Machine Learning of First-Principles Force-Fields for Alkane and Polyene Hydrocarbons

A dual-cutoff machine-learned potential for condensed organic systems obtained via uncertainty-guided active learning

Machine-learned potentials (MLPs) trained on ab initio data combine the computational efficiency of classical interatomic potentials with the accuracy and generality of the first-principles method used in the creation of the respective training set. In this work, we implement and train a MLP to obtain an accurate description of the potential energy surface and property predictions for organic compounds, as both single molecules and in the condensed phase. We devise a dual descriptor, based on the atomic cluster expansion (ACE), that couples an information-rich short-range description with a coarser long-range description that captures weak intermolecular interactions. We employ uncertainty-guided active learning for the training set generation, creating a dataset that is comparatively small for the breadth of application and consists of alcohols, alkanes, and an adipate. Utilizing that MLP, we calculate densities of those systems of varying chain lengths as a function of temperature, obtaining a discrepancy of less than 4% compared with experiment. Vibrational frequencies calculated with the MLP have a root mean square error of less than 1 THz compared to DFT. The heat capacities of condensed systems are within 11% of experimental findings, which is strong evidence that the dual descriptor provides an accurate framework for the prediction of both short-range intramolecular and long-range intermolecular interactions.

Active sparse Bayesian committee machine potential for isothermal-isobaric molecular dynamics simulations

Recent advancements in machine learning potentials (MLPs) have significantly impacted the fields of chemistry, physics, and biology by enabling large-scale first-principles simulations. Among different machine learning approaches, kernel-based MLPs distinguish themselves through their ability to handle small datasets, quantify uncertainties, and minimize over-fitting. Nevertheless, their extensive computational requirements present considerable challenges. To alleviate these, sparsification methods have been developed, aiming to reduce computational scaling without compromising accuracy. In the context of isothermal and isobaric ML molecular dynamics (MD) simulations, achieving precise pressure estimation is crucial for reproducing reliable system behavior under constant pressure. Despite progress, sparse kernel MLPs struggle with precise pressure prediction. Here, we introduce a virial kernel function that significantly enhances the pressure estimation accuracy of MLPs. Additionally, we propose the active sparse Bayesian committee machine (BCM) potential, an on-the-fly MLP architecture that aggregates local sparse Gaussian process regression (SGPR) MLPs. The sparse BCM potential overcomes the steep computational scaling with the kernel size, and a predefined restriction on the size of kernel allows for fast and efficient on-the-fly training. Our advancements facilitate accurate and computationally efficient machine learning-enhanced MD (MLMD) simulations across diverse systems, including ice-liquid coexisting phases, Li10Ge(PS6)2 lithium solid electrolyte, and high-pressure liquid boron nitride.

Deep-Learning Interatomic Potential Connects Molecular Structural Ordering to the Macroscale Properties of Polyacrylonitrile

Polyacrylonitrile (PAN) is an important commercial polymer, bearing atactic stereochemistry resulting from nonselective radical polymerization. As such, an accurate, fundamental understanding of governing interactions among PAN molecular units is indispensable for advancing the design principles of final products at reduced processability costs. While ab initio molecular dynamics (AIMD) simulations can provide the necessary accuracy for treating key interactions in polar polymers, such as dipole-dipole interactions and hydrogen bonding, and analyzing their influence on the molecular orientation, their implementation is limited to small molecules only. Herein, we show that the neural network interatomic potentials (NNIPs) that are trained on the small-scale AIMD data (acquired for oligomers) can be efficiently employed to examine the structures and properties at large scales (polymers). NNIP provides critical insight into intra- and interchain hydrogen-bonding and dipolar correlations and accurately predicts the amorphous bulk PAN structure validated by modeling the experimental X-ray structure factor. Furthermore, the NNIP-predicted PAN properties, such as density and elastic modulus, are in good agreement with their experimental values. Overall, the trend in the elastic modulus is found to correlate strongly with the PAN structural orientations encoded in the Hermans orientation factor. This study enables the ability to predict the structure-property relations for PAN and analogues with sustainable ab initio accuracy across scales.

Local-environment-guided selection of atomic structures for the development of machine-learning potentials

Machine learning potentials (MLPs) have attracted significant attention in computational chemistry and materials science due to their high accuracy and computational efficiency. The proper selection of atomic structures is crucial for developing reliable MLPs. Insufficient or redundant atomic structures can impede the training process and potentially result in a poor quality MLP. Here, we propose a local-environment-guided screening algorithm for efficient dataset selection in MLP development. The algorithm utilizes a local environment bank to store unique local environments of atoms. The dissimilarity between a particular local environment and those stored in the bank is evaluated using the Euclidean distance. A new structure is selected only if its local environment is significantly different from those already present in the bank. Consequently, the bank is then updated with all the new local environments found in the selected structure. To demonstrate the effectiveness of our algorithm, we applied it to select structures for a Ge system and a Pd13H2 particle system. The algorithm reduced the training data size by around 80% for both without compromising the performance of the MLP models. We verified that the results were independent of the selection and ordering of the initial structures. We also compared the performance of our method with the farthest point sampling algorithm, and the results show that our algorithm is superior in both robustness and computational efficiency. Furthermore, the generated local environment bank can be continuously updated and can potentially serve as a growing database of feature local environments, aiding in efficient dataset maintenance for constructing accurate MLPs.

PhyNEO: A Neural-Network-Enhanced Physics-Driven Force Field Development Workflow for Bulk Organic Molecule and Polymer Simulations

An accurate, generalizable, and transferable force field plays a crucial role in the molecular dynamics simulations of organic polymers and biomolecules. Conventional empirical force fields often fail to capture precise intermolecular interactions due to their negligence of important physics, such as polarization, charge penetration, many-body dispersion, etc. Moreover, the parameterization of these force fields relies heavily on top-down fittings, limiting their transferabilities to new systems where the experimental data are often unavailable. To address these challenges, we introduce a general and fully ab initio force field construction strategy, named PhyNEO. It features a hybrid approach that combines both the physics-driven and the data-driven methods and is able to generate a bulk potential with chemical accuracy using only quantum chemistry data of very small clusters. Careful separations of long-/short-range interactions and nonbonding/bonding interactions are the key to the success of PhyNEO. By such a strategy, we mitigate the limitations of pure data-driven methods in long-range interactions, thus largely increasing the data efficiency and the scalability of machine learning models. The new approach is thoroughly tested on poly(ethylene oxide) and polyethylene glycol systems, giving superior accuracies in both microscopic and bulk properties compared to conventional force fields. This work thus offers a promising framework for the development of advanced force fields in a wide range of organic molecular systems.

High-Dimensional Neural Network Potentials for Accurate Prediction of Equation of State: A Case Study of Methane

Machine learning-based interatomic potentials, such as those provided by neural networks, are increasingly important in molecular dynamics simulations. In the present work, we consider the applicability and robustness of machine learning molecular dynamics to predict the equation of state properties of methane by using high-dimensional neural network potentials (HDNNPs). We investigate two different strategies for generating training data: one strategy based upon bulk representations using periodic cells and another strategy based upon clusters of molecules. We assess the accuracy of the trained potentials by predicting the equilibrium mass density for a wide range of thermodynamic conditions to characterize the liquid phase, supercritical fluid, and gas phase, as well as the liquid-vapor coexistence curve. Our results show an excellent agreement with reference phase diagrams, with an average error below ∼2% for all studied phases. Moreover, we confirm the applicability of models trained on cluster data sets for producing accurate and reliable results.

Accelerating explicit solvent models of heterogeneous catalysts with machine learning interatomic potentials

Realistically modelling how solvents affect catalytic reactions is a longstanding challenge due to its prohibitive computational cost. Typically, an explicit atomistic treatment of the solvent molecules is needed together with molecular dynamics (MD) simulations and enhanced sampling methods. Here, we demonstrate the utility of machine learning interatomic potentials (MLIPs), coupled with active learning, to enable fast and accurate explicit solvent modelling of adsorption and reactions on heterogeneous catalysts. MLIPs trained on-the-fly were able to accelerate ab initio MD simulations by up to 4 orders of magnitude while reproducing with high fidelity the geometrical features of water in the bulk and at metal-water interfaces. Using these ML-accelerated simulations, we accurately predicted key catalytic quantities such as the adsorption energies of CO*, OH*, COH*, HCO*, and OCCHO* on Cu surfaces and the free energy barriers of C-H scission of ethylene glycol over Cu and Pd surfaces, as validated with ab initio calculations. We envision that such simulations will pave the way towards detailed and realistic studies of solvated catalysts at large time- and length-scales.

Reduced Potential Barrier of Sodium-Substituted Disordered Rocksalt Cathode for Oxygen Evolution Electrocatalysts

Cation-disordered rocksalt (DRX) cathodes have been viewed as next-generation high-energy density materials surpassing conventional layered cathodes for lithium-ion battery (LIB) technology. Utilizing the opportunity of a better cation mixing facility in DRX, we synthesize Na-doped DRX as an efficient electrocatalyst toward oxygen evolution reaction (OER). This novel OER electrocatalyst generates a current density of 10 mA cm−2 at an overpotential (η) of 270 mV, Tafel slope of 67.5 mV dec−1, and long-term stability >5.5 days’ superior to benchmark IrO2 (η = 330 mV with Tafel slope = 74.8 mV dec−1). This superior electrochemical behavior is well supported by experiment and sparse Gaussian process potential (SGPP) machine learning-based search for minimum energy structure. Moreover, as oxygen binding energy (OBE) on the surface closely relates to OER activity, our density functional theory (DFT) calculations reveal that Na-doping assists in facile O2 evolution (OBE = 5.45 eV) compared with pristine-DRX (6.51 eV).

Machine Learning Prediction of the Transmission Function for Protein Sequencing with Graphene Nanoslit

Protein sequencing has rapidly changed the landscape of healthcare and life science by accelerating the growth of diagnostics and personalized medicines for a variety of fatal diseases. Next-generation nanopore/nanoslit sequencing is promising to achieve single-molecule resolution with chromosome-size-long readability. However, due to inherent complexity, high-throughput sequencing of all 20 amino acids demands different approaches. Aiming to accelerate the detection of amino acids, a general machine learning (ML) method has been developed for quick and accurate prediction of the transmission function for amino acid sequencing. Among the utilized ML models, the XGBoost regression model is found to be the most effective algorithm for fast prediction of the transmission function with a very low test root-mean-square error (RMSE ∼0.05). In addition, using the random forest ML classification technique, we are able to classify the neutral amino acids with a prediction accuracy of 100%. Therefore, our approach is an initiative for the prediction of the transmission function through ML and can provide a platform for the quick identification of amino acids with high accuracy.

Fast atomic structure optimization with on-the-fly sparse Gaussian process potentials. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2022;34:344007. [PMID: 35675808 DOI: 10.1088/1361-648x/ac76ff]

We apply on-the-fly machine learning potentials (MLPs) using the sparse Gaussian process regression (SGPR) algorithm for fast optimization of atomic structures. Great acceleration is achieved even in the context of a single local optimization. Although for finding the exact local minimum, due to limited accuracy of MLPs, switching to another algorithm may be needed. For random gold clusters, the forces are reduced to ∼0.1 eV Å^-1within less than ten first-principles (FP) calculations. Because of highly transferable MLPs, this algorithm is specially suitable for global optimization methods such as random or evolutionary structure searching or basin hopping. This is demonstrated by sequential optimization of random gold clusters for which, after only a few optimizations, FP calculations were rarely needed.

Current State and Perspectives of Simulation and Modeling of Aliphatic Isocyanates and Polyisocyanates

Aliphatic isocyanates and polyisocyanates are central molecules in the fabrication of polyurethanes, coatings, and adhesives and, due to their excellent mechanical and stability properties, are continuously investigated in advanced applications; however, despite the growing interest in isocyanate-based systems, atomistic simulations on them have been limited by the lack of accurate parametrizations for these molecular species. In this review, we will first provide an overview of current research on isocyanate systems to highlight their most promising applications, especially in fields far from their typical usage, and to justify the need for further modeling works. Next, we will discuss the state of their modeling, from first-principle studies to atomistic molecular dynamics simulations and coarse-grained approaches, highlighting the recent advances in atomistic modeling. Finally, the most promising lines of research in the modeling of isocyanates are discussed in light of the possibilities opened by novel approaches, such as machine learning.

Predicting properties of periodic systems from cluster data: A case study of liquid water

The accuracy of the training data limits the accuracy of bulk properties from machine-learned potentials. For example, hybrid functionals or wave-function-based quantum chemical methods are readily available for cluster data but effectively out of scope for periodic structures. We show that local, atom-centered descriptors for machine-learned potentials enable the prediction of bulk properties from cluster model training data, agreeing reasonably well with predictions from bulk training data. We demonstrate such transferability by studying structural and dynamical properties of bulk liquid water with density functional theory and have found an excellent agreement with experimental and theoretical counterparts.

Sparse Gaussian Process Regression-Based Machine Learned First-Principles Force-Fields for Saturated, Olefinic, and Aromatic Hydrocarbons

Universal machine learning (ML) interatomic potentials (IAPs) for saturated, olefinic, and aromatic hydrocarbons are generated by using the Sparse Gaussian process regression algorithm. The universal potentials are obtained by combining the potentials for the previously trained alkane/polyene systems and the potentials generated with the presently trained cyclic/aromatic hydrocarbon systems, along with the newly trained cross-terms between the two systems. The ML-IAPs have been trained using the PBE + D3 level of density functional theory for the on-the-fly adaptive sampling of various hydrocarbon molecules and these clusters composed of small molecules. We tested the ML-IAPs and found that they correctly predicted the structures and energies of the β-carotene monomer and dimer. Also, the simulations of liquid ethylene reproduced the molecular volume and the simulations of toluene crystals reproduced higher stability of the α-phase over the β-phase. These ab initio-level force-fields could eventually evolve toward universal organic/polymeric/biomolecular systems.