Machine learning approaches to XANES spectra for quantitative 3D structural determination: The case of CO2 adsorption on CPO-27-Ni MOF

Abstract In this work we have applied machine learning methods (Extra Trees, Ridge Regression and Neural Networks) to predict structural parameters of the system based on its XANES spectrum. We used two ML approaches: direct one, i.e. when ML model is trained to predict the structural parameters directly from the XANES spectrum and inverse one when ML model is used to approximate spectrum as a function of structural parameters. We show the applicability of several ML approaches to predict the geometry of CO2 molecule adsorbed on Ni2+ surface sites hosted in the channels of CPO-27-Ni metal-organic framework. Quantitative fitting is based on difference XANES spectra and we discuss advantages and disadvantages of the two ML approaches and critically examine the overfitting phenomenon, caused by systematic differences of experimental data and learning dataset.

• Publication year

  2020

• Venue

  Radiation Physics and Chemistry

• Publication date

  2020-10-01

• Fields of study

  Materials Science, Chemistry

• Identifiers
  DOI 10.1016/J.RADPHYSCHEM.2019.108430
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra

  2019cited by this paper
• Towards calibration-invariant spectroscopy using deep learning

  2019cited by this paper
• Evolution of Pt and Pd species in functionalized UiO-67 metal-organic frameworks

  2019cited by this paper
• Quantitative structural determination of active sites from in situ and operando XANES spectra: From standard ab initio simulations to chemometric and machine learning approaches

  2019cited by this paper
• Neural Network Approach for Characterizing Structural Transformations by X-Ray Absorption Fine Structure Spectroscopy.

  2018cited by this paper
• Palladium Carbide and Hydride Formation in the Bulk and at the Surface of Palladium Nanoparticles

  2018cited by this paper
• Composition-driven Cu-speciation and reducibility in Cu-CHA zeolite catalysts: a multivariate XAS/FTIR approach to complexity

  2017cited by this paper
• In situ formation of hydrides and carbides in palladium catalyst: When XANES is better than EXAFS and XRD

  2017cited by this paper
• Exploring structure and reactivity of Cu sites in functionalized UiO-67 MOFs

  2017cited by this paper
• Improved Infrared Spectra Prediction by DFT from a New Experimental Database.

  2017cited by this paper
• Effect of Molecular Guest Binding on the d-d Transitions of Ni2+ of CPO-27-Ni: A Combined UV-Vis, Resonant-Valence-to-Core X-ray Emission Spectroscopy, and Theoretical Study.

  2017cited by this paper
• Automated generation and ensemble-learned matching of X-ray absorption spectra

  2017cited by this paper
• Reversible Capture and Release of Cl2 and Br2 with a Redox-Active Metal-Organic Framework.

  2017cited by this paper
• Ligands Make the Difference! Molecular Insights into CrVI/SiO2 Phillips Catalyst during Ethylene Polymerization.

  2017cited by this paper
• Optimized Finite Difference Method for the Full-Potential XANES Simulations: Application to Molecular Adsorption Geometries in MOFs and Metal-Ligand Intersystem Crossing Transients.

  2015cited by this paper
• Multivariate analysis, chemometrics, and machine learning in laser spectroscopy

  2014cited by this paper
• Reactivity of surface species in heterogeneous catalysts probed by in situ X-ray absorption techniques.

  2013cited by this paper
• Structure–activity relationships of simple molecules adsorbed on CPO-27-Ni metal–organic framework: In situ experiments vs. theory

  2012cited by this paper
• Direct evidence of adsorption induced Cr(II) mobility on the SiO(2) surface upon complexation by CO.

  2010cited by this paper
• Scaling Factors and Uncertainties for ab Initio Anharmonic Vibrational Frequencies.

  2010cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition

  2009cited by this paper
• CO Adsorption on CPO-27-Ni Coordination Polymer: Spectroscopic Features and Interaction Energy

  2009cited by this paper
• Ab initio theory and calculations of X-ray spectra

  2009cited by this paper
• Adsorption properties and structure of CO2 adsorbed on open coordination sites of metal-organic framework Ni2(dhtp) from gas adsorption, IR spectroscopy and X-ray diffraction.

  2008cited by this paper
• Local structure of CPO-27-Ni metallorganic framework upon dehydration and coordination of NO

  2008cited by this paper
• Ab‐initio simulations of materials using VASP: Density‐functional theory and beyond

  2008cited by this paper
• FitIt: New software to extract structural information on the basis of XANES fitting

  2007cited by this paper
• Quantitative local structure refinement from XANES: multi-dimensional interpolation approach.

  2006cited by this paper
• Extremely randomized trees

  2006cited by this paper
• An in situ high-temperature single-crystal investigation of a dehydrated metal-organic framework compound and field-induced magnetization of one-dimensional metal-oxygen chains.

  2005cited by this paper
• The MXAN procedure: a new method for analysing the XANES spectra of metalloproteins to obtain structural quantitative information.

  2003cited by this paper
• X-ray absorption near-edge structure calculations beyond the muffin-tin approximation

  2001cited by this paper
• Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set.

  1996cited by this paper
• Numerical Methods for the Solution of Ill-Posed Problems

  1995cited by this paper

• Advanced X-ray absorption spectroscopy for probing dynamics in CO2 reduction reaction electrocatalysts

  2025cites this paper
• Advancements in Understanding the Physicochemical Properties of Reticular Materials: An In Situ and Operando Spectroscopic Perspective

  2025cites this paper
• Sustainable carbon materials in environmental and energy applications

  2025cites this paper
• Machine Learning for Quantitative Structural Information from Infrared Spectra: The Case of Palladium Hydride

  2024cites this paper
• Toward a Machine Learning Approach to Interpreting X-ray Spectra of Trace Impurities by Converting XANES to EXAFS.

  2024cites this paper
• Adsorbate Configurations in Ni Single-Atom Catalysts during CO_{2} Electrocatalytic Reduction Unveiled by Operando XAS, XES, and Machine Learning.

  2024cites this paper
• Computational and Machine Learning Methods for CO2 Capture Using Metal-Organic Frameworks.

  2024cites this paper
• Recent Progress on Advanced Solid Adsorbents for CO2 Capture: From Mechanism to Machine Learning

  2024cites this paper
• Unifying Mixed Gas Adsorption in Molecular Sieve Membranes and MOFs using Machine Learning

  2024cites this paper
• Compact Representation of the Local Atomic Structure of Matter for Machine Learning in XANES-Spectroscopy Data Processing

  2024cites this paper
• In situ X-ray spectroscopies beyond conventional X-ray absorption spectroscopy on deciphering dynamic configuration of electrocatalysts

  2023cites this paper
• A systematic review of machine learning approaches in carbon capture applications

  2023cites this paper
• Machine learning accelerates the investigation of targeted MOFs: Performance prediction, rational design and intelligent synthesis

  2023cites this paper
• Efficient and interpretable graph network representation for angle-dependent properties applied to optical spectroscopy

  2022cites this paper
• Operando Photo-Electrochemical Catalysts Synchrotron Studies

  2022cites this paper
• Graph neural network predictions of metal organic framework CO<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e488" altimg="si38.svg"><mml:msub><mml:mrow /><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msub></mml:math> adsorption properties

  2022cites this paper
• Graph Neural Network Predictions of Metal Organic Framework CO 2 Adsorption Properties

  2022cites this paper
• Enhancing the analysis of disorder in X-ray absorption spectra: application of deep neural networks to T-jump-X-ray probe experiments.

  2021cites this paper
• Efficient, Interpretable Graph Neural Network Representation for Angle-dependent Properties and its Application to Optical Spectroscopy

  2021cites this paper
• Recent progress and application of computational chemistry to understand inorganic photochemistry

  2021cites this paper
• Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties

  2021cites this paper
• Efficient, Interpretable Atomistic Graph Neural Network Representation for Angle-dependent Properties and its Application to Optical Spectroscopy Prediction

  2021cites this paper
• On Synchrotron Radiation for Studying the Transformation of Toxic Elements in the Soil–Plant System: A Review

  2021cites this paper
• Realizing the data-driven, computational discovery of metal-organic framework catalysts

  2021cites this paper
• Machine learning powered by principal component descriptors as the key for sorted structural fit of XANES.

  2021cites this paper
• Revisiting the Extended X-ray Absorption Fine Structure Fitting Procedure through a Machine Learning-Based Approach.

  2021cites this paper
• Machine Learning Meets with Metal Organic Frameworks for Gas Storage and Separation

  2021cites this paper
• In Situ/Operando Electrocatalyst Characterization by X-ray Absorption Spectroscopy

  2020cites this paper
• “Inverting” X-ray Absorption Spectra of Catalysts by Machine Learning in Search for Activity Descriptors

  2019cites this paper