Machinelearning potentials are accelerating the development of energy materials, especially in identifying phase diagrams and other thermodynamic properties. In this work, we present a neural network potential based on atomcentered symmetry function descriptors to model the energetics of lithium intercalation into graphite. The potential was trained on a dataset of over 9000 diverse lithium–graphite configurations that varied in applied stress and strain, lithium concentration, lithium–carbon and lithium–lithium bond distances, and stacking order to ensure wide sampling of the potential atomic configurations during intercalation. We calculated the energies of these structures using density functional theory (DFT) through the Bayesian error estimation functional with van der Waals correlation exchangecorrelation functional, which can accurately describe the van der Waals interactions that are crucial to determining the thermodynamics of this phase space. Bayesian optimization, as implemented in
 Award ID(s):
 1945525
 NSFPAR ID:
 10503668
 Publisher / Repository:
 Digital Discovery
 Date Published:
 Journal Name:
 Digital Discovery
 Volume:
 2
 Issue:
 4
 ISSN:
 2635098X
 Page Range / eLocation ID:
 1058 to 1069
 Format(s):
 Medium: X
 Sponsoring Org:
 National Science Foundation
More Like this

Abstract Dragonfly , was used to select optimal set of symmetry function parameters, ultimately resulting in a potential with a prediction error of 8.24 meV atom^{−1}on unseen test data. The potential can predict energies, structural properties, and elastic constants at an accuracy comparable to other DFT exchangecorrelation functionals at a fraction of the computational cost. The accuracy of the potential is also comparable to similar machinelearned potentials describing other systems. We calculate the open circuit voltage with the calculator and find good agreement with experiment, especially in the regimex ≥ 0.3, forx in Li_{x}C_{6}. This study further illustrates the power of machine learning potentials, which promises to revolutionize design and optimization of battery materials. 
Abstract Vibrational spectroscopy enables critical insight into the structural and dynamic properties of molecules. Presently, the majority of theoretical approaches to spectroscopy employ wavefunction‐based
ab initio or density functional methods that rely on the harmonic approximation. This approximation breaks down for large molecules with strongly anharmonic bonds or for molecules with large internuclear separations. An alternative to these methods involves generating molecular anharmonic potential energy surfaces (potentials) and using them to extrapolate the vibrational frequencies. This study examines the efficacy of density functional theory (DFT) and the correlation consistent Composite Approach (ccCA) in generating anharmonic frequencies from potentials of small main group molecules. Vibrational self‐consistent field Theory (VSCF) and post‐VSCF methods were used to calculate the fundamental frequencies of these molecules from their potentials. Functional choice, basis set selection, and mode‐coupling are also examined as factors in influencing accuracy. The absolute deviations for the calculated frequencies using potentials at the ccCA level of theory were lower than the potentials at the DFT level. With DFT resulting in bending modes that are better described than those of ccCA, a multilevel DFT:ccCA approach where DFT potentials are used for single vibrational mode potentials and ccCA is used for vibrational mode‐mode couplings can be utilized for larger polyatomic systems. The frequencies obtained with this multilevel approach using VCIPSI‐PT2 were closer to experimental frequencies than the scaled harmonic frequencies, indicating the success of utilizing post‐VSCF methods to generate more accurate representations of computed infrared spectra. 
Abstract Machine learning interatomic potentials (IPs) can provide accuracy close to that of firstprinciples methods, such as density functional theory (DFT), at a fraction of the computational cost. This greatly extends the scope of accurate molecular simulations, providing opportunities for quantitative design of materials and devices on scales hitherto unreachable by DFT methods. However, machine learning IPs have a basic limitation in that they lack a physical model for the phenomena being predicted and therefore have unknown accuracy when extrapolating outside their training set. In this paper, we propose a class of Dropout Uncertainty Neural Network (DUNN) potentials that provide rigorous uncertainty estimates that can be understood from both Bayesian and frequentist statistics perspectives. As an example, we develop a DUNN potential for carbon and show how it can be used to predict uncertainty for static and dynamical properties, including stress and phonon dispersion in graphene. We demonstrate two approaches to propagate uncertainty in the potential energy and atomic forces to predicted properties. In addition, we show that DUNN uncertainty estimates can be used to detect configurations outside the training set, and in some cases, can serve as a predictor for the accuracy of a calculation.

Neural network potentials (NNPs) trained against density functional theory (DFT) are capable of reproducing the potential energy surface at a fraction of the computational cost. However, most NNP implementations focus on energy and forces. In this work, we modified the NNP model introduced by Behler and Parrinello to predict Fermi energy, band edges, and partial density of states of Cu 2 O. Our NNP can reproduce the DFT potential energy surface and properties at a fraction of the computational cost. We used our NNP to perform molecular dynamics (MD) simulations and validated the predicted properties against DFT calculations. Our model achieved a root mean squared error of 16 meV for the energy prediction. Furthermore, we show that the standard deviation of the energies predicted by the ensemble of training snapshots can be used to estimate the uncertainty in the predictions. This allows us to switch from the NNP to DFT onthefly during the MD simulation to evaluate the forces when the uncertainty is high.more » « less

The strong couplings between electronic states in conical intersection regions are among the most challenging problems in quantum chemistry. XMSCASPT2, a secondorder multireference quasidegenerate perturbation theory, has been successful in describing potential energy surfaces near the conical intersections. We have recently proposed a less expensive method for this problem, namely stateinteraction pairdensity functional theory (SIPDFT), which considers the coupling between electronic states described by multiconfiguration pairdensity functional theory (MCPDFT). Here we test the accuracy of SIPDFT for closely coupled potential energy surfaces of methylamine along five different reaction paths for N–H bond fission. We choose paths that pass close to a conical intersection of the ground and first excited states. We find that SIPDFT predicts potential energy curves and energy splittings near the locally avoided crossing in close proximity to those obtained by XMSCASPT2. This validates the method for application to photochemical simulations.more » « less