Mapping XANES spectra on structural descriptors of copper oxide clusters using supervised machine learning

Structural descriptors and information extraction from X-ray emission spectra: aqueous sulfuric acid

Machine learning can reveal new insights into X-ray spectroscopy of liquids when the local atomistic environment is presented to the model in a suitable way. Many unique structural descriptor families have been developed for this purpose. We benchmark the performance of six different descriptor families using a computational data set of 24 200 sulfur Kβ X-ray emission spectra of aqueous sulfuric acid simulated at six different concentrations. We train a feed-forward neural network to predict the spectra from the corresponding descriptor vectors and find that the local many-body tensor representation, smooth overlap of atomic positions and atom-centered symmetry functions excel in this comparison. We found a similar hierarchy when applying the emulator-based component analysis to identify and separate the spectrally relevant structural characteristics from the irrelevant ones. In this case, the spectra were dominantly dependent on the concentration of the system, whereas adding the second most significant degree of freedom in the decomposition allowed for distinction of the protonation state of the acid molecule.

Oxidizing Role of Cu Cocatalysts in Unassisted Photocatalytic CO2 Reduction Using p-GaN/Al2O3/Au/Cu Heterostructures

Photocatalytic CO2 reduction to CO under unassisted (unbiased) conditions was recently demonstrated using heterostructure catalysts that combine p-type GaN with plasmonic Au nanoparticles and Cu nanoparticles as cocatalysts (p-GaN/Al2O3/Au/Cu). Here, we investigate the mechanistic role of Cu in p-GaN/Al2O3/Au/Cu under unassisted photocatalytic operating conditions using Cu K-edge X-ray absorption spectroscopy and first-principles calculations. Upon exposure to gas-phase CO2 and H2O vapor reaction conditions, the composition of the Cu nanoparticles is identified as a mixture of CuI and CuII oxide, hydroxide, and carbonate compounds without metallic Cu. These composition changes, indicating oxidative conditions, are rationalized by bulk Pourbaix thermodynamics. Under photocatalytic operating conditions with visible light excitation of the plasmonic Au nanoparticles, further oxidation of CuI to CuII is observed, indicating light-driven hole transfer from Au-to-Cu. This observation is supported by the calculated band alignments of the oxidized Cu compositions with plasmonic Au particles, where light-driven hole transfer from Au-to-Cu is found to be thermodynamically favored. These findings demonstrate that under unassisted (unbiased) gas-phase reaction conditions, Cu is found in carbonate-rich oxidized compositions rather than metallic Cu. These species then act as the active cocatalyst and play an oxidative rather than a reductive role in catalysis when coupled with plasmonic Au particles for light absorption, possibly opening an additional channel for water oxidation in this system.

Machine learning for analysis of experimental scattering and spectroscopy data in materials chemistry

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.

Data-Driven Predetermination of Cu Oxidation State in Copper Nanoparticles: Application to the Synthesis by Laser Ablation in Liquid

Copper-based nanocrystals are reference nanomaterials for integration into emerging green technologies, with laser ablation in liquid (LAL) being a remarkable technique for their synthesis. However, the achievement of a specific type of nanocrystal, among the whole library of nanomaterials available using LAL, has been until now an empirical endeavor based on changing synthesis parameters and characterizing the products. Here, we started from the bibliographic analysis of LAL synthesis of Cu-based nanocrystals to identify the relevant physical and chemical features for the predetermination of copper oxidation state. First, single features and their combinations were screened by linear regression analysis, also using a genetic algorithm, to find the best correlation with experimental output and identify the equation giving the best prediction of the LAL results. Then, machine learning (ML) models were exploited to unravel cross-correlations between features that are hidden in the linear regression analysis. Although the LAL-generated Cu nanocrystals may be present in a range of oxidation states, from metallic copper to cuprous oxide (Cu2O) and cupric oxide (CuO), in addition to the formation of other materials such as Cu2S and CuCN, ML was able to guide the experiments toward the maximization of the compounds in the greatest demand for integration in sustainable processes. This approach is of general applicability to other nanomaterials and can help understand the origin of the chemical pathways of nanocrystals generated by LAL, providing a rational guideline for the conscious predetermination of laser-synthesis parameters toward the desired compounds.

Iterative multiscale and multi-physics computations for operando catalyst nanostructure elucidation and kinetic modeling

Modern heterogeneous catalysis has benefitted immensely from computational predictions of catalyst structure and its evolution under reaction conditions, first-principles mechanistic investigations, and detailed kinetic modeling, which are rungs on a multiscale workflow. Establishing connections across these rungs and integration with experiments have been challenging. Here, operando catalyst structure prediction techniques using density functional theory simulations and ab initio thermodynamics calculations, molecular dynamics, and machine learning techniques are presented. Surface structure characterization by computational spectroscopic and machine learning techniques is then discussed. Hierarchical approaches in kinetic parameter estimation involving semi-empirical, data-driven, and first-principles calculations and detailed kinetic modeling via mean-field microkinetic modeling and kinetic Monte Carlo simulations are discussed along with methods and the need for uncertainty quantification. With these as the background, this article proposes a bottom-up hierarchical and closed loop modeling framework incorporating consistency checks and iterative refinements at each level and across levels.

AI for Nanomaterials Development in Clean Energy and Carbon Capture, Utilization and Storage (CCUS)

Zero-carbon energy and negative emission technologies are crucial for achieving a carbon neutral future, and nanomaterials have played critical roles in advancing such technologies. More recently, due to the explosive growth in data, the adoption and exploitation of artificial intelligence (AI) as part of the materials research framework have had a tremendous impact on the development of nanomaterials. AI has enabled revolutionary next-generation paradigms to significantly accelerate all stages of material discovery and facilitate the exploration of the enormous design space. In this review, we summarize recent advancements of AI applications in nanomaterials discovery, with a special emphasis on the selected applications of AI and nanotechnology for the net-zero emission future including the development of solar cells, hydrogen energy, battery materials for renewable energy, and CO₂ capture and conversion materials for carbon capture, utilization and storage (CCUS) technologies. In addition, we discuss the limitations and challenges of current AI applications in this area by identifying the gaps that exist in current development. Finally, we present the prospect for future research directions in order to facilitate the large-scale applications of artificial intelligence for advancements in nanomaterials.

Data-Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts

The design of heterogeneous catalysts is necessarily surface-focused, generally achieved via optimization of adsorption energy and microkinetic modelling. A prerequisite is to ensure the adsorption energy is physically meaningful is the stable existence of the conceived active-site structure on the surface. The development of improved understanding of the catalyst surface, however, is challenging practically because of the complex nature of dynamic surface formation and evolution under in-situ reactions. We propose therefore data-driven machine-learning (ML) approaches as a solution. In this Minireview we summarize recent progress in using machine-learning to search and predict (meta)stable structures, assist operando simulation under reaction conditions and micro-environments, and critically analyze experimental characterization data. We conclude that ML will become the new norm to lower costs associated with discovery and design of optimal heterogeneous catalysts.

Mechanism of Catalytic CO2 Hydrogenation to Methane and Methanol Using a Bimetallic Cu3Pd Cluster at a Zirconia Support

For very small nanocluster-based catalysts, the exploration of the influence of the particle size, composition, and support offers precisely variable parameters in a wide material search space to control catalysts' performance. We present the mechanism of the CO₂ methanation reaction on the oxidized bimetallic Cu₃Pd tetramer (Cu₃PdO₂) supported on a zirconia model support represented by Zr₁₂O₂₄ based on the energy profile obtained from density functional theory calculations on the reaction of CO₂ and H₂. In order to determine the role of the Pd atom, the performance of Cu₃PdO₂ with monometallic Cu₄O₂ at the same support has been compared. Parallel to methane formation, the alternative path of methanol formation at this catalyst has also been investigated. The results show that the exchange of a single atom in Cu₄ with a single Pd atom improves catalyst/s performance via lowering the barriers associated with hydrogen dissociation steps that occur on the Pd atom. The above-mentioned results suggest that the doping strategy at the level of single atoms can offer a precise control knob for designing new catalysts with desired performance.

Informed Chemical Classification of Organophosphorus Compounds via Unsupervised Machine Learning of X-ray Absorption Spectroscopy and X-ray Emission Spectroscopy

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.

Theoretical Perspective on Operando Spectroscopy of Fluxional Nanocatalysts

Improvements in operando spectroscopy have enabled the catalysis community to investigate the dynamic nature of catalysts under operating conditions with increasing detail. Still, the highly dynamic nature of some catalysts, such as fluxional supported subnano clusters, presents a formidable challenge even for the most state-of-the-art techniques. The reason is that such fluxional catalytic interfaces contain a variety of thermally accessible states. Operando spectroscopies used in catalysis generally fall into two categories: ensemble-based techniques, which provide spectra containing the signals of the entire ensemble of states of the catalyst and are not necessarily dominated by the most active species, and localized techniques, which provide atomistic-level information about the dynamics of active sites in a very small area, which might not include the most active species. Combining many different kinds of techniques can provide detailed insight; however, we propose that effective utilization of specific computational techniques and approaches within the fluxionality paradigm can fill the gap and enable atomistic characterization of the most relevant catalytic sites.

Solving the structure of "single-atom" catalysts using machine learning - assisted XANES analysis

"Single-atom" catalysts (SACs) have demonstrated excellent activity and selectivity in challenging chemical transformations such as photocatalytic CO₂ reduction. For heterogeneous photocatalytic SAC systems, it is essential to obtain sufficient information of their structure at the atomic level in order to understand reaction mechanisms. In this work, a SAC was prepared by grafting a molecular cobalt catalyst on a light-absorbing carbon nitride surface. Due to the sensitivity of the X-ray absorption near edge structure (XANES) spectra to subtle variances in the Co SAC structure in reaction conditions, different machine learning (ML) methods, including principal component analysis, K-means clustering, and neural network (NN), were utilized for in situ Co XANES data analysis. As a result, we obtained quantitative structural information of the SAC nearest atomic environment, thereby extending the NN-XANES approach previously demonstrated for nanoparticles and size-selective clusters.

Prediction of the photoelectrochemical performance of hematite electrodes using analytical data

Combination of analytical data could predict and specify the critical factors for the photoelectrode performance.

Pyrolysis of a metal-organic framework followed by in situ X-ray absorption spectroscopy, powder diffraction and pair distribution function analysis

Metal-organic frameworks (MOFs) can serve as precursors for new nanomaterials via thermal decomposition. Such MOF-derived nanomaterials (MDNs) are often comprised of metal and/or metal oxide particles embedded on porous carbon....

Probing Active Sites in CuxPdy Cluster Catalysts by Machine-Learning-Assisted X-ray Absorption Spectroscopy

Size-selected clusters are important model catalysts because of their narrow size and compositional distributions, as well as enhanced activity and selectivity in many reactions. Still, their structure-activity relationships are, in general, elusive. The main reason is the difficulty in identifying and quantitatively characterizing the catalytic active site in the clusters when it is confined within subnanometric dimensions and under the continuous structural changes the clusters can undergo in reaction conditions. Using machine learning approaches for analysis of the operando X-ray absorption near-edge structure spectra, we obtained accurate speciation of the Cu_xPd_y cluster types during the propane oxidation reaction and the structural information about each type. As a result, we elucidated the information about active species and relative roles of Cu and Pd in the clusters.

Unsupervised machine learning for unbiased chemical classification in X-ray absorption spectroscopy and X-ray emission spectroscopy

We report a comprehensive computational study of unsupervised machine learning for extraction of chemically relevant information in X-ray absorption near edge structure (XANES) and in valence-to-core X-ray emission spectra (VtC-XES) for classification of a broad ensemble of sulphorganic molecules. By progressively decreasing the constraining assumptions of the unsupervised machine learning algorithm, moving from principal component analysis (PCA) to a variational autoencoder (VAE) to t-distributed stochastic neighbour embedding (t-SNE), we find improved sensitivity to steadily more refined chemical information. Surprisingly, when embedding the ensemble of spectra in merely two dimensions, t-SNE distinguishes not just oxidation state and general sulphur bonding environment but also the aromaticity of the bonding radical group with 87% accuracy as well as identifying even finer details in electronic structure within aromatic or aliphatic sub-classes. We find that the chemical information in XANES and VtC-XES is very similar in character and content, although they unexpectedly have different sensitivity within a given molecular class. We also discuss likely benefits from further effort with unsupervised machine learning and from the interplay between supervised and unsupervised machine learning for X-ray spectroscopies. Our overall results, i.e., the ability to reliably classify without user bias and to discover unexpected chemical signatures for XANES and VtC-XES, likely generalize to other systems as well as to other one-dimensional chemical spectroscopies.

Comparative analysis of XANES and EXAFS for local structural characterization of disordered metal oxides

In functional materials, the local environment around active species that may contain just a few nearest-neighboring atomic shells often changes in response to external conditions. Strong disorder in the local environment poses a challenge to commonly used extended X-ray absorption fine structure (EXAFS) analysis. Furthermore, the dilute concentrations of absorbing atoms, small sample size and the constraints of the experimental setup often limit the utility of EXAFS for structural analysis. X-ray absorption near-edge structure (XANES) has been established as a good alternative method to provide local electronic and geometric information of materials. The pre-edge region in the XANES spectra of metal compounds is a useful but relatively under-utilized resource of information of the chemical composition and structural disorder in nano-materials. This study explores two examples of materials in which the transition metal environment is either relatively symmetric or strongly asymmetric. In the former case, EXAFS results agree with those obtained from the pre-edge XANES analysis, whereas in the latter case they are in a seeming contradiction. The two observations are reconciled by revisiting the limitations of EXAFS in the case of a strong, asymmetric bond length disorder, expected for mixed-valence oxides, and emphasize the utility of the pre-edge XANES analysis for detecting local heterogeneities in structural and compositional motifs.

Deciphering the Phillips Catalyst by Orbital Analysis and Supervised Machine Learning from Cr Pre-edge XANES of Molecular Libraries

Unveiling the nature and the distribution of surface sites in heterogeneous catalysts, and for the Phillips catalyst (CrO₃/SiO₂) in particular, is still a grand challenge despite more than 60 years of research. Commonly used references in Cr K-edge XANES spectral analysis rely on bulk materials (Cr-foil, Cr₂O₃) or molecules (CrCl₃) that significantly differ from actual surface sites. In this work, we built a library of Cr K-edge XANES spectra for a series of tailored molecular Cr complexes, varying in oxidation state, local coordination environment, and ligand strength. Quantitative analysis of the pre-edge region revealed the origin of the pre-edge shape and intensity distribution. In particular, the characteristic pre-edge splitting observed for Cr(III) and Cr(IV) molecular complexes is directly related to the electronic exchange interactions in the frontier orbitals (spin-up and -down transitions). The series of experimental references was extended by theoretical spectra for potential active site structures and used for training the Extra Trees machine learning algorithm. The most informative features of the spectra (descriptors) were selected for the prediction of Cr oxidation states, mean interatomic distances in the first coordination sphere, and type of ligands. This set of descriptors was applied to uncover the site distribution in the Phillips catalyst at three different stages of the process. The freshly calcined catalyst consists of mainly Cr(VI) sites. The CO-exposed catalyst contains mainly Cr(II) silicates with a minor fraction of Cr(III) sites. The Phillips catalyst exposed to ethylene contains mainly highly coordinated Cr(III) silicates along with unreduced Cr(VI) sites.

Enhancing the analysis of disorder in X-ray absorption spectra: application of deep neural networks to T-jump-X-ray probe experiments

Many chemical and biological reactions, including ligand exchange processes, require thermal energy for the reactants to overcome a transition barrier and reach the product state. Temperature-jump (T-jump) spectroscopy uses a near-infrared (NIR) pulse to rapidly heat a sample, offering an approach for triggering these processes and directly accessing thermally-activated pathways. However, thermal activation inherently increases the disorder of the system under study and, as a consequence, can make quantitative interpretations of structural changes challenging. In this Article, we optimise a deep neural network (DNN) for the instantaneous prediction of Co K-edge X-ray absorption near-edge structure (XANES) spectra. We apply our DNN to analyse T-jump pump/X-ray probe data pertaining to the ligand exchange processes and solvation dynamics of Co2+ in chlorinated aqueous solution. Our analysis is greatly facilitated by machine learning, as our DNN is able to predict quickly and cost-effectively the XANES spectra of thousands of geometric configurations sampled from ab initio molecular dynamics (MD) using nothing more than the local geometric environment around the X-ray absorption site. We identify directly the structural changes following the T-jump, which are dominated by sample heating and a commensurate increase in the Debye-Waller factor.

Latent Representation Learning for Structural Characterization of Catalysts

Supervised machine learning-enabled mapping of the X-ray absorption near edge structure (XANES) spectra to local structural descriptors offers new methods for understanding the structure and function of working nanocatalysts. We briefly summarize a status of XANES analysis approaches by supervised machine learning methods. We present an example of an autoencoder-based, unsupervised machine learning approach for latent representation learning of XANES spectra. This new approach produces a lower-dimensional latent representation, which retains a spectrum-structure relationship that can be eventually mapped to physicochemical properties. The latent space of the autoencoder also provides a pathway to interpret the information content "hidden" in the X-ray absorption coefficient. Our approach (that we named latent space analysis of spectra, or LSAS) is demonstrated for the supported Pd nanoparticle catalyst studied during the formation of Pd hydride. By employing the low-dimensional representation of Pd K-edge XANES, the LSAS method was able to isolate the key factors responsible for the observed spectral changes.

In Situ/Operando Electrocatalyst Characterization by X-ray Absorption Spectroscopy

During the last decades, X-ray absorption spectroscopy (XAS) has become an indispensable method for probing the structure and composition of heterogeneous catalysts, revealing the nature of the active sites and establishing links between structural motifs in a catalyst, local electronic structure, and catalytic properties. Here we discuss the fundamental principles of the XAS method and describe the progress in the instrumentation and data analysis approaches undertaken for deciphering X-ray absorption near edge structure (XANES) and extended X-ray absorption fine structure (EXAFS) spectra. Recent usages of XAS in the field of heterogeneous catalysis, with emphasis on examples concerning electrocatalysis, will be presented. The latter is a rapidly developing field with immense industrial applications but also unique challenges in terms of the experimental characterization restrictions and advanced modeling approaches required. This review will highlight the new insight that can be gained with XAS on complex real-world electrocatalysts including their working mechanisms and the dynamic processes taking place in the course of a chemical reaction. More specifically, we will discuss applications of in situ and operando XAS to probe the catalyst's interactions with the environment (support, electrolyte, ligands, adsorbates, reaction products, and intermediates) and its structural, chemical, and electronic transformations as it adapts to the reaction conditions.

Radiation-Assisted Formation of Metal Nanoparticles in Molten Salts

Knowledge of structural and thermal properties of molten salts is crucial for understanding and predicting their stability in many applications such as thermal energy storage and nuclear energy systems. Probing the behavior of metal contaminants in molten salts is presently limited to either foreign ionic species or metal nanocrystals added to the melt. To bridge the gap between these two end states and follow the nucleation and growth of metal species in molten salt environment in situ, we use synchrotron X-rays as both a source of solvated electrons for reducing Ni²⁺ ions added to ZnCl₂ melt and as an atomic-level probe for detecting formation of zerovalent Ni nanoparticles. By combining extended X-ray absorption fine structure analysis with X-ray absorption near edge structure modeling, we obtained the average size and structure of the nanoparticles and proposed a radiation-induced reduction mechanism of metal ions in molten salts.

Harnessing deep neural networks to solve inverse problems in quantum dynamics: machine-learned predictions of time-dependent optimal control fields

Inverse problems continue to garner immense interest in the physical sciences, particularly in the context of controlling desired phenomena in non-equilibrium systems. In this work, we utilize a series of deep neural networks for predicting time-dependent optimal control fields, E(t), that enable desired electronic transitions in reduced-dimensional quantum dynamical systems. To solve this inverse problem, we investigated two independent machine learning approaches: (1) a feedforward neural network for predicting the frequency and amplitude content of the power spectrum in the frequency domain (i.e., the Fourier transform of E(t)), and (2) a cross-correlation neural network approach for directly predicting E(t) in the time domain. Both of these machine learning methods give complementary approaches for probing the underlying quantum dynamics and also exhibit impressive performance in accurately predicting both the frequency and strength of the optimal control field. We provide detailed architectures and hyperparameters for these deep neural networks as well as performance metrics for each of our machine-learned models. From these results, we show that machine learning, particularly deep neural networks, can be employed as cost-effective statistical approaches for designing electromagnetic fields to enable desired transitions in these quantum dynamical systems.

Progress in Computational and Machine-Learning Methods for Heterogeneous Small-Molecule Activation

The chemical conversion of small molecules such as H₂ , H₂ O, O₂ , N₂ , CO₂ , and CH₄ to energy and chemicals is critical for a sustainable energy future. However, the high chemical stability of these molecules poses grand challenges to the practical implementation of these processes. In this regard, computational approaches such as density functional theory, microkinetic modeling, data science, and machine learning have guided the rational design of catalysts by elucidating mechanistic insights, identifying active sites, and predicting catalytic activity. Here, the theory and methodologies for heterogeneous catalysis and their applications for small-molecule activation are reviewed. An overview of fundamental theory and key computational methods for designing catalysts, including the emerging data science techniques in particular, is given. Applications of these methods for finding efficient heterogeneous catalysts for the activation of the aforementioned small molecules are then surveyed. Finally, promising directions of the computational catalysis field for further outlooks are discussed, focusing on the challenges and opportunities for new methods.

The Role of Structural Representation in the Performance of a Deep Neural Network for X-Ray Spectroscopy

An important consideration when developing a deep neural network (DNN) for the prediction of molecular properties is the representation of the chemical space. Herein we explore the effect of the representation on the performance of our DNN engineered to predict Fe K-edge X-ray absorption near-edge structure (XANES) spectra, and address the question: How important is the choice of representation for the local environment around an arbitrary Fe absorption site? Using two popular representations of chemical space-the Coulomb matrix (CM) and pair-distribution/radial distribution curve (RDC)-we investigate the effect that the choice of representation has on the performance of our DNN. While CM and RDC featurisation are demonstrably robust descriptors, it is possible to obtain a smaller mean squared error (MSE) between the target and estimated XANES spectra when using RDC featurisation, and converge to this state a) faster and b) using fewer data samples. This is advantageous for future extension of our DNN to other X-ray absorption edges, and for reoptimisation of our DNN to reproduce results from higher levels of theory. In the latter case, dataset sizes will be limited more strongly by the resource-intensive nature of the underlying theoretical calculations.

Neural network assisted analysis of bimetallic nanocatalysts using X-ray absorption near edge structure spectroscopy

Trained neural networks are used to extract the first partial coordination numbers from XANES spectra. In bimetallic nanoparticles, the four local structure descriptors provide rich information on structural motifs.