Nonparametric Local Pseudopotentials with Machine Learning: A Tin Pseudopotential Built Using Gaussian Process Regression

High-Quality Local Pseudopotentials for Metals

A major obstacle hindering the application of orbital-free density functional theory (OF-DFT) to all metals is the lack of accurate local pseudopotentials (LPSs), especially for transition metals. In this work, we developed high-quality LPSs for all simple and transition metals by fitting the atomic eigenvalues and orbital norms beyond the cutoff radii. Due to the lack of nonlocality in LPSs, it is very challenging to simultaneously fit the semicore and outermost valence orbitals of transition metals. We overcame this issue by excluding the semicore orbitals from the LPS optimizations. This allows us to achieve excellent fittings of the outermost valence orbitals, which are responsible for chemical bonding. The norm-conserving condition is then satisfied, leading to high-quality LPSs. To construct LPSs for magnetic systems, we introduce an additional metric: the atomic spin-polarization energy. By including this metric in the fitting, the LPSs reasonably reproduced many properties of magnetic metals and alloys. The high-quality LPSs developed in this work bring us one step closer to large-scale, reliable OF-DFT simulations of all metals and their alloys.

Neural network-based pseudopotential: development of a transferable local pseudopotential

Transferable local pseudopotentials (LPPs) are essential for fast quantum simulations of materials. However, various types of LPPs suffer from low transferability, especially since they do not consider the norm-conserving condition. Here we propose a novel approach based on a deep neural network to produce transferable LPPs. We introduced a generalized Kerker method expressed with the deep neural network to represent the norm-conserving pseudo-wavefunctions. Its unique feature is that all necessary conditions of pseudopotentials can be explicitly considered in terms of a loss function. Then, it can be minimized using the back-propagation technique just with single point all-electron atom data. To assess the transferability and accuracy of the neural network-based LPPs (NNLPs), we carried out density functional theory calculations for the s- and p-block elements of the second to the fourth periods. The NNLPs outperformed other types of LPPs in both atomic and bulk calculations for most elements. In particular, they showed good transferability by predicting various properties of bulk systems including binary alloys with higher accuracy than LPPs tailored to bulk data.

Perspective on integrating machine learning into computational chemistry and materials science

Machine learning (ML) methods are being used in almost every conceivable area of electronic structure theory and molecular simulation. In particular, ML has become firmly established in the construction of high-dimensional interatomic potentials. Not a day goes by without another proof of principle being published on how ML methods can represent and predict quantum mechanical properties-be they observable, such as molecular polarizabilities, or not, such as atomic charges. As ML is becoming pervasive in electronic structure theory and molecular simulation, we provide an overview of how atomistic computational modeling is being transformed by the incorporation of ML approaches. From the perspective of the practitioner in the field, we assess how common workflows to predict structure, dynamics, and spectroscopy are affected by ML. Finally, we discuss how a tighter and lasting integration of ML methods with computational chemistry and materials science can be achieved and what it will mean for research practice, software development, and postgraduate training.