The Kitchin Research Group

Geometry optimization and transition state searches are two very common tasks in molecular simulation. Typically every one of these is done from scratch, and they can only be made faster by using a better initial guess. Typical optimization algorithms use some variation of gradient descent, and the best ones also use an iterative approach to estimate the Hessian (second derivatives). The problem is we do not know the underlying function that is being optimized, so there is hardly any choice to benefit from the Hessian (which allows bigger, more accurate steps to be taken).

In this paper, we use machine learning to develop a surrogate model that is cheap compared to the DFT calculations, and that has an uncertainty quantification so we can tell when it is accurate. This allows us to take many cheap steps when the surrogate model is accurate, and only do expensive calculations when needed. More importantly though, the surrogate model works across many different geometry optimizations, which allows us to benefit from previous calculations. We show this works on a variety of atomic geometries ranging from metal slabs, slabs with adsorbates, and nanoparticle geometries, as well as with nudged elastic band calculations for transitions state searches.

@article{yang-2021-machin-learn,
  author =       {Yilin Yang and Omar A. Jim{\'e}nez-Negr{\'o}n and John R.
                  Kitchin},
  title =        {Machine-Learning Accelerated Geometry Optimization in
                  Molecular Simulation},
  journal =      {The Journal of Chemical Physics},
  volume =       154,
  number =       23,
  pages =        234704,
  year =         2021,
  doi =          {10.1063/5.0049665},
  url =          {https://doi.org/10.1063/5.0049665},
}

Copyright (C) 2021 by John Kitchin. See the License for information about copying.

org-mode source

Org-mode version = 9.4.6

Modeling alloys is tricky, and modeling dilute alloys has been an open challenge for a long time. Segregation is one of the biggest challenges; the surface composition is not the same as the bulk, and is influenced by adsorption. Although we know that the composition varies to lower the surface free energy, the configurational degrees of freedom make it difficult to find the lowest energy arrangement of atoms. In the dilute limit, the quantum chemical calculations and Monte Carlo simulates we do become very expensive due to the unit cell size. In this work, we use machine learning to build surrogate models for the configurational energy of an alloy slab in the dilute limit. Then, we use those models in conjunction with a semi-grand canonical Monte Carlo (MC) simulation to solve several of these problems. First, by fixing the alloy chemical potential at the desired dilute limit, we avoid the need for large unit cells. Second, the surrogate models are much more efficient than DFT, so we can use them in the MC simulations to run tens of thousands of simulation steps to get the required samples for reliable statistical averaging. In dilute alloys, the focus is on the unique catalytic properties of single atoms of an active metal like Pd in an inert metal like Ag. In the single atom limit though, there are few active sites. If you increase the bulk concentration, at some point the single atoms begin to aggregate into dimers and trimers, and adsorbates can make the aggregation happen faster. Aggregation is undesirable because it usually leads to lower selectivity, and more bulk like reactivity. An open question has been how do you design alloy catalysts under reaction conditions, given all this complexity. We apply this approach to the adsorption of acrolein on a dilute AgPd alloy, and show how to use the method to identify the bulk concentration where aggregation begins in a reactive environment.

@article{liu-2021-semi-grand,
  author =       {Mingjie Liu and Yilin Yang and John R. Kitchin},
  title =        {Semi-Grand Canonical Monte Carlo Simulation of the Acrolein
                  Induced Surface Segregation and Aggregation of {AgPd} With
                  Machine Learning Surrogate Models},
  journal =      {The Journal of Chemical Physics},
  volume =       154,
  number =       13,
  pages =        134701,
  year =         2021,
  doi =          {10.1063/5.0046440},
  url =          {https://doi.org/10.1063/5.0046440},
}

Copyright (C) 2021 by John Kitchin. See the License for information about copying.

org-mode source

Org-mode version = 9.4.6

Many machine learned potentials work by creating a numeric fingerprint that represents the local atomic environment around an atom, and then "machine learning" a function that computes the atomic energy for that atom. The total energy of an atomic configuration is then simply the sum of the atomic energies, and the forces are simply the derivative of that energy with respect to the atomic positions. In the Behler-Parrinello formulation, each element gets its own neural network for these calculations. In this work, we show that a single neural network with multiple outputs can be used instead. This means that all the elements share the weights in the neural network, and the atomic energy of each element is linearly proportional to the output of the last hidden layer. This has some benefits for transferability and suggests that there is a common nonlinear dimensional transform of the numeric fingerprints for the elements in this study.

@article{liu-2020-singl,
  author =       {Mingjie Liu and John R. Kitchin},
  title =        {Singlenn: Modified Behler-Parrinello Neural Network With
                  Shared Weights for Atomistic Simulations With Transferability},
  journal =      {The Journal of Physical Chemistry C},
  volume =       124,
  number =       32,
  pages =        {17811-17818},
  year =         2020,
  doi =          {10.1021/acs.jpcc.0c04225},
  url =          {https://doi.org/10.1021/acs.jpcc.0c04225},
}

Discuss on Twitter

Copyright (C) 2021 by John Kitchin. See the License for information about copying.

org-mode source

Org-mode version = 9.4

Generating renewable hydrogen is an important capability for reducing CO₂ emissions. In this work we use a photo-driven process where light interacts with a photosensitizer to generate electrons that reduce metal ions in solution to create nanoparticle catalysts, which subsequently catalyze hydrogen evolution from the oxidation of an amino alcohol. A challenge in this work is figuring out what the synthesis conditions are that lead to high activity; the metal salt compositions and concentrations, photosensitizer concentration, the concentration of amino alcohol and solvent choices all impact the catalytic performance. Exploring all these variables one at a time is expensive and time-consuming. To address this, we used a 96-well plate photoreactor that enabled us to run many experiments in parallel using a colorimetric hydrogen detecting tape to measure activity. This allowed us to explore many bimetallic co-catalysts comprised of Pd/Sn, Pd/Mo, Pd/Ru, Pd/Pb, Pd/Ni, Ni/Sn, Mo/Sn and Pt/Sn. Of these we found Pd/Sn showed the highest synergistic behavior, and best activity. We also show using DFT that Pd/Sn has a near optimal hydrogen adsorption energy, which is consistent with other highly active hydrogen evolution catalysts. This work shows an effective way to quickly screen hundreds of reaction conditions to explore the relationship between synthesis conditions and catalytic activity.

@article{lopato-2020-paral-screen,
  author =       {Eric M. Lopato and Emily A Eikey and Zoe C Simon and Seoin
                  Back and Kevin Tran and Jacqueline Lewis and Jakub F.
                  Kowalewski and Sadegh Yazdi and John R. Kitchin and Zachary W.
                  Ulissi and Jill E. Millstone and Stefan Bernhard},
  title =        {Parallelized Screening of Characterized and {DFT}-Modelled
                  Bimetallic Colloidal Co-Catalysts for Photocatalytic Hydrogen
                  Evolution},
  journal =      {ACS Catalysis},
  volume =       {10},
  number =       {7},
  pages =        {4244-4252},
  year =         2020,
  doi =          {10.1021/acscatal.9b05404},
  url =          {https://doi.org/10.1021/acscatal.9b05404},
}

Copyright (C) 2021 by John Kitchin. See the License for information about copying.

org-mode source

Org-mode version = 9.4.6

Bibliometrics are increasingly used to quantify scholarly productivity. In this paper, we introduce a Python package called pybliometrics that provides a scriptable interface to Scopus to aggregate publication data for analysis. The package provides pretty comprehensive coverage of the APIs for author, abstract, affiliation and citation queries. The manuscript shows examples for downloading abstracts in bulk, building collaboration network graphs, and analyzing citation trends. You have to get a key from Scopus to access their databases, and the package provides some guidance on how to get it and configure the package. If you are interested in bibliometrics, this package may be useful to you!

@article{rose-2019-pybliom,
  author =       {Michael E. Rose and John R. Kitchin},
  title =        {Pybliometrics: Scriptable Bibliometrics Using a Python
                  Interface To Scopus},
  journal =      {SoftwareX},
  volume =       10,
  number =       {nil},
  pages =        100263,
  year =         2019,
  doi =          {10.1016/j.softx.2019.100263},
  url =          {https://doi.org/10.1016/j.softx.2019.100263},
  DATE_ADDED =   {Mon Jul 8 07:06:58 2019},
}

Copyright (C) 2019 by John Kitchin. See the License for information about copying.

org-mode source

Org-mode version = 9.2.3