This investigation presents a generally applicable framework for parameterizing interatomic potentials to accurately capture large deformation pathways. It incorporates a multi-objective genetic algorithm, training and screening property sets, and correlation and principal component analyses. The framework enables iterative definition of properties in the training and screening sets, guided by correlation relationships between properties, aiming to achieve optimal parametrizations for properties of interest. Specifically, the performance of increasingly complex potentials, Buckingham, Stillinger-Weber, Tersoff, and modified reactive empirical bond-order potentials are compared. Using MoSe2as a case study, we demonstrate good reproducibility of training/screening properties and superior transferability. For MoSe2, the best performance is achieved using the Tersoff potential, which is ascribed to its apparent higher flexibility embedded in its functional form. These results should facilitate the selection and parametrization of interatomic potentials for exploring mechanical and phononic properties of a large library of two-dimensional and bulk materials.
Developing an accurate interatomic potential model is a prerequisite for achieving reliable results from classical molecular dynamics (CMD) simulations; however, most of the potentials are biased as specific simulation purposes or conditions are considered in the parameterization. For developing an unbiased potential, a finite‐temperature dynamics machine learning (FTD‐ML) approach is proposed, and its processes and feasibility are demonstrated using the Buckingham potential model and aluminum (Al) as an example. Compared with conventional machine learning approaches, FTD‐ML exhibits three distinguished features: 1) FTD‐ML intrinsically incorporates more extensive configurational and conditional space for enhancing the transferability of developed potentials; 2) FTD‐ML employs various properties calculated directly from CMD, for ML model training and prediction validation against experimental data instead of first‐principles data; 3) FTD‐ML is much more computationally cost effective than first‐principles simulations, especially when the system size increases over 103atoms as employed in this research for ensuring reliable training data. The Al Buckingham potential developed by the FTD‐ML approach exhibits good performance for general simulation purposes. Thus, the FTD‐ML approach is expected to contribute to a fast development of interatomic potential model suitable for various simulation purposes and conditions, without limitation of model type, while maintaining experimental‐level accuracy.
more » « less- NSF-PAR ID:
- 10457794
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Advanced Theory and Simulations
- Volume:
- 3
- Issue:
- 2
- ISSN:
- 2513-0390
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Abstract Previous research has shown a consistent discrepancy in the reported structure of alkaline earth aluminosilicate glasses using molecular dynamics (MD) simulations versus nuclear magnetic resonance (NMR) experiments. Past MD results have consistently shown less than 5% five‐coordinated Al units (Al[5]) in peraluminous glass compositions, but with high fractions of triple‐bonded oxygens (TBO, i.e., triclusters). Experimental results have shown a high fraction of Al[5]with no direct evidence for TBO. One of the main criticisms associated with high TBO content found in MD‐generated glass structures is the use of classical interatomic potentials. To investigate this issue, we analyze the formation of both TBO and Al[5]using three independently developed potentials with varying silica content and [Al2O3]/[MgO] ratios for the magnesium aluminosilicate (MAS) system. We specifically choose compositions with high ratios of alumina to magnesium oxide as this region is not as commonly explored. Results indicate that Al[5]charge compensates the Al network in metaluminous compositions (compositions with more Mg than Al) while both TBO and Al[5]are prevalent in peraluminous ranges (high Al content compositions) to charge balance Al units. From the literature, NMR experiments report MAS glasses with varying Al[5]fractions and show significant differences for the same reported compositions. When comparing MD results from this work, the fraction of calculated Al[5]is within the experimental variation found in the literature. This indicates that classical potentials can accurately capture alumina environments and that both Al[5]and TBO can coexist in relatively high fractions. From the consistency in our results, we conclude that TBOs are inherent to the aluminosilicate glass system and are not simulation artifacts.
-
more » « less
Abstract Machine learning interatomic potentials (IPs) can provide accuracy close to that of first-principles 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.
-
more » « less
Machine learning (ML) continues to revolutionize computational chemistry for accelerating predictions and simulations by training on experimental or accurate but expensive quantum mechanical (QM) calculations. Photodynamics simulations require hundreds of trajectories coupled with multiconfigurational QM calculations of excited-state potential energies surfaces that contribute to the prohibitive computational cost at long timescales and complex organic molecules. ML accelerates photodynamics simulations by combining nonadiabatic photodynamics simulations with an ML model trained with high-fidelity QM calculations of energies, forces, and non-adiabatic couplings. This approach has provided time-dependent molecular structural information for understanding photochemical reaction mechanisms of organic reactions in vacuum and complex environments (i.e., explicit solvation). This review focuses on the fundamentals of QM calculations and ML techniques. We, then, discuss the strategies to balance adequate training data and the computational cost of generating these training data. Finally, we demonstrate the power of applying these ML-photodynamics simulations to understand the origin of reactivities and selectivities of organic photochemical reactions, such as cis–trans isomerization, [2 + 2]-cycloaddition, 4π-electrostatic ring-closing, and hydrogen roaming mechanism.
-
Grein, Christoph (Ed.)Phonons, as quantized vibrational modes in crystalline materials, play a crucial role in determining a wide range of physical properties, such as thermal and electrical conductivity, making their study a cornerstone in materials science. In this study, we present a simple yet effective strategy for deep learning harmonic phonons in crystalline solids by leveraging existing phonon databases and state-of-the-art machine learning techniques. The key of our method lies in transforming existing phonon datasets, primarily represented in interatomic force constants, into a force-displacement representation suitable for training machine learning universal interatomic potentials. By applying our approach to one of the largest phonon databases publicly available, we demonstrate that the resultant machine learning universal harmonic interatomic potential not only accurately predicts full harmonic phonon spectra but also calculates key thermodynamic properties with remarkable precision. Furthermore, the restriction to a harmonic potential energy surface in our model provides a way of assessing uncertainty in machine learning predictions of vibrational properties, essential for guiding further improvements and applications in materials science.more » « less
