1
|
Hollenbach JD, Pate CM, Jia H, Hart JL, Clancy P, Taheri ML. Real-time tracking of structural evolution in 2D MXenes using theory-enhanced machine learning. Sci Rep 2024; 14:17881. [PMID: 39095485 PMCID: PMC11297154 DOI: 10.1038/s41598-024-66902-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Accepted: 07/05/2024] [Indexed: 08/04/2024] Open
Abstract
In situ Electron Energy Loss Spectroscopy (EELS) combined with Transmission Electron Microscopy (TEM) has traditionally been pivotal for understanding how material processing choices affect local structure and composition. However, the ability to monitor and respond to ultrafast transient changes, now achievable with EELS and TEM, necessitates innovative analytical frameworks. Here, we introduce a machine learning (ML) framework tailored for the real-time assessment and characterization of in operando EELS Spectrum Images (EELS-SI). We focus on 2D MXenes as the sample material system, specifically targeting the understanding and control of their atomic-scale structural transformations that critically influence their electronic and optical properties. This approach requires fewer labeled training data points than typical deep learning classification methods. By integrating computationally generated structures of MXenes and experimental datasets into a unified latent space using Variational Autoencoders (VAE) in a unique training method, our framework accurately predicts structural evolutions at latencies pertinent to closed-loop processing within the TEM. This study presents a critical advancement in enabling automated, on-the-fly synthesis and characterization, significantly enhancing capabilities for materials discovery and the precision engineering of functional materials at the atomic scale.
Collapse
Affiliation(s)
- Jonathan D Hollenbach
- Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Cassandra M Pate
- Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Haili Jia
- Department of Chemical and Biomolecular and Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - James L Hart
- Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Paulette Clancy
- Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD, USA
- Department of Chemical and Biomolecular and Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Mitra L Taheri
- Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Physical Sciences Division, Pacific Northwest National Laboratory, Richland, WA, USA.
| |
Collapse
|
2
|
Levell Z, Le J, Yu S, Wang R, Ethirajan S, Rana R, Kulkarni A, Resasco J, Lu D, Cheng J, Liu Y. Emerging Atomistic Modeling Methods for Heterogeneous Electrocatalysis. Chem Rev 2024; 124:8620-8656. [PMID: 38990563 DOI: 10.1021/acs.chemrev.3c00735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/12/2024]
Abstract
Heterogeneous electrocatalysis lies at the center of various technologies that could help enable a sustainable future. However, its complexity makes it challenging to accurately and efficiently model at an atomic level. Here, we review emerging atomistic methods to simulate the electrocatalytic interface with special attention devoted to the components/effects that have been challenging to model, such as solvation, electrolyte ions, electrode potential, reaction kinetics, and pH. Additionally, we review relevant computational spectroscopy methods. Then, we showcase several examples of applying these methods to understand and design catalysts relevant to green hydrogen. We also offer experimental views on how to bridge the gap between theory and experiments. Finally, we provide some perspectives on opportunities to advance the field.
Collapse
Affiliation(s)
- Zachary Levell
- Texas Materials Institute and Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas 78712, United States
| | - Jiabo Le
- Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, 1219 Zhongguan West Road, Ningbo 315201, China
| | - Saerom Yu
- Texas Materials Institute and Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas 78712, United States
| | - Ruoyu Wang
- Texas Materials Institute and Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas 78712, United States
| | - Sudheesh Ethirajan
- Department of Chemical Engineering, University of California, Davis, California 95616, United States
| | - Rachita Rana
- Department of Chemical Engineering, University of California, Davis, California 95616, United States
| | - Ambarish Kulkarni
- Department of Chemical Engineering, University of California, Davis, California 95616, United States
| | - Joaquin Resasco
- Department of Chemical Engineering, The University of Texas at Austin, Austin, Texas 78712, United States
| | - Deyu Lu
- Center for Functional Nanomaterials, Brookhaven National Laboratory, Upton, New York 11973, United States
| | - Jun Cheng
- State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, China
- Laboratory of AI for Electrochemistry (AI4EC), Tan Kah Kee Innovation Laboratory, Xiamen 361005, China
| | - Yuanyue Liu
- Texas Materials Institute and Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas 78712, United States
| |
Collapse
|
3
|
Kjær ETS, Anker AS, Kirsch A, Lajer J, Aalling-Frederiksen O, Billinge SJL, Jensen KMØ. MLstructureMining: a machine learning tool for structure identification from X-ray pair distribution functions. DIGITAL DISCOVERY 2024; 3:908-918. [PMID: 38756225 PMCID: PMC11094694 DOI: 10.1039/d4dd00001c] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Accepted: 03/27/2024] [Indexed: 05/18/2024]
Abstract
Synchrotron X-ray techniques are essential for studies of the intrinsic relationship between synthesis, structure, and properties of materials. Modern synchrotrons can produce up to 1 petabyte of data per day. Such amounts of data can speed up materials development, but also comes with a staggering growth in workload, as the data generated must be stored and analyzed. We present an approach for quickly identifying an atomic structure model from pair distribution function (PDF) data from (nano)crystalline materials. Our model, MLstructureMining, uses a tree-based machine learning (ML) classifier. MLstructureMining has been trained to classify chemical structures from a PDF and gives a top-3 accuracy of 99% on simulated PDFs not seen during training, with a total of 6062 possible classes. We also demonstrate that MLstructureMining can identify the chemical structure from experimental PDFs from nanoparticles of CoFe2O4 and CeO2, and we show how it can be used to treat an in situ PDF series collected during Bi2Fe4O9 formation. Additionally, we show how MLstructureMining can be used in combination with the well-known methods, principal component analysis (PCA) and non-negative matrix factorization (NMF) to analyze data from in situ experiments. MLstructureMining thus allows for real-time structure characterization by screening vast quantities of crystallographic information files in seconds.
Collapse
Affiliation(s)
- Emil T S Kjær
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| | - Andy S Anker
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| | - Andrea Kirsch
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| | - Joakim Lajer
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| | | | - Simon J L Billinge
- Department of Applied Physics and Applied Mathematics Science, Columbia University New York NY 10027 USA
| | - Kirsten M Ø Jensen
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| |
Collapse
|
4
|
Carbone MR, Maffettone PM, Qu X, Yoo S, Lu D. Accurate, Uncertainty-Aware Classification of Molecular Chemical Motifs from Multimodal X-ray Absorption Spectroscopy. J Phys Chem A 2024. [PMID: 38416723 DOI: 10.1021/acs.jpca.3c06910] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/01/2024]
Abstract
Accurate classification of molecular chemical motifs from experimental measurement is an important problem in molecular physics, chemistry, and biology. In this work, we present neural network ensemble classifiers for predicting the presence (or lack thereof) of 41 different chemical motifs on small molecules from simulated C, N, and O K-edge X-ray absorption near-edge structure (XANES) spectra. Our classifiers not only achieve class-balanced accuracies of more than 0.95 but also accurately quantify uncertainty. We also show that including multiple XANES modalities improves predictions notably on average, demonstrating a "multimodal advantage" over any single modality. In addition to structure refinement, our approach can be generalized to broad applications with molecular design pipelines.
Collapse
Affiliation(s)
- Matthew R Carbone
- Computational Science Initiative, Brookhaven National Laboratory, Upton, New York 11973, United States
| | - Phillip M Maffettone
- National Synchrotron Light Source II, Brookhaven National Laboratory, Upton, New York 11973, United States
| | - Xiaohui Qu
- Center for Functional Nanomaterials, Brookhaven National Laboratory, Upton, New York 11973, United States
| | - Shinjae Yoo
- Computational Science Initiative, Brookhaven National Laboratory, Upton, New York 11973, United States
| | - Deyu Lu
- Center for Functional Nanomaterials, Brookhaven National Laboratory, Upton, New York 11973, United States
| |
Collapse
|
5
|
Anker AS, Butler KT, Selvan R, Jensen KMØ. Machine learning for analysis of experimental scattering and spectroscopy data in materials chemistry. Chem Sci 2023; 14:14003-14019. [PMID: 38098730 PMCID: PMC10718081 DOI: 10.1039/d3sc05081e] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Accepted: 11/20/2023] [Indexed: 12/17/2023] Open
Abstract
The rapid growth of materials chemistry data, driven by advancements in large-scale radiation facilities as well as laboratory instruments, has outpaced conventional data analysis and modelling methods, which can require enormous manual effort. To address this bottleneck, we investigate the application of supervised and unsupervised machine learning (ML) techniques for scattering and spectroscopy data analysis in materials chemistry research. Our perspective focuses on ML applications in powder diffraction (PD), pair distribution function (PDF), small-angle scattering (SAS), inelastic neutron scattering (INS), and X-ray absorption spectroscopy (XAS) data, but the lessons that we learn are generally applicable across materials chemistry. We review the ability of ML to identify physical and structural models and extract information efficiently and accurately from experimental data. Furthermore, we discuss the challenges associated with supervised ML and highlight how unsupervised ML can mitigate these limitations, thus enhancing experimental materials chemistry data analysis. Our perspective emphasises the transformative potential of ML in materials chemistry characterisation and identifies promising directions for future applications. The perspective aims to guide newcomers to ML-based experimental data analysis.
Collapse
Affiliation(s)
- Andy S Anker
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| | - Keith T Butler
- Department of Chemistry, University College London Gower Street London WC1E 6BT UK
| | - Raghavendra Selvan
- Department of Computer Science, University of Copenhagen 2100 Copenhagen Ø Denmark
- Department of Neuroscience, University of Copenhagen 2200 Copenhagen N Denmark
| | - Kirsten M Ø Jensen
- Department of Chemistry and Nano-Science Center, University of Copenhagen 2100 Copenhagen Ø Denmark
| |
Collapse
|
6
|
Perras FA, Culver DB. On the use of NMR distance measurements for assessing surface site homogeneity. Dalton Trans 2023. [PMID: 38015038 DOI: 10.1039/d3dt03201a] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2023]
Abstract
The past few decades have seen tremendous growth in the area of single-site heterogeneous catalysis, which aims to combine the best aspects of homogeneous and heterogeneous catalysis, namely molecular-level site control and ease of separation/recycling. Despite this, we still do not have a means of assessing site homogeneity and whether the produced catalyst is indeed a "single-site". Recent developments have enabled the use of NMR-based distance measurements to determine the conformations and configurations of surface sites, leading to the question whether such measurements can be used to distinguish materials containing either single or multiple surface sites with otherwise indistinguishable NMR properties. We describe a Monte Carlo-based multi-structure search algorithm and its application to the determination of multi-site structures from supported metal complexes. The sensitivity of REDOR data to the existence of multiple sites is assessed using synthetic data and prior literature examples are revisited to determine whether the single-site approximation was indeed appropriate. We lastly apply this new methodology to differentiate the configurations of zirconocene complexes grafted onto alumina supports that were thermally treated at different temperatures.
Collapse
Affiliation(s)
- Frédéric A Perras
- Department of Chemistry, Iowa State University, Ames, IA 50011, USA.
- Chemical and Biological Sciences, Ames National Laboratory, Ames, IA 50011, USA
| | - Damien B Culver
- Department of Chemistry, Iowa State University, Ames, IA 50011, USA.
| |
Collapse
|
7
|
Watson L, Pope T, Jay RM, Banerjee A, Wernet P, Penfold TJ. A Δ-learning strategy for interpretation of spectroscopic observables. STRUCTURAL DYNAMICS (MELVILLE, N.Y.) 2023; 10:064101. [PMID: 37941993 PMCID: PMC10629969 DOI: 10.1063/4.0000215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/19/2023] [Accepted: 10/17/2023] [Indexed: 11/10/2023]
Abstract
Accurate computations of experimental observables are essential for interpreting the high information content held within x-ray spectra. However, for complicated systems this can be difficult, a challenge compounded when dynamics becomes important owing to the large number of calculations required to capture the time-evolving observable. While machine learning architectures have been shown to represent a promising approach for rapidly predicting spectral lineshapes, achieving simultaneously accurate and sufficiently comprehensive training data is challenging. Herein, we introduce Δ-learning for x-ray spectroscopy. Instead of directly learning the structure-spectrum relationship, the Δ-model learns the structure dependent difference between a higher and lower level of theory. Consequently, once developed these models can be used to translate spectral shapes obtained from lower levels of theory to mimic those corresponding to higher levels of theory. Ultimately, this achieves accurate simulations with a much reduced computational burden as only the lower level of theory is computed, while the model can instantaneously transform this to a spectrum equivalent to a higher level of theory. Our present model, demonstrated herein, learns the difference between TDDFT(BLYP) and TDDFT(B3LYP) spectra. Its effectiveness is illustrated using simulations of Rh L3-edge spectra tracking the C-H activation of octane by a cyclopentadienyl rhodium carbonyl complex.
Collapse
Affiliation(s)
- Luke Watson
- Chemistry, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom
| | - Thomas Pope
- Chemistry, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom
| | - Raphael M. Jay
- Department of Physics and Astronomy, Uppsala University, 751 20 Uppsala, Sweden
| | - Ambar Banerjee
- Department of Physics and Astronomy, Uppsala University, 751 20 Uppsala, Sweden
| | - Philippe Wernet
- Department of Physics and Astronomy, Uppsala University, 751 20 Uppsala, Sweden
| | - Thomas J. Penfold
- Chemistry, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom
| |
Collapse
|
8
|
Vogt LI, Cotelesage JJH, Dolgova NV, Boyes C, Qureshi M, Sokaras D, Sharifi S, George SJ, Pickering IJ, George GN. Sulfur X-ray Absorption and Emission Spectroscopy of Organic Sulfones. J Phys Chem A 2023; 127:3692-3704. [PMID: 36912654 DOI: 10.1021/acs.jpca.2c08647] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/14/2023]
Abstract
The sulfones are a widespread group of organo-sulfur compounds, which contain the sulfonyl SO2 group attached to two carbons and have a formal sulfur oxidation state of +2. We have examined the sulfur K near-edge X-ray absorption spectroscopy (XAS) of a range of different sulfones and find substantial spectroscopic variability depending upon the nature of the coordination to the sulfonyl group. We have also examined the sulfur Kβ X-ray emission spectroscopy (XES) of selected representative sulfones. Density functional theory simulations show satisfactory reproduction of both absorption and emission spectra while enabling assignment of the various transitions comprising the spectra. The correspondence between observed and simulated spectra shows promise for ab initio prediction of sulfur X-ray absorption and emission spectra of sulfones of any substituent. The absorption spectra and, to a lesser extent, the emission spectra are sensitive to the nature of the organic groups bound to the sulfonyl (SO2) moiety, clearly showing the potential of X-ray spectroscopy as an in situ probe of sulfone chemistry.
Collapse
Affiliation(s)
- Linda I Vogt
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Julien J H Cotelesage
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Natalia V Dolgova
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Curtis Boyes
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada
| | - Muhammad Qureshi
- Stanford Synchrotron Radiation Lightsource, SLAC National Accelerator Laboratory, Stanford University, Menlo Park, California 94025, United States
| | - Dimosthenis Sokaras
- Stanford Synchrotron Radiation Lightsource, SLAC National Accelerator Laboratory, Stanford University, Menlo Park, California 94025, United States
| | - Samin Sharifi
- Chevron Energy Technology Company, Richmond, California 94802, United States
| | - Simon J George
- Simon Scientific, P.O. Box 71024, Richmond, California 94807, United States
| | - Ingrid J Pickering
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada.,Department of Chemistry, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5C9, Canada
| | - Graham N George
- Molecular and Environmental Sciences Group, Department of Geological Sciences, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5E2, Canada.,Department of Chemistry, University of Saskatchewan, Saskatoon, Saskatchewan S7N 5C9, Canada
| |
Collapse
|
9
|
Rana R, Vila FD, Kulkarni AR, Bare SR. Bridging the Gap between the X-ray Absorption Spectroscopy and the Computational Catalysis Communities in Heterogeneous Catalysis: A Perspective on the Current and Future Research Directions. ACS Catal 2022. [DOI: 10.1021/acscatal.2c03863] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Rachita Rana
- Department of Chemical Engineering, University of California, Davis, California95616, United States
| | - Fernando D. Vila
- Department of Physics, University of Washington, Seattle, Washington98195, United States
| | - Ambarish R. Kulkarni
- Department of Chemical Engineering, University of California, Davis, California95616, United States
| | - Simon R. Bare
- Stanford Synchrotron Radiation Lightsource, SLAC National Accelerator Laboratory, Menlo Park, California94025, United States
| |
Collapse
|
10
|
Penfold TJ, Rankine CD. A deep neural network for valence-to-core X-ray emission spectroscopy. Mol Phys 2022. [DOI: 10.1080/00268976.2022.2123406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
Affiliation(s)
- T. J. Penfold
- Chemistry–School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne, UK
| | - C. D. Rankine
- Chemistry–School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne, UK
| |
Collapse
|
11
|
Jang I, Kaur S, Yethiraj A. Importance of feature construction in machine learning for phase transitions. J Chem Phys 2022; 157:094904. [DOI: 10.1063/5.0102187] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
Machine learning is an important tool in the study of the phase behavior from molecular simulations. In this work we use un-supervised machine learning methods to study the phase behavior of two off-lattice models, a binary Lennard-Jones (LJ) mixture and the Widom-Rowlinson (WR) mixture. We find that the choice of the feature vector is crucial to the ability of the algorithm to predict a phase transition. We consider two feature vectors, one where the elements are distances of the particles of a given species from a probe (distance-based feature) and one where the elements are +1 if there is an excess of particles of the same species within a cut-off distance and -1 otherwise (affinity-based feature). We use principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) methods to investigate the phase behavior at a critical composition. We find that the choice of the feature vector is key to the success of unsupervised machine learning algorithm in predicting the phase behavior, and the sophistication of the machine learning algorithm is of secondary importance. In the case of the LJ mixture both feature vectors are adequate to accurately predict the critical point, but in the case of the WR mixture the affinity-based feature vector provides accurate estimates of the critical point, but the distance-based feature vector does not provide a clear signature of the phase transition. The study suggests that physical insight in choice of input features is an important aspect of implementing machine learning methods.
Collapse
Affiliation(s)
- Inhyuk Jang
- University of Wisconsin-Madison, United States of America
| | - Supreet Kaur
- University of Wisconsin-Madison, United States of America
| | - Arun Yethiraj
- Department of Chemistry, University of Wisconsin Madison, United States of America
| |
Collapse
|
12
|
Tetef S, Kashyap V, Holden WM, Velian A, Govind N, Seidler GT. Informed Chemical Classification of Organophosphorus Compounds via Unsupervised Machine Learning of X-ray Absorption Spectroscopy and X-ray Emission Spectroscopy. J Phys Chem A 2022; 126:4862-4872. [PMID: 35839329 DOI: 10.1021/acs.jpca.2c03635] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
We analyze an ensemble of organophosphorus compounds to form an unbiased characterization of the information encoded in their X-ray absorption near-edge structure (XANES) and valence-to-core X-ray emission spectra (VtC-XES). Data-driven emergence of chemical classes via unsupervised machine learning, specifically cluster analysis in the Uniform Manifold Approximation and Projection (UMAP) embedding, finds spectral sensitivity to coordination, oxidation, aromaticity, intramolecular hydrogen bonding, and ligand identity. Subsequently, we implement supervised machine learning via Gaussian process classifiers to identify confidence in predictions that match our initial qualitative assessments of clustering. The results further support the benefit of utilizing unsupervised machine learning as a precursor to supervised machine learning, which we term Unsupervised Validation of Classes (UVC), a result that goes beyond the present case of X-ray spectroscopies.
Collapse
Affiliation(s)
- Samantha Tetef
- Department of Physics, University of Washington, Seattle, Washington 98195, United States
| | - Vikram Kashyap
- Department of Physics, University of Washington, Seattle, Washington 98195, United States
| | - William M Holden
- Department of Physics, University of Washington, Seattle, Washington 98195, United States
| | - Alexandra Velian
- Department of Chemistry, University of Washington, Seattle, Washington 98195, United States
| | - Niranjan Govind
- Physical and Computational Sciences Directorate, Pacific Northwest National Laboratory, Richland, Washington 99352, United States
| | - Gerald T Seidler
- Department of Physics, University of Washington, Seattle, Washington 98195, United States
| |
Collapse
|
13
|
Nascimento DR, Govind N. Computational approaches for XANES, VtC-XES, and RIXS using linear-response time-dependent density functional theory based methods. Phys Chem Chem Phys 2022; 24:14680-14691. [PMID: 35699090 DOI: 10.1039/d2cp01132h] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
Abstract
The emergence of state-of-the-art X-ray light sources has paved the way for novel spectroscopies that take advantage of their atomic specificity to shed light on fundamental physical, chemical, and biological processes both in the static and time domains. The success of these experiments hinges on the ability to interpret and predict core-level spectra, which has opened avenues for theory to play a key role. Over the last two decades, linear-response time-dependent density functional theory (LR-TDDFT), despite various theoretical challenges, has become a computationally attractive and versatile framework to study excited-state spectra including X-ray spectroscopies. In this context, we focus our discussion on LR-TDDFT approaches for the computation of X-ray Near-Edge Structure (XANES), Valence-to-Core X-ray Emission (VtC-XES), and Resonant Inelastic X-ray Scattering (RIXS) spectroscopies in molecular systems with an emphasis on Gaussian basis set implementations. We illustrate these approaches with applications and provide a brief outlook of possible new directions.
Collapse
Affiliation(s)
- Daniel R Nascimento
- Department of Chemistry, The University of Memphis, Memphis, TN, 38152, USA.
| | - Niranjan Govind
- Physical and Computational Sciences Directorate, Pacific Northwest National Laboratory, Richland, Washington 99352, USA.
| |
Collapse
|
14
|
Rankine CD, Penfold TJ. Accurate, affordable, and generalizable machine learning simulations of transition metal x-ray absorption spectra using the XANESNET deep neural network. J Chem Phys 2022; 156:164102. [PMID: 35490005 DOI: 10.1063/5.0087255] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Abstract
The affordable, accurate, and generalizable prediction of spectroscopic observables plays a key role in the analysis of increasingly complex experiments. In this article, we develop and deploy a deep neural network-XANESNET-for predicting the lineshape of first-row transition metal K-edge x-ray absorption near-edge structure (XANES) spectra. XANESNET predicts the spectral intensities using only information about the local coordination geometry of the transition metal complexes encoded in a feature vector of weighted atom-centered symmetry functions. We address in detail the calibration of the feature vector for the particularities of the problem at hand, and we explore the individual feature importance to reveal the physical insight that XANESNET obtains at the Fe K-edge. XANESNET relies on only a few judiciously selected features-radial information on the first and second coordination shells suffices along with angular information sufficient to separate satisfactorily key coordination geometries. The feature importance is found to reflect the XANES spectral window under consideration and is consistent with the expected underlying physics. We subsequently apply XANESNET at nine first-row transition metal (Ti-Zn) K-edges. It can be optimized in as little as a minute, predicts instantaneously, and provides K-edge XANES spectra with an average accuracy of ∼±2%-4% in which the positions of prominent peaks are matched with a >90% hit rate to sub-eV (∼0.8 eV) error.
Collapse
Affiliation(s)
- C D Rankine
- Chemistry-School of Natural and Environmental Sciences, Newcastle University, Newcastle Upon Tyne NE1 7RU, United Kingdom
| | - T J Penfold
- Chemistry-School of Natural and Environmental Sciences, Newcastle University, Newcastle Upon Tyne NE1 7RU, United Kingdom
| |
Collapse
|