Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships
Abstract
X-ray absorption spectroscopy (XAS) produces a wealth of information about the local structure of materials, but interpretation of spectra often relies on easily accessible trends and prior assumptions about the structure. Recently, researchers have demonstrated that machine learning models can automate this process to predict the coordinating environments of absorbing atoms from their XAS spectra. However, machine learning models are often difficult to interpret, making it challenging to determine when they are valid and whether they are consistent with physical theories. In this work, we present three main advances to the data-driven analysis of XAS spectra: we demonstrate the efficacy of random forests in solving two new property determination tasks (predicting Bader charge and mean nearest neighbor distance), we address how choices in data representation affect model interpretability and accuracy, and we show that multiscale featurization can elucidate the regions and trends in spectra that encode various local properties. The multiscale featurization transforms the spectrum into a vector of polynomial-fit features, and is contrasted with the commonly-used “pointwise” featurization that directly uses the entire spectrum as input. We find that across thousands of transition metal oxide spectra, the relative importance of features describing the curvature of the spectrum can bemore »
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES)
- OSTI Identifier:
- 1643957
- Alternate Identifier(s):
- OSTI ID: 1756396
- Grant/Contract Number:
- FG02-23 97ER25308; AC02-05CH11231; FG02-97ER2530; FP00007929
- Resource Type:
- Published Article
- Journal Name:
- npj Computational Materials
- Additional Journal Information:
- Journal Name: npj Computational Materials Journal Volume: 6 Journal Issue: 1; Journal ID: ISSN 2057-3960
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United Kingdom
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; Atomistic models; characterization and analytical techniques; structure of solids and liquids; theoretical chemistry
Citation Formats
Torrisi, Steven B., Carbone, Matthew R., Rohr, Brian A., Montoya, Joseph H., Ha, Yang, Yano, Junko, Suram, Santosh K., and Hung, Linda. Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships. United Kingdom: N. p., 2020.
Web. doi:10.1038/s41524-020-00376-6.
Torrisi, Steven B., Carbone, Matthew R., Rohr, Brian A., Montoya, Joseph H., Ha, Yang, Yano, Junko, Suram, Santosh K., & Hung, Linda. Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships. United Kingdom. https://doi.org/10.1038/s41524-020-00376-6
Torrisi, Steven B., Carbone, Matthew R., Rohr, Brian A., Montoya, Joseph H., Ha, Yang, Yano, Junko, Suram, Santosh K., and Hung, Linda. Wed .
"Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships". United Kingdom. https://doi.org/10.1038/s41524-020-00376-6.
@article{osti_1643957,
title = {Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships},
author = {Torrisi, Steven B. and Carbone, Matthew R. and Rohr, Brian A. and Montoya, Joseph H. and Ha, Yang and Yano, Junko and Suram, Santosh K. and Hung, Linda},
abstractNote = {X-ray absorption spectroscopy (XAS) produces a wealth of information about the local structure of materials, but interpretation of spectra often relies on easily accessible trends and prior assumptions about the structure. Recently, researchers have demonstrated that machine learning models can automate this process to predict the coordinating environments of absorbing atoms from their XAS spectra. However, machine learning models are often difficult to interpret, making it challenging to determine when they are valid and whether they are consistent with physical theories. In this work, we present three main advances to the data-driven analysis of XAS spectra: we demonstrate the efficacy of random forests in solving two new property determination tasks (predicting Bader charge and mean nearest neighbor distance), we address how choices in data representation affect model interpretability and accuracy, and we show that multiscale featurization can elucidate the regions and trends in spectra that encode various local properties. The multiscale featurization transforms the spectrum into a vector of polynomial-fit features, and is contrasted with the commonly-used “pointwise” featurization that directly uses the entire spectrum as input. We find that across thousands of transition metal oxide spectra, the relative importance of features describing the curvature of the spectrum can be localized to individual energy ranges, and we can separate the importance of constant, linear, quadratic, and cubic trends, as well as the white line energy. This work has the potential to assist rigorous theoretical interpretations, expedite experimental data collection, and automate analysis of XAS spectra, thus accelerating the discovery of new functional materials.},
doi = {10.1038/s41524-020-00376-6},
journal = {npj Computational Materials},
number = 1,
volume = 6,
place = {United Kingdom},
year = {Wed Jul 29 00:00:00 EDT 2020},
month = {Wed Jul 29 00:00:00 EDT 2020}
}
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1038/s41524-020-00376-6
https://doi.org/10.1038/s41524-020-00376-6
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 48 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
“Inverting” X-ray Absorption Spectra of Catalysts by Machine Learning in Search for Activity Descriptors
journal, September 2019
- Timoshenko, Janis; Frenkel, Anatoly I.
- ACS Catalysis, Vol. 9, Issue 11
α-Fe 2 O 3 Nanoparticles as Oxygen Carriers for Chemical Looping Combustion: An Integrated Materials Characterization Approach to Understanding Oxygen Carrier Performance, Reduction Mechanism, and Particle Size Effects
journal, June 2018
- Alalwan, Hayder A.; Mason, Sara E.; Grassian, Vicki H.
- Energy & Fuels, Vol. 32, Issue 7
Supervised Machine-Learning-Based Determination of Three-Dimensional Structure of Metallic Nanoparticles
journal, October 2017
- Timoshenko, Janis; Lu, Deyu; Lin, Yuewei
- The Journal of Physical Chemistry Letters, Vol. 8, Issue 20
Elucidating the Evolving Atomic Structure in Atomic Layer Deposition Reactions with in Situ XANES and Machine Learning
journal, October 2019
- Trejo, Orlando; Dadlani, Anup L.; De La Paz, Francisco
- Chemistry of Materials, Vol. 31, Issue 21
Classification of local chemical environments from x-ray absorption spectra using supervised machine learning
journal, March 2019
- Carbone, Matthew R.; Yoo, Shinjae; Topsakal, Mehmet
- Physical Review Materials, Vol. 3, Issue 3
Catalyst discovery through megalibraries of nanomaterials
journal, December 2018
- Kluender, Edward J.; Hedrick, James L.; Brown, Keith A.
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 1
Assignment of pre-edge peaks in K-edge x-ray absorption spectra of 3d transition metal compounds: electric dipole or quadrupole?
journal, November 2008
- Yamamoto, Takashi
- X-Ray Spectrometry, Vol. 37, Issue 6
Chemical imaging of catalytic solids with synchrotron radiation
journal, January 2010
- Beale, Andrew M.; Jacques, Simon D. M.; Weckhuysen, Bert M.
- Chemical Society Reviews, Vol. 39, Issue 12
Chemical Imaging of Spatial Heterogeneities in Catalytic Solids at Different Length and Time Scales
journal, June 2009
- Weckhuysen, Bert M.
- Angewandte Chemie International Edition, Vol. 48, Issue 27
Atomate: A high-level interface to generate, execute, and analyze computational materials science workflows
journal, November 2017
- Mathew, Kiran; Montoya, Joseph H.; Faghaninia, Alireza
- Computational Materials Science, Vol. 139
On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets
journal, September 2014
- Kusne, Aaron Gilad; Gao, Tieren; Mehta, Apurva
- Scientific Reports, Vol. 4, Issue 1
Double perovskites as a family of highly active catalysts for oxygen evolution in alkaline solution
journal, September 2013
- Grimaud, Alexis; May, Kevin J.; Carlton, Christopher E.
- Nature Communications, Vol. 4, Issue 1
The Electronic Structure of the Metal Active Site Determines the Geometric Structure and Function of the Metalloregulator NikR
journal, July 2019
- Ha, Yang; Hu, Heidi; Higgins, Khadine
- Biochemistry, Vol. 58, Issue 34
Oxidation state and coordination of Fe in minerals: An Fe K- XANES spectroscopic study
journal, May 2001
- Wilke, Max; Farges, François; Petit, Pierre-Emmanuel
- American Mineralogist, Vol. 86, Issue 5-6
-edge absorption spectra of selected vanadium compounds
journal, November 1984
- Wong, J.; Lytle, F. W.; Messmer, R. P.
- Physical Review B, Vol. 30, Issue 10
exciting: a full-potential all-electron package implementing density-functional theory and many-body perturbation theory
journal, August 2014
- Gulans, Andris; Kontur, Stefan; Meisenbichler, Christian
- Journal of Physics: Condensed Matter, Vol. 26, Issue 36
Analyzing machine learning models to accelerate generation of fundamental materials insights
journal, March 2019
- Umehara, Mitsutaro; Stein, Helge S.; Guevarra, Dan
- npj Computational Materials, Vol. 5, Issue 1
CRYSTAL: a multi-agent AI system for automated mapping of materials' crystal structures
journal, April 2019
- Gomes, Carla P.; Bai, Junwen; Xue, Yexiang
- MRS Communications, Vol. 9, Issue 02
A fast and robust algorithm for Bader decomposition of charge density
journal, June 2006
- Henkelman, Graeme; Arnaldsson, Andri; Jónsson, Hannes
- Computational Materials Science, Vol. 36, Issue 3
Parameter-free calculations of X-ray spectra with FEFF9
journal, January 2010
- Rehr, John J.; Kas, Joshua J.; Vila, Fernando D.
- Physical Chemistry Chemical Physics, Vol. 12, Issue 21
Laboratory von Hámos X-ray spectroscopy for routine sample characterization
journal, October 2016
- Németh, Zoltán; Szlachetko, Jakub; Bajnóczi, Éva G.
- Review of Scientific Instruments, Vol. 87, Issue 10
Next-Generation Experimentation with Self-Driving Laboratories
journal, June 2019
- Häse, Florian; Roch, Loïc M.; Aspuru-Guzik, Alán
- Trends in Chemistry, Vol. 1, Issue 3
Probing Atomic Distributions in Mono- and Bimetallic Nanoparticles by Supervised Machine Learning
journal, December 2018
- Timoshenko, Janis; Wrasman, Cody J.; Luneau, Mathilde
- Nano Letters, Vol. 19, Issue 1
A facile method for sodium-modified Fe 2 O 3 /Al 2 O 3 oxygen carrier by an air atmospheric pressure plasma jet for chemical looping combustion process
journal, May 2017
- Huang, Wei-Chen; Kuo, Yu-Lin; Su, Yu-Ming
- Chemical Engineering Journal, Vol. 316
Geometrical fitting of experimental XANES spectra by a full multiple-scattering procedure
journal, June 2001
- Benfatto, M.; Della Longa, S.
- Journal of Synchrotron Radiation, Vol. 8, Issue 4
Neural Network Approach for Characterizing Structural Transformations by X-Ray Absorption Fine Structure Spectroscopy
journal, May 2018
- Timoshenko, Janis; Anspoks, Andris; Cintins, Arturs
- Physical Review Letters, Vol. 120, Issue 22
Ab initio theory and calculations of X-ray spectra
journal, July 2009
- Rehr, John J.; Kas, Joshua J.; Prange, Micah P.
- Comptes Rendus Physique, Vol. 10, Issue 6
Transition elements in water-bearing silicate glasses/melts. part I. a high-resolution and anharmonic analysis of Ni coordination environments in crystals, glasses, and melts
journal, May 2001
- Farges, François; Brown, Gordon E.; Petit, Pierre-Emmanuel
- Geochimica et Cosmochimica Acta, Vol. 65, Issue 10
Sensitivity of Pt x-ray absorption near edge structure to the morphology of small Pt clusters
journal, February 2002
- Ankudinov, A. L.; Rehr, J. J.; Low, John J.
- The Journal of Chemical Physics, Vol. 116, Issue 5
Ab initio and experimental pre-edge investigations of the Mn -edge XANES in oxide-type materials
journal, April 2005
- Farges, François
- Physical Review B, Vol. 71, Issue 15
MXAN : a new software procedure to perform geometrical fitting of experimental XANES spectra
journal, March 2001
- Benfatto, M.; Congiu-Castellano, A.; Daniele, A.
- Journal of Synchrotron Radiation, Vol. 8, Issue 2
Machine Learning Prediction of H Adsorption Energies on Ag Alloys
journal, January 2019
- Hoyt, Robert A.; Montemore, Matthew M.; Fampiou, Ioanna
- Journal of Chemical Information and Modeling, Vol. 59, Issue 4
Hubbard model corrections in real-space x-ray spectroscopy theory
journal, April 2012
- Ahmed, Towfiq; Kas, J. J.; Rehr, J. J.
- Physical Review B, Vol. 85, Issue 16
Quantitative structural determination of active sites from in situ and operando XANES spectra: From standard ab initio simulations to chemometric and machine learning approaches
journal, October 2019
- Guda, Alexander A.; Guda, Sergey A.; Lomachenko, Kirill A.
- Catalysis Today, Vol. 336
Cr K-Edge XANES Spectroscopy: Ligand and Oxidation State Dependence — What is Oxidation State?
conference, January 2007
- Tromp, Moniek; Moulin, Jerome; Reid, Gillian
- X-RAY ABSORPTION FINE STRUCTURE - XAFS13: 13th International Conference, AIP Conference Proceedings
Efficient implementation of core-excitation Bethe–Salpeter equation calculations
journal, December 2015
- Gilmore, K.; Vinson, John; Shirley, E. L.
- Computer Physics Communications, Vol. 197
Bethe-Salpeter equation calculations of core excitation spectra
journal, March 2011
- Vinson, J.; Rehr, J. J.; Kas, J. J.
- Physical Review B, Vol. 83, Issue 11
The Mn K Absorption Edge in Manganese Metal and Manganese Compounds
journal, July 1949
- Hanson, Harold; Beeman, W. W.
- Physical Review, Vol. 76, Issue 1
SciPy 1.0: fundamental algorithms for scientific computing in Python
journal, February 2020
- Virtanen, Pauli; Gommers, Ralf; Oliphant, Travis E.
- Nature Methods
Functional mapping reveals mechanistic clusters for OER catalysis across (Cu–Mn–Ta–Co–Sn–Fe)O x composition and pH space
journal, January 2019
- Stein, Helge S.; Guevarra, Dan; Shinde, Aniketa
- Materials Horizons, Vol. 6, Issue 6
Automated generation and ensemble-learned matching of X-ray absorption spectra
journal, March 2018
- Zheng, Chen; Mathew, Kiran; Chen, Chi
- npj Computational Materials, Vol. 4, Issue 1
New Technique for Investigating Noncrystalline Structures: Fourier Analysis of the Extended X-Ray—Absorption Fine Structure
journal, November 1971
- Sayers, Dale E.; Stern, Edward A.; Lytle, Farrel W.
- Physical Review Letters, Vol. 27, Issue 18
Multi-spectroscopic study of Fe(II) in silicate glasses: Implications for the coordination environment of Fe(II) in silicate melts
journal, September 2005
- Jackson, William E.; Farges, Francois; Yeager, Mark
- Geochimica et Cosmochimica Acta, Vol. 69, Issue 17
A linear dependence of energy levels on the valency of elements
journal, January 1932
- Kunzl, V.
- Collection of Czechoslovak Chemical Communications, Vol. 4
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
journal, December 2015
- Kirklin, Scott; Saal, James E.; Meredig, Bryce
- npj Computational Materials, Vol. 1, Issue 1
Accelerating the discovery of materials for clean energy in the era of smart automation
journal, April 2018
- Tabor, Daniel P.; Roch, Loïc M.; Saikin, Semion K.
- Nature Reviews Materials, Vol. 3, Issue 5
X-ray absorption spectroscopy
journal, August 2009
- Yano, Junko; Yachandra, Vittal K.
- Photosynthesis Research, Vol. 102, Issue 2-3
On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events
journal, March 2020
- Vandermause, Jonathan; Torrisi, Steven B.; Batzner, Simon
- npj Computational Materials, Vol. 6, Issue 1
propnet: A Knowledge Graph for Materials Science
journal, February 2020
- Mrdjenovich, David; Horton, Matthew K.; Montoya, Joseph H.
- Matter, Vol. 2, Issue 2
EXAFS: new horizons in structure determinations
journal, June 1978
- Eisenberger, P.; Kincaid, B.
- Science, Vol. 200, Issue 4349
Revealing Electronic Signatures of Lattice Oxygen Redox in Lithium Ruthenates and Implications for High-Energy Li-Ion Battery Material Designs
journal, September 2019
- Yu, Yang; Karayaylali, Pinar; Nowak, Stanisław H.
- Chemistry of Materials, Vol. 31, Issue 19
Matminer: An open source toolkit for materials data mining
journal, September 2018
- Ward, Logan; Dunn, Alexander; Faghaninia, Alireza
- Computational Materials Science, Vol. 152
Coordination chemistry of Ti(IV) in silicate glasses and melts: II. Glasses at ambient temperature and pressure
journal, August 1996
- Farges, Franois; Brown, Gordon E.; Navrotsky, Alexandra
- Geochimica et Cosmochimica Acta, Vol. 60, Issue 16
Coordination and Oxidation State Analysis of Cobalt in Nanocrystalline LiGa 5 O 8 by X-ray Absorption Spectroscopy
journal, April 2013
- Yildirim, B.; Riesen, H.
- Journal of Physics: Conference Series, Vol. 430
EXAFS and XANES analysis of oxides at the nanoscale
journal, October 2014
- Kuzmin, Alexei; Chaboy, Jesús
- IUCrJ, Vol. 1, Issue 6
Adventures in DFT by a wavefunction theorist
journal, October 2019
- Bartlett, Rodney J.
- The Journal of Chemical Physics, Vol. 151, Issue 16
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013
- Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
- APL Materials, Vol. 1, Issue 1
Experiment Specification, Capture and Laboratory Automation Technology (ESCALATE): a software pipeline for automated chemical experimentation and data management
journal, June 2019
- Pendleton, Ian M.; Cattabriga, Gary; Li, Zhi
- MRS Communications, Vol. 9, Issue 3
The MXAN procedure: a new method for analysing the XANES spectra of metalloproteins to obtain structural quantitative information
journal, December 2002
- Benfatto, M.; Della Longa, S.; Natoli, C. R.
- Journal of Synchrotron Radiation, Vol. 10, Issue 1
Random Forest Models for Accurate Identification of Coordination Environments from X-Ray Absorption Near-Edge Structure
journal, May 2020
- Zheng, Chen; Chen, Chi; Chen, Yiming
- Patterns, Vol. 1, Issue 2
Redox activity of surface oxygen anions in oxygen-deficient perovskite oxides during electrochemical reactions
journal, January 2015
- Mueller, David N.; Machala, Michael L.; Bluhm, Hendrik
- Nature Communications, Vol. 6, Issue 1
The oxidation state of iron determined by Fe K-edge XANES—application to iron gall ink in historical manuscripts
journal, January 2009
- Wilke, Max; Hahn, Oliver; Woodland, Alan B.
- Journal of Analytical Atomic Spectrometry, Vol. 24, Issue 10
Prediction of Synthesis of 2D Metal Carbides and Nitrides (MXenes) and Their Precursors with Positive and Unlabeled Machine Learning
journal, March 2019
- Frey, Nathan C.; Wang, Jin; Vega Bellido, Gabriel Iván
- ACS Nano, Vol. 13, Issue 3
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
journal, October 2019
- Selvaraju, Ramprasaath R.; Cogswell, Michael; Das, Abhishek
- International Journal of Computer Vision, Vol. 128, Issue 2
High-throughput computational X-ray absorption spectroscopy
journal, July 2018
- Mathew, Kiran; Zheng, Chen; Winston, Donald
- Scientific Data, Vol. 5, Issue 1
Spatial and temporal exploration of heterogeneous catalysts with synchrotron radiation
journal, August 2018
- Meirer, Florian; Weckhuysen, Bert M.
- Nature Reviews Materials, Vol. 3, Issue 9
Automated Phase Mapping with AgileFD and its Application to Light Absorber Discovery in the V–Mn–Nb Oxide System
journal, December 2016
- Suram, Santosh K.; Xue, Yexiang; Bai, Junwen
- ACS Combinatorial Science, Vol. 19, Issue 1
Ti -edge XANES studies of Ti coordination and disorder in oxide compounds: Comparison between theory and experiment
journal, July 1997
- Farges, François; Brown, Gordon E.; Rehr, J. J.
- Physical Review B, Vol. 56, Issue 4
PyFitit: The software for quantitative analysis of XANES spectra using machine-learning algorithms
journal, May 2020
- Martini, A.; Guda, S. A.; Guda, A. A.
- Computer Physics Communications, Vol. 250
Addressing electron-hole correlation in core excitations of solids: An all-electron many-body approach from first principles
journal, April 2017
- Vorwerk, Christian; Cocchi, Caterina; Draxl, Claudia
- Physical Review B, Vol. 95, Issue 15
XAS study of Mn, Fe and Cu as indicators of historical glass decay
journal, January 2013
- Abuín, M.; Serrano, A.; Chaboy, J.
- Journal of Analytical Atomic Spectrometry, Vol. 28, Issue 7
The NumPy Array: A Structure for Efficient Numerical Computation
journal, March 2011
- van der Walt, Stéfan; Colbert, S. Chris; Varoquaux, Gaël
- Computing in Science & Engineering, Vol. 13, Issue 2
Theoretical approaches to x-ray absorption fine structure
journal, July 2000
- Rehr, J. J.; Albers, R. C.
- Reviews of Modern Physics, Vol. 72, Issue 3
Soft X‐Ray Absorption Edges of Metal Ions in Complexes. III. Zinc (II) Complexes
journal, January 1958
- Cotton, F. Albert; Hanson, Harold P.
- The Journal of Chemical Physics, Vol. 28, Issue 1
Sulfur K-Edge X-ray Absorption Spectroscopy as a Probe of Ligand−Metal Bond Covalency: Metal vs Ligand Oxidation in Copper and Nickel Dithiolene Complexes
journal, February 2007
- Sarangi, Ritimukta; DeBeer George, Serena; Rudd, Deanne Jackson
- Journal of the American Chemical Society, Vol. 129, Issue 8
Theoretical x-ray absorption Debye-Waller factors
journal, July 2007
- Vila, Fernando D.; Rehr, J. J.; Rossner, H. H.
- Physical Review B, Vol. 76, Issue 1
Bethe–Salpeter equation for absorption and scattering spectroscopy: implementation in the exciting code
journal, August 2019
- Vorwerk, Christian; Aurich, Benjamin; Cocchi, Caterina
- Electronic Structure, Vol. 1, Issue 3
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013
- Ong, Shyue Ping; Richards, William Davidson; Jain, Anubhav
- Computational Materials Science, Vol. 68