It is demonstrated that explicitly incorporating the domain knowledge of the interatomic bonds can significantly and systematically improve the prediction of $\beta$-ZnS/NaCl stability and an increasing amount of bond-informed recursion features improves the predictive accuracy.
Abstract
The prediction of the structural stability of octet $AB$-type binary compounds is a classical materials informatics problem. The challenge is to capture the relative stability of 4-fold coordinated atoms in zincblende ($\beta$-ZnS) structure and 6-fold coordinated atoms in rocksalt (NaCl) structure, modulated by charge transfer and atomic-size differences. Previous structure maps and machine-learning approaches used atomic features such as valence-electron count, ionization potential and atomic radii, using either physical intuition or symbolic regression. Here, we demonstrate that explicitly incorporating the domain knowledge of the interatomic bonds can significantly and systematically improve the prediction of $\beta$-ZnS/NaCl stability. We encode this bonding information through a coarse-grained representation of the local electronic structure obtained by a recursive solution of a tight-binding bond model. The underlying pairwise Hamiltonians are taken from downfolded eigenstates of density-functional theory calculations for diatomic molecules and thereby include domain knowledge of the bond between specific $A-B$ pairs. The benefit of this description is demonstrated with an ensemble of independently trained Kernel Ridge or symbolic regression models combined with sequential feature selection. The obtained models are compared to a previous symbolic-regression model using the same set of \emph{ab initio} calculations for octet binaries as training data. We find a significant improvement in the prediction of the formation energy difference of $AB$ compounds as compared to previous works and demonstrate that an increasing amount of bond-informed recursion features improves the predictive accuracy.
Transformer Atomic Cluster Expansion (TRACE) is introduced, an energy-conserving architecture that combines atomic cluster expansion density correlations with local multihead cross-attention that captures multi-species crystallization, liquid structures, phase diagrams, and chemical reactivity.
SALTED provides an open-source Python package for machine learning the quantum-mechanical electron density, $n(\mathbf{r})$, in molecular and condensed-phase systems based on input atomic coordinates and species. The program adopts a linear atom-centered decomposition of the electron density, which makes it highly transferable across diverse atomistic configurations sharing similar chemical environments. Because of this representation choice, SALTED is naturally interfaced with state-of-the-art electronic-structure programs based on atomic orbitals, namely CP2K, FHI-aims, and PySCF, from which reference electron-density data can be generated and used to train a model. The learning algorithm is based on a symmetry-adapted extension of Gaussian process regression, making SALTED especially efficient in small-data regimes. Thanks to the implementation of vector-field kernel functions, SALTED can also learn the first-order response of the electron density to applied electric fields, $\partial n(\mathbf{r})/\partial \mathbf{E}$. The application of SALTED within computational workflows has already shown its utility in a wide variety of contexts, including the calculation of polarization vectors and polarizability tensors, the accurate evaluation of Coulomb forces in QM/MM molecular-dynamics simulations, and electronic-structure studies of large-scale 2D materials.
Zekun Lou, Alan M. Lewis, Théophane Bernhard et al.· 0 citations
This study detected anomalies in experimental structures that had already passed all prior validation, as well as limitations in the reliability of the MLIP PES calculations, and similarity descriptors were calculated to quantify the differences between the original and optimized structures.
This work proposes an operator-centric framework in which the external (nuclear) potential, expressed in an AO basis, serves as the model input and builds hierarchical, body-ordered representations of atomic configurations that closely mirror the principles underlying several popular atom-centered descriptors.
Jigyasa Nigam, T. Smidt, G. Dusson· Journal of Chemical Physics· 2 citations
The electronic density of states (DOS) is conventionally computed from a relaxed crystal structure, which is unavailable for compounds that have been neither synthesized nor cataloged. Here we introduce DOSSIER ($\textbf{D}$ensity $\textbf{o}$f $\textbf{S}$tates from $\textbf{S}$to$\textbf{i}$chiometry with $\textbf{E}$ncoder $\textbf{R}$epresentations), a chemical language model that maps elemental composition directly to this spectrum. The encoder is pretrained by cross-modal knowledge distillation from a universal machine-learning interatomic potential; the transfer lowers the error by 11% when only 1,000 training examples are available. On the Mat2Spec benchmark, DOSSIER reaches a mean absolute error of 3.76 states eV$^{-1}$ against 3.64 for the best structure-aware model; on an extended Materials Project dataset, the predicted spectra yield band gaps and $\textit{d}$-band descriptors with useful accuracy. Screening 11,977 binary and 13,251 five-component high-entropy alloy compositions for a $\textit{d}$-projected DOS resembling that of NiPt$_{3}$ places known oxygen reduction electrocatalysts near the top of the ranking.
Ivan D. Rubtsov, Ivan V Dudakov, Vadim V. Korolev· 0 citations
Equimolar NaCa(BH$_4$)$_3$ offers a theoretical hydrogen capacity of 11.24 wt.% and a decomposition enthalpy expected to fall between those of NaBH$_4$ and Ca(BH$_4$)$_2$, but it has never been prepared and no crystal structure has been reported. Predictions for it have so far been built within the perovskite family that its heavier homologues adopt. Here that assumption is removed. Six candidate frameworks were assembled from three independent sources --- experimentally determined ABX$_3$ borohydrides, a distorted perovskite from data-driven structure prediction, and an unbiased search over a structural database in which all 2238 generated candidates were relaxed with none excluded --- and at fixed charge-neutral composition the cation arrangement of every framework was enumerated exhaustively, 420 decorations reducing to 118 symmetry-inequivalent configurations, screened with a machine-learning potential and settled from first principles. The most stable structure is not a perovskite. It is a monoclinic framework of space group Cm, reached only by the unrestricted search, at $-$4.185640 eV/atom, 7.67 meV/atom below the best framework available beforehand; two chemically unrelated donor prototypes converge on it to 0.076 meV/atom, and its ordered cation arrangement is the ground state of its own series. Its phonon spectrum carries no imaginary mode at any wavevector the supercell resolves exactly and its relaxed-ion elastic tensor is positive definite, whereas the orthorhombic perovskite candidate is unstable to $-$2.401 THz. That contrast supplies a physical reason for the reported failure to obtain this composition in perovskite form, and the simulated diffraction pattern reported here identifies the predicted framework by seven reflections that neither parent phase nor the competing framework produces.
Sanaa Ismail, Ricardo Amaral, A. Gadallah et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
