American Chemical Society (ACS)
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; metal−oxo species; machine learning; density functional theory; spin-state-dependent reactivity; transition metal catalysis; artificial neural networks

Citation Formats

Nandy, Aditya, Zhu, Jiazhou, Janet, Jon Paul, Duan, Chenru, Getman, Rachel B., and Kulik, Heather J. Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation. United States: N. p., 2019. Web. doi:10.1021/acscatal.9b02165.
Nandy, Aditya, Zhu, Jiazhou, Janet, Jon Paul, Duan, Chenru, Getman, Rachel B., & Kulik, Heather J. Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation. United States. doi:10.1021/acscatal.9b02165.
Nandy, Aditya, Zhu, Jiazhou, Janet, Jon Paul, Duan, Chenru, Getman, Rachel B., and Kulik, Heather J. Tue . "Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation". United States. doi:10.1021/acscatal.9b02165. https://www.osti.gov/servlets/purl/1560618.
@article{osti_1560618,
title = {Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation},
author = {Nandy, Aditya and Zhu, Jiazhou and Janet, Jon Paul and Duan, Chenru and Getman, Rachel B. and Kulik, Heather J.},
abstractNote = {Metal–oxo moieties are important catalytic intermediates in the selective partial oxidation of hydrocarbons and in water splitting. Stable metal–oxo species have reactive properties that vary depending on the spin state of the metal, complicating the development of structure–property relationships. To overcome these challenges, we train machine-learning (ML) models capable of predicting metal–oxo formation energies across a range of first-row metals, oxidation states, and spin states. Using connectivity-only features tailored for inorganic chemistry as inputs to kernel ridge regression or artificial neural network (ANN) ML models, we achieve good mean absolute errors (4–5 kcal/mol) on set-aside test data across a range of ligand orientations. Analysis of feature importance for oxo formation energy prediction reveals the dominance of nonlocal, electronic ligand properties in contrast to other transition metal complex properties (e.g., spin-state or ionization potential). We enumerate the theoretical catalyst space with an ANN, revealing expected trends in oxo formation energetics, such as destabilization of the metal–oxo species with increasing d-filling, as well as exceptions, such as weak correlations with indicators of oxidative stability of the metal in the resting state or unexpected spin-state dependence in reactivity. We carry out uncertainty-aware evolutionary optimization using the ANN to explore a >37 000 candidate catalyst space. New metal and oxidation state combinations are uncovered and validated with density functional theory (DFT), including counterintuitive oxo formation energies for oxidatively stable complexes. This approach doubles the density of confirmed DFT leads in originally sparsely populated regions of property space, highlighting the potential of ML-model-driven discovery to uncover catalyst design rules and exceptions.},
doi = {10.1021/acscatal.9b02165},
journal = {ACS Catalysis},
issn = {2155-5435},
number = 9,
volume = 9,
place = {United States},
year = {2019},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: Representative structures for the equatorially symmetric (top) and equatorially asymmetric (bottom) data sets, which each have up to two unique ligand types, L1 and L2 (here L1 = CN, L2 = NH3). The metal is shown as an orange sphere, and other atoms are shown as sticks, withmore » oxygen in red, nitrogen in blue, and carbon in gray.« less

Save / Share:
Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.