Atomic structure of boron resolved using machine learning and global sampling

In Situ Surfaced Mn-Mn Dimeric Sites Dictate CO Hydrogenation Activity and C2 Selectivity over MnRh Binary Catalysts

Massive ethanol production has long been a dream of human society. Despite extensive research in past decades, only a few systems have the potential of industrialization: specifically, Mn-promoted Rh (MnRh) binary heterogeneous catalysts were shown to achieve up to 60% C2 oxygenates selectivity in converting syngas (CO/H2) to ethanol. However, the active site of the binary system has remained poorly characterized. Here, large-scale machine-learning global optimization is utilized to identify the most stable Mn phases on Rh metal surfaces under reaction conditions by exploring millions of likely structures. We demonstrate that Mn prefers the subsurface sites of Rh metal surfaces and is able to emerge onto the surface forming MnRh surface alloy once the oxidative O/OH adsorbates are present. Our machine-learning-based transition state exploration further helps to resolve automatedly the whole reaction network, including 74 elementary reactions on various MnRh surface sites, and reveals that the Mn-Mn dimeric site at the monatomic step edge is the true active site for C2 oxygenate formation. The turnover frequency of the C2 product on the Mn-Mn dimeric site at MnRh steps is at least 107 higher than that on pure Rh steps from our microkinetic simulations, with the selectivity to the C2 product being 52% at 523 K. Our results demonstrate the key catalytic role of Mn-Mn dimeric sites in allowing C-O bond cleavage and facilitating the hydrogenation of O-terminating C2 intermediates, and rule out Rh metal by itself as the active site for CO hydrogenation to C2 oxygenates.

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Recent years have seen a surge of machine learning (ML) in chemistry for predicting chemical properties, but a low-cost, general-purpose, and high-performance model, desirable to be accessible on central processing unit (CPU) devices, remains not available. For this purpose, here we introduce an atomic attention mechanism into many-body function corrected neural network (MBNN), namely, MBNN-att ML model, to predict both the extensive and intensive properties of molecules and materials. The MBNN-att uses explicit function descriptors as the inputs for the atom-based feed-forward neural network (NN). The output of the NN is designed to be a vector to implement the multihead self-attention mechanism. This vector is split into two parts: the atomic attention weight part and the many-body-function part. The final property is obtained by summing the products of each atomic attention weight and the corresponding many-body function. We show that MBNN-att performs well on all QM9 properties, i.e., errors on all properties, below chemical accuracy, and, in particular, achieves the top performance for the energy-related extensive properties. By systematically comparing with other explicit-function-type descriptor ML models and the graph representation ML models, we demonstrate that the many-body-function framework and atomic attention mechanism are key ingredients for the high performance and the good transferability of MBNN-att in molecular property prediction.

Construction of High Accuracy Machine Learning Interatomic Potential for Surface/Interface of Nanomaterials-A Review

The inherent discontinuity and unique dimensional attributes of nanomaterial surfaces and interfaces bestow them with various exceptional properties. These properties, however, also introduce difficulties for both experimental and computational studies. The advent of machine learning interatomic potential (MLIP) addresses some of the limitations associated with empirical force fields, presenting a valuable avenue for accurate simulations of these surfaces/interfaces of nanomaterials. Central to this approach is the idea of capturing the relationship between system configuration and potential energy, leveraging the proficiency of machine learning (ML) to precisely approximate high-dimensional functions. This review offers an in-depth examination of MLIP principles and their execution and elaborates on their applications in the realm of nanomaterial surface and interface systems. The prevailing challenges faced by this potent methodology are also discussed.

Predictions of Boron Phase Stability Using an Efficient Bayesian Machine Learning Interatomic Potential

Thermodynamic phase stability of three elemental boron allotropes, i.e., α-B, β-B, and γ-B, was investigated using a Bayesian interatomic potential trained via a sparse Gaussian process (SGP). SGP potentials trained with data sets from on-the-fly active learning achieve quantum mechanical level accuracy when employed in molecular dynamics (MD) simulations to predict wide-ranging thermodynamic, structural, and vibrational properties. The simulated phase diagram (500-1400 K and 0-16 GPa) agrees with experimental measurements. The SGP-based MD simulations also successfully predicted that the B13 defect is critical in stabilizing β-B below 700 K. At higher temperatures, the entropy becomes the dominant factor, making β-B the more stable phase over α-B. This letter demonstrates that SGP potentials based on a training set consisting of defect-free-only systems could make correct predictions of defect-related phenomena in solid-state crystals, paving the path to investigate crystal phase stability and transitions.

Amorphous Chloride Solid Electrolytes with High Li-Ion Conductivity for Stable Cycling of All-Solid-State High-Nickel Cathodes

Solid electrolytes (SEs) are central components that enable high-performance, all-solid-state lithium batteries (ASSLBs). Amorphous SEs hold great potential for ASSLBs because their grain-boundary-free characteristics facilitate intact solid-solid contact and uniform Li-ion conduction for high-performance cathodes. However, amorphous oxide SEs with limited ionic conductivities and glassy sulfide SEs with narrow electrochemical windows cannot sustain high-nickel cathodes. Herein, we report a class of amorphous Li-Ta-Cl-based chloride SEs possessing high Li-ion conductivity (up to 7.16 mS cm-1) and low Young's modulus (approximately 3 GPa) to enable excellent Li-ion conduction and intact physical contact among rigid components in ASSLBs. We reveal that the amorphous Li-Ta-Cl matrix is composed of LiCl43-, LiCl54-, LiCl65- polyhedra, and TaCl6- octahedra via machine-learning simulation, solid-state 7Li nuclear magnetic resonance, and X-ray absorption analysis. Attractively, our amorphous chloride SEs exhibit excellent compatibility with high-nickel cathodes. We demonstrate that ASSLBs comprising amorphous chloride SEs and high-nickel single-crystal cathodes (LiNi0.88Co0.07Mn0.05O2) exhibit ∼99% capacity retention after 800 cycles at ∼3 C under 1 mA h cm-2 and ∼80% capacity retention after 75 cycles at 0.2 C under a high areal capacity of 5 mA h cm-2. Most importantly, a stable operation of up to 9800 cycles with a capacity retention of ∼77% at a high rate of 3.4 C can be achieved in a freezing environment of -10 °C. Our amorphous chloride SEs will pave the way to realize high-performance high-nickel cathodes for high-energy-density ASSLBs.

The Identity of Nickel Peroxide as a Nickel Superoxyhydroxide for Enhanced Electrocatalysis

Nickel peroxides are a class of stoichiometric oxidants that can selectively oxidize various organic compounds, but their molecular level structure remained elusive until now. Herein, we utilized structural prediction using the Stochastic Surface Walking method based on a neural network potential energy surface and advanced characterization using the as-synthesized nickel peroxide to unravel its chemical identity as the bridging superoxide containing nickel hydroxide, or nickel superoxyhydroxide. Superoxide incorporation tunes the local chemical environment of nickel and oxygen beyond the conventional Bode plot, offering a 6.4-fold increase in the electrocatalytic activity of urea oxidation. A volcanic dependence of the activity on the oxygen equivalents leads to the proposed active site of the Ni(OO)(OH)Ni five-membered ring. This work not only unveils the possible structures of nickel peroxides but also emphasizes the significance of tailoring the oxygen environment for advanced catalysis.

Accuracy Assessment of Atomistic Neural Network Potentials: The Impact of Cutoff Radius and Message Passing

Atomistic neural network potentials have achieved great success in accelerating atomistic simulations in complicated systems in recent years. They are typically based on the atomic decomposition of total properties, truncating the interatomic correlations to a local environment within a given cutoff radius. A more recently developed message passing (MP) neural network framework can, in principle, incorporate nonlocal effects through iteratively correlating some atoms outside the cutoff sphere with atoms inside, a process referred to as MP. However, how the model accuracy depends on the cutoff radius and the MP process has rarely been discussed. In this work, we investigate this dependence using a recursively embedded atom neural network method that possesses both local and MP features, in two representative systems: liquid H2O and solid Al2O3. We focus on how these settings influence predictions for structural and vibrational properties, namely, radial distribution functions (RDFs) and vibrational density of states (VDOSs). We find that while MP lowers test errors of energy and forces in general, it may not improve the prediction for RDFs and/or VDOSs if direct interatomic correlations in the local environment are insufficiently described. A cutoff radius exceeding the first neighbor shell is necessary, beyond which involving MP quickly enhances the model accuracy until convergence. This is a potentially more efficient way to increase the model accuracy than directly increasing the cutoff radius, especially with more memory savings in the GPU implementation. Our findings also suggest that using the mean test error as the measure of the model accuracy alone is inadequate.

Global Neural Network Potential with Explicit Many-Body Functions for Improved Descriptions of Complex Potential Energy Surface

The high dimensional machine learning potential (MLP) that has developed rapidly in the past decade represents a giant step forward in large-scale atomic simulation for complex systems. The long-range interaction and the poor description of chemical reactions are typical problems of high dimensional MLP, which are mainly caused by the poor structure discrimination of the atom-centered ML model. Herein, we propose a low-cost neural-network-based MLP architecture for fitting global potential energy surface data, namely, G-MBNN, that can offer improved energy and force resolution on a complex potential energy surface. In G-MBNN, a set of many-body energy terms based on the local atomic environment are explicitly included in computing the total energy─the total energy of the system is written as the sum of atomic energy and many-body energy contributions. These extra many-body energy terms are computationally low-cost and, importantly, can provide easy access to delicate energy terms in complex systems such as very short repulsion, long-range attractions, and sensitive angular-dependent covalent interactions. We implement G-MBNN in the LASP code and demonstrate the improved accuracy of the new framework in representative systems, including ternary-element energy materials LiCoOx, TiO2 with defects, and a series of organic reactions.

An optimal Fe-C coordination ensemble for hydrocarbon chain growth: a full Fischer-Tropsch synthesis mechanism from machine learning

Fischer-Tropsch synthesis (FTS, CO + H2 → long-chain hydrocarbons) because of its great significance in industry has attracted huge attention since its discovery. For Fe-based catalysts, after decades of efforts, even the product distribution remains poorly understood due to the lack of information on the active site and the chain growth mechanism. Herein powered by a newly developed machine-learning-based transition state (ML-TS) exploration method to treat properly reaction-induced surface reconstruction, we are able to resolve where and how long-chain hydrocarbons grow on complex in situ-formed Fe-carbide (FeCx) surfaces from thousands of pathway candidates. Microkinetics simulations based on first-principles kinetics data further determine the rate-determining and the selectivity-controlling steps, and reveal the fine details of the product distribution in obeying and deviating from the Anderson-Schulz-Flory law. By showing that all FeCx phases can grow coherently upon each other, we demonstrate that the FTS active site, namely the A-P5 site present on reconstructed Fe3C(031), Fe5C2(510), Fe5C2(021), and Fe7C3(071) terrace surfaces, is not necessarily connected to any particular FeCx phase, rationalizing long-standing structure-activity puzzles. The optimal Fe-C coordination ensemble of the A-P5 site exhibits both Fe-carbide (Fe4C square) and metal Fe (Fe3 trimer) features.

ChecMatE: A workflow package to automatically generate machine learning potentials and phase diagrams for semiconductor alloys

Semiconductor alloy materials are highly versatile due to their adjustable properties; however, exploring their structural space is a challenging task that affects the control of their properties. Traditional methods rely on ad hoc design based on the understanding of known chemistry and crystallography, which have limitations in computational efficiency and search space. In this work, we present ChecMatE (Chemical Material Explorer), a software package that automatically generates machine learning potentials (MLPs) and uses global search algorithms to screen semiconductor alloy materials. Taking advantage of MLPs, ChecMatE enables a more efficient and cost-effective exploration of the structural space of materials and predicts their energy and relative stability with ab initio accuracy. We demonstrate the efficacy of ChecMatE through a case study of the InxGa1-xN system, where it accelerates structural exploration at reduced costs. Our automatic framework offers a promising solution to the challenging task of exploring the structural space of semiconductor alloy materials.

Methanol Synthesis from CO2/CO Mixture on Cu-Zn Catalysts from Microkinetics-Guided Machine Learning Pathway Search

Methanol synthesis on industrial Cu/ZnO/Al₂O₃ catalysts via the hydrogenation of CO and CO₂ mixture, despite several decades of research, is still puzzling due to the nature of the active site and the role of CO₂ in the feed gas. Herein, with the large-scale machine learning atomic simulation, we develop a microkinetics-guided machine learning pathway search to explore thousands of reaction pathways for CO₂ and CO hydrogenations on thermodynamically favorable Cu-Zn surface structures, including Cu(111), Cu(211), and Zn-alloyed Cu(211) surfaces, from which the lowest energy pathways are identified. We find that Zn decorates at the step-edge at Cu(211) up to 0.22 ML under reaction conditions with the Zn-Zn dimeric sites being avoided. CO₂ and CO hydrogenations occur exclusively at the step-edge of the (211) surface with up to 0.11 ML Zn coverage, where the low coverage of Zn (0.11 ML) does not much affect the reaction kinetics, but the higher coverages of Zn (0.22 ML) poison the catalyst. It is CO₂ hydrogenation instead of CO hydrogenation that dominates methanol synthesis, agreeing with previous isotope experiments. While metallic steps are identified as the major active site, we show that the [-Zn-OH-Zn-] chains (cationic Zn) can grow on Cu(111) surfaces under reaction conditions, which suggests the critical role of CO in the mixed gas for reducing the cationic Zn and exposing metal sites for methanol synthesis. Our results provide a comprehensive picture on the dynamic coupling of the feed gas composition, the catalyst active site, and the reaction activity in this complex heterogeneous catalytic system.

Artificial intelligence pathway search to resolve catalytic glycerol hydrogenolysis selectivity

The complex interaction between molecules and catalyst surfaces leads to great difficulties in understanding and predicting the activity and selectivity in heterogeneous catalysis. Here we develop an end-to-end artificial intelligence framework for the activity prediction of heterogeneous catalytic systems (AI-Cat method), which takes simple inputs from names of molecules and metal catalysts and outputs the reaction energy profile from the input molecule to low energy pathway products. The AI-Cat method combines two neural network models, one for predicting reaction patterns and the other for providing the reaction barrier and energy, with a Monte Carlo tree search to resolve the low energy pathways in a reaction network. We then apply AI-Cat to resolve the reaction network of glycerol hydrogenolysis on Cu surfaces, which is a typical selective C-O bond activation system and of key significance for biomass-derived polyol utilization. We show that glycerol hydrogenolysis features a huge reaction network of relevant candidates, containing 420 reaction intermediates and 2467 elementary reactions. Among them, the surface-mediated enol-keto tautomeric resonance is a key step to facilitate the primary C-OH bond breaking and thus selects 1,2-propanediol as the major product on Cu catalysts. 1,3-Propanediol can only be produced under strong acidic conditions and high surface H coverage by following a hydrogenation-dehydration pathway. AI-Cat further discovers six low-energy reaction patterns for C-O bond activation on metals that is of general significance to polyol catalysis. Our results demonstrate that the reaction prediction for complex heterogeneous catalysis is now feasible with AI-based atomic simulation and a Monte Carlo tree search.

Theoretical methods for structural phase transitions in elemental solids at extreme conditions: statics and dynamics

In recent years, theoretical studies have moved from a traditionally supporting role to a more proactive role in the research of phase transitions at high pressures. In many cases, theoretical prediction leads the experimental exploration. This is largely owing to the rapid progress of computer power and theoretical methods, particularly the structure prediction methods tailored for high-pressure applications. This review introduces commonly used structure searching techniques based on static and dynamic approaches, their applicability in studying phase transitions at high pressure, and new developments made toward predicting complex crystalline phases. Successful landmark studies for each method are discussed, with an emphasis on elemental solids and their behaviors under high pressure. The review concludes with a perspective on outstanding challenges and opportunities in the field.

Smallest Stable Si/SiO_{2} Interface that Suppresses Quantum Tunneling from Machine-Learning-Based Global Search

While the downscaling of size for field effect transistors is highly desirable for computation efficiency, quantum tunneling at the Si/SiO_{2} interface becomes the leading concern when approaching the nanometer scale. By developing a machine-learning-based global search method, we now reveal all the likely Si/SiO_{2} interface structures from thousands of candidates. Two high Miller index Si(210) and (211) interfaces, being only ∼1  nm in periodicity, are found to possess good carrier mobility, low carrier trapping, and low interfacial energy. The results provide the basis for fabricating stepped Si surfaces for next-generation transistors.

Zeolite-confined subnanometric PtSn mimicking mortise-and-tenon joinery for catalytic propane dehydrogenation

Heterogeneous catalysts are often composite materials synthesized via several steps of chemical transformation, and thus the atomic structure in composite is a black-box. Herein with machine-learning-based atomic simulation we explore millions of structures for MFI zeolite encapsulated PtSn catalyst, demonstrating that the machine-learning enhanced large-scale potential energy surface scan offers a unique route to connect the thermodynamics and kinetics within catalysts' preparation procedure. The functionalities of the two stages in catalyst preparation are now clarified, namely, the oxidative clustering and the reductive transformation, which form separated Sn₄O₄ and PtSn alloy clusters in MFI. These confined clusters have high thermal stability at the intersection voids of MFI because of the formation of "Mortise-and-tenon Joinery". Among, the PtSn clusters with high Pt:Sn ratios (>1:1) are active for propane dehydrogenation to propene, ∼10³ in turnover-of-frequency greater than conventional Pt₃Sn metal. Key recipes to optimize zeolite-confined metal catalysts are predicted.

Machine learning potential era of zeolite simulation

Zeolites, owing to their great variety and complexity in structure and wide applications in chemistry, have long been the hot topic in chemical research. This perspective first presents a short retrospect of theoretical investigations on zeolites using the tools from classical force fields to quantum mechanics calculations and to the latest machine learning (ML) potential simulations. ML potentials as the next-generation technique for atomic simulation open new avenues to simulate and interpret zeolite systems and thus hold great promise for finally predicting the structure-functionality relation of zeolites. Recent advances using ML potentials are then summarized from two main aspects: the origin of zeolite stability and the mechanism of zeolite-related catalytic reactions. We also discussed the possible scenarios of ML potential application aiming to provide instantaneous and easy access of zeolite properties. These advanced applications could now be accomplished by combining cloud-computing-based techniques with ML potential-based atomic simulations. The future development of ML potentials for zeolites in the respects of improving the calculation accuracy, expanding the application scope and constructing the zeolite-related datasets is finally outlooked.

In Situ Active Site for Fe-Catalyzed Fischer-Tropsch Synthesis: Recent Progress and Future Challenges

Fischer-Tropsch synthesis (FTS) that converts syngas into long-chain hydrocarbons is a key technology in the chemical industry. As one of the best catalysts for FTS, the Fe-based composite develops rich solid phases (metal, oxides, and carbides) in the catalytic reaction, which triggered the quest for the true active site in catalysis in the past century. Recent years have seen great advances in probing the active-site structure using modern experimental and theoretical tools. This Perspective serves to highlight these latest achievements, focusing on the geometrical structure and thermodynamic stability of Fe carbide bulk phases, the exposed surfaces, and their relationship to FTS activity. The current reaction mechanisms on CO activation and carbon chain growth are also discussed, in the context of theoretical models and experimental evidence. We also present the outlook regarding the current challenges in Fe-based FTS.

REANN: A PyTorch-based end-to-end multi-functional deep neural network package for molecular, reactive, and periodic systems

In this work, we present a general purpose deep neural network package for representing energies, forces, dipole moments, and polarizabilities of atomistic systems. This so-called recursively embedded atom neural network model takes advantages of both the physically inspired atomic descriptor based neural networks and the message-passing based neural networks. Implemented in the PyTorch framework, the training process is parallelized on both the central processing unit and the graphics processing unit with high efficiency and low memory in which all hyperparameters can be optimized automatically. We demonstrate the state-of-the-art accuracy, high efficiency, scalability, and universality of this package by learning not only energies (with or without forces) but also dipole moment vectors and polarizability tensors in various molecular, reactive, and periodic systems. An interface between a trained model and LAMMPs is provided for large scale molecular dynamics simulations. We hope that this open-source toolbox will allow for future method development and applications of machine learned potential energy surfaces and quantum-chemical properties of molecules, reactions, and materials.

Automated search for optimal surface phases (ASOPs) in grand canonical ensemble powered by machine learning

The surface of a material often undergoes dramatic structure evolution under a chemical environment, which, in turn, helps determine the different properties of the material. Here, we develop a general-purpose method for the automated search of optimal surface phases (ASOPs) in the grand canonical ensemble, which is facilitated by the stochastic surface walking (SSW) global optimization based on global neural network (G-NN) potential. The ASOP simulation starts by enumerating a series of composition grids, then utilizes SSW-NN to explore the configuration and composition spaces of surface phases, and relies on the Monte Carlo scheme to focus on energetically favorable compositions. The method is applied to silver surface oxide formation under the catalytic ethene epoxidation conditions. The known phases of surface oxides on Ag(111) are reproduced, and new phases on Ag(100) are revealed, which exhibit novel structure features that could be critical for understanding ethene epoxidation. Our results demonstrate that the ASOP method provides an automated and efficient way for probing complex surface structures that are beneficial for designing new functional materials under working conditions.

Understanding Zinc-Doped Hydroxyapatite Structures Using the First-Principles Calculations and Convolutional Neural Network Algorithm

Element doping is widely used to improve the performance of materials by changing their intrinsic properties. However, the lack of direct crystallographic structures for dopants has restricted the effective high-throughput...

Dynamics of Heterogeneous Catalytic Processes at Operando Conditions

The rational design of high-performance catalysts is hindered by the lack of knowledge of the structures of active sites and the reaction pathways under reaction conditions, which can be ideally addressed by an in situ/operando characterization. Besides the experimental insights, a theoretical investigation that simulates reaction conditions-so-called operando modeling-is necessary for a plausible understanding of a working catalyst system at the atomic scale. However, there is still a huge gap between the current widely used computational model and the concept of operando modeling, which should be achieved through multiscale computational modeling. This Perspective describes various modeling approaches and machine learning techniques that step toward operando modeling, followed by selected experimental examples that present an operando understanding in the thermo- and electrocatalytic processes. At last, the remaining challenges in this area are outlined.

Theoretical studies on triplet-state driven dissociation of formaldehyde by quasi-classical molecular dynamics simulation on machine-learning potential energy surface

The H-atom dissociation of formaldehyde on the lowest triplet state (T1) is studied by quasi-classical molecular dynamic simulations on the high-dimensional machine-learning potential energy surface (PES) model. An atomic-energy based deep-learning neural network (NN) is used to represent the PES function, and the weighted atom-centered symmetry functions are employed as inputs of the NN model to satisfy the translational, rotational, and permutational symmetries, and to capture the geometry features of each atom and its individual chemical environment. Several standard technical tricks are used in the construction of NN-PES, which includes the application of clustering algorithm in the formation of the training dataset, the examination of the reliability of the NN-PES model by different fitted NN models, and the detection of the out-of-confidence region by the confidence interval of the training dataset. The accuracy of the full-dimensional NN-PES model is examined by two benchmark calculations with respect to ab initio data. Both the NN and electronic-structure calculations give a similar H-atom dissociation reaction pathway on the T1 state in the intrinsic reaction coordinate analysis. The small-scaled trial dynamics simulations based on NN-PES and ab initio PES give highly consistent results. After confirming the accuracy of the NN-PES, a large number of trajectories are calculated in the quasi-classical dynamics, which allows us to get a better understanding of the T1-driven H-atom dissociation dynamics efficiently. Particularly, the dynamics simulations from different initial conditions can be easily simulated with a rather low computational cost. The influence of the mode-specific vibrational excitations on the H-atom dissociation dynamics driven by the T1 state is explored. The results show that the vibrational excitations on symmetric C-H stretching, asymmetric C-H stretching, and C=O stretching motions always enhance the H-atom dissociation probability obviously.

Hydrogen Coupling on Platinum Using Artificial Neural Network Potentials and DFT

To date, the understanding of reactions at solid-liquid interfaces has proven challenging, mainly because of the inaccessible nature of such systems to current experimental techniques with atomic resolution. This has meant that many important features, including free energy barriers and the atomistic structure of intermediates, remain unknown. To tackle these issues, we construct and utilize a high-dimensional neural network (HDNN) potential for the simulation of hydrogen evolution at the HCl(aq)/Pt(111) interface, taking into consideration the influence of adsorbate-adsorbate, adsorbate-solvent interactions, and ion solvation explicitly. Long time scale MD simulations reveal coadsorbed H_ad/H₂O_ad on the surface. The free energy profiles for the Tafel and Heyrovsky type hydrogen coupling are extracted using umbrella sampling. It is found that the preferential mechanism can change depending on the surface coverage, highlighting the dual mechanistic nature for HER on Pt(111). Our work demonstrates the importance of controlling the solvent-substrate interactions in developing catalysts beyond Pt.

Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality

Recent advances in machine-learned interatomic potentials largely benefit from the atomistic representation and locally invariant many-body descriptors. It was, however, recently argued that including three-body (or even four-body) features is incomplete to distinguish specific local structures. Utilizing an embedded density descriptor made by linear combinations of neighboring atomic orbitals and realizing that each orbital coefficient physically depends on its own local environment, we propose a recursively embedded atom neural network model. We formally prove that this model can efficiently incorporate complete many-body correlations without explicitly computing high-order terms. This model not only successfully addresses challenges regarding local completeness and nonlocality in representative systems, but also provides an easy and general way to update local many-body descriptors to have a message-passing form without changing their basic structures.

In Situ Active Site for CO Activation in Fe-Catalyzed Fischer-Tropsch Synthesis from Machine Learning

In situ-formed iron carbides (FeC_x) are the key components responsible for Fischer-Tropsch synthesis (FTS, CO + H₂ → long-chain hydrocarbons) on Fe-based catalysts in industry. The true active site is, however, highly controversial despite more than a century of study, which is largely due to the combined complexity in both FeC_x structures and mechanism of CO hydrogenation. Herein powered by machine learning simulation, millions of structure candidates for FeC_x bulk and surfaces are explored under FTS conditions, which leads to resolving the active site for CO activation. This is achieved without a priori input from experiment by first constructing the thermodynamics convex hull of bulk phases, followed by identifying the low surface energy surfaces and evaluating the adsorption ability of CO and H, and finally determining the lowest energy reaction pathway of CO activation. Rich information on FeC_x structures and CO hydrogenation pathways is gleaned: (i) Fe₅C₂, Fe₇C₃, and Fe₂C are the three stable bulk phases under FTS in producing olefins, where Fe₇C₃ and Fe₂C have multiple energetically nearly degenerate bulk crystal phases; (ii) only three low surface energy surfaces of these bulk phases, namely, χ-Fe₅C₂(510), χ-Fe₅C₂(111), and η-Fe₂C(111), expose the Fe sites that can adsorb H atoms exothermically, where the surface Fe:C ratio is 2, 1.75, and 2, respectively; (iii) CO activation via direct dissociation can occur at the surface C vacancies (e.g., with a barrier of 1.1 eV) that are created dynamically via hydrogenation. These atomic-level understandings facilitate the building of the structure-activity correlation and designing better FT catalysts.

Molecular modelling of compounds used for corrosion inhibition studies: a review

Molecular modelling of organic compounds using computational software has emerged as a powerful approach for theoretical determination of the corrosion inhibition potential of organic compounds. Some of the common techniques involved in the theoretical studies of corrosion inhibition potential and mechanisms include density functional theory (DFT), molecular dynamics (MD) and Monte Carlo (MC) simulations, and artificial neural network (ANN) and quantitative structure-activity relationship (QSAR) modeling. Using computational modelling, the chemical reactivity and corrosion inhibition activities of organic compounds can be explained. The modelling can be regarded as a time-saving and eco-friendly approach for screening organic compounds for corrosion inhibition potential before their wet laboratory synthesis would be carried out. Another advantage of computational modelling is that molecular sites responsible for interactions with metallic surfaces (active sites or adsorption sites) and the orientation of organic compounds can be easily predicted. Using different theoretical descriptors/parameters, the inhibition effectiveness and nature of the metal-inhibitor interactions can also be predicted. The present review article is a collection of major advancements in the field of computational modelling for the design and testing of the corrosion inhibition effectiveness of organic corrosion inhibitors.

Accelerating Metadynamics-Based Free-Energy Calculations with Adaptive Machine Learning Potentials

There is an increasing demand for free-energy calculations using ab initio molecular dynamics these days. Metadynamics (MetaD) is frequently utilized to reconstruct the free-energy surface, but it is often computationally intractable for the first-principles calculations. Machine learning potentials (MLPs) have become popular alternatives. However, the training could be a long and arduous process before using them in practical applications. To accelerate MetaD use with MLPs for the free-energy calculation in an easy manner, we propose the adaptive machine learning potential-accelerated metadynamics (AMLP-MetaD). In this method, the MLP in the form of a Gaussian approximation potential (GAP) can adapt itself based on its uncertainty estimation, which decides whether to accept the model prediction or recalculate it with a reference method (usually density functional theory) for further training during the MetaD simulation. We demonstrate that the free-energy landscape similar to the ab initio one can be obtained using AMLP-MetaD with a 10-time speedup. Moreover, the quality of the free-energy results can be deeply improved using Δ-MLP, which is the GAP-corrected density functional tight binding in our case. We exemplify this novel method with two model systems, CO adsorption on the Pt₁₃ cluster and the Pt(111) surface, which are of vital importance in heterogeneous catalysis. The successful application in these two tests highlights that our proposed method can be used in both cluster and periodic systems and for up to two collective variables.

Perspective on computational reaction prediction using machine learning methods in heterogeneous catalysis

Heterogeneous catalysis plays a significant role in the modern chemical industry. Towards the rational design of novel catalysts, understanding reactions over surfaces is the most essential aspect. Typical industrial catalytic processes such as syngas conversion and methane utilisation can generate a large reaction network comprising thousands of intermediates and reaction pairs. This complexity not only arises from the permutation of transformations between species but also from the extra reaction channels offered by distinct surface sites. Despite the success in investigating surface reactions at the atomic scale, the huge computational expense of ab initio methods hinders the exploration of such complicated reaction networks. With the proliferation of catalysis studies, machine learning as an emerging tool can take advantage of the accumulated reaction data to emulate the output of ab initio methods towards swift reaction prediction. Here, we briefly summarise the conventional workflow of reaction prediction, including reaction network generation, ab initio thermodynamics and microkinetic modelling. An overview of the frequently used regression models in machine learning is presented. As a promising alternative to full ab initio calculations, machine learning interatomic potentials are highlighted. Furthermore, we survey applications assisted by these methods for accelerating reaction prediction, exploring reaction networks, and computational catalyst design. Finally, we envisage future directions in computationally investigating reactions and implementing machine learning algorithms in heterogeneous catalysis.

In Situ Surface Structures of PdAg Catalyst and Their Influence on Acetylene Semihydrogenation Revealed by Machine Learning and Experiment

PdAg alloy is an industrial catalyst for acetylene-selective hydrogenation in excess ethene. While significant efforts have been devoted to increase the selectivity, there has been little progress in the catalyst performance at low temperatures. Here by combining a machine-learning atomic simulation and catalysis experiment, we clarify the surface status of PdAg alloy catalyst under the reaction conditions and screen out a rutile-TiO₂ supported Pd₁Ag₃ catalyst with high performance: i.e., 85% selectivity at >96% acetylene conversion over a 100 h period in an experiment. The machine-learning global potential energy surface exploration determines the Pd-Ag-H bulk and surface phase diagrams under the reaction conditions, which reveals two key bulk compositions, Pd₁Ag₁ (R3̅m) and Pd₁Ag₃ (Pm3̅m), and quantifies the surface structures with varied Pd:Ag ratios under the reaction conditions. We show that the catalyst activity is controlled by the PdAg patterns on the (111) surface that are variable under reaction conditions, but the selectivity is largely determined by the amount of Pd exposure on the (100) surface. These insights provide the fundamental basis for the rational design of a better catalyst via three measures: (i) controlling the Pd:Ag ratio at 1:3, (ii) reducing the nanoparticle size to limit PdAg local patterns, (iii) searching for active supports to terminate the (100) facets.

Zirconia-Supported ZnO Single Layer for Syngas Conversion Revealed from Machine-Learning Atomic Simulation

ZnZrO ternary oxide represents a prominent catalytic system, identified recently for syngas conversion and CO₂ reduction via OX-ZEO technology. One intriguing observation of the ZnZrO catalyst is the very low amount of Zn required for achieving high activity, which challenges the current views on the active site of binary oxide catalysts. Herein, we demonstrate, via machine-learning-based atomic simulation, that the structure evolution of the ZnZrO system in synthesis can be traced from bulk to surface, which leads to the identification of the active site of the ZnZrO catalyst. Theory shows that an unprecedented single-layer Zn-O structure can adhere strongly to the monoclinic ZrO₂ minority (001) surface, forming a stable oxide-on-oxide interface Zn-O/M(001). The single-layer Zn-O can convert syngas to methanol with a high turnover frequency (7.38 s^-1) from microkinetics simulation. Electron structure analyses reveal that the pentahedron [ZnO₄] in Zn-O/M(001) enhances the surface electron donation to promote the catalytic activity.

The dome of gold nanolized for catalysis

Gold is noble in bulk but turns out to be a superior catalyst at the nanoscale when supported on oxides, in particular titania. The critical thickness for activity, namely two-layer gold particles on titania, observed two decades ago represents one of the most influential mysteries in the recent history of heterogeneous catalysis. By developing a Bayesian optimization controlled global potential energy surface exploration tool with machine learning potential, here we determine the atomic structures of gold particles within ∼2 nm on a TiO2 surface. We show that the smallest stable Au nanoparticle is Au24 which is pinned on the oxygen-rich TiO2 and exhibits an unprecedented dome architecture made by a single-layer Au sheet but with an apparent two-atomic-layer height. Importantly, this has the highest activity for CO oxidation at room temperature. The physical origin of the high activity is the outstanding electron storage ability of the nano-dome, which activates the lattice oxygen of the oxide. The determined CO oxidation mechanism, the simulated rate and the fitted apparent energy barrier are consistent with known experimental facts, providing key evidence for the presence of both the high-activity Au dome and the low-activity close-packed Au particles in real catalysts. The future direction for the preparation of active and stable Au-based catalysts is thus outlined.

Accelerating atomistic simulations with piecewise machine-learned ab Initio potentials at a classical force field-like cost

Combining piecewise switching functions with embedded atom neural networks to accelerate atomistic simulations with ab initio accuracy.

Reaction prediction via atomistic simulation: from quantum mechanics to machine learning

It is an ultimate goal in chemistry to predict reaction without recourse to experiment. Reaction prediction is not just the reaction rate determination of known reactions but, more broadly, the reaction exploration to identify new reaction routes. This review briefly overviews the theory on chemical reaction and the current methods for computing/estimating reaction rate and exploring reaction space. We particularly focus on the atomistic simulation methods for reaction exploration, which are benefited significantly by recently emerged machine learning potentials. We elaborate the stochastic surface walking global pathway sampling based on the global neural network (SSW-NN) potential, developed in our group since 2013, which can explore complex reactions systems unbiasedly and automatedly. Two examples, molecular reaction and heterogeneous catalytic reactions, are presented to illustrate the current status for reaction prediction using SSW-NN.

Crystal Structure Prediction of Binary Alloys via Deep Potential

Predicting crystal structure has been a challenging problem in physics and materials science for a long time. A reliable energy calculation engine combined with an efficient global search algorithm, such as particle swarm optimization algorithm or genetic algorithm, is needed to conduct crystal structure prediction. In recent years, machine learning-based interatomic potential energy surface models have been proposed, potentially allowing us to perform crystal structure prediction for systems with the accuracy of density functional theory (DFT) and the speed of empirical force fields. In this paper, we employ a previously developed Deep Potential model to predict the intermetallic compound of the aluminum-magnesium system, and find six meta-stable phases with negative or nearly zero formation energy. In particular, Mg12Al8 shows excellent ductility and Mg5Al27 has a high Young's modulus. Based on our benchmark results, we propose a relatively robust structure screening criterion that selects potentially stable structures from the Deep Potential-based convex hull and performs DFT refinement. By using this criterion, the computational cost needed to construct the convex hull with ab initio accuracy can be dramatically reduced.