An official website of the United States government
Abstract Density functional theory (DFT) has been a critical component of computational materials research and discovery for decades. However, the computational cost of solving the central Kohn–Sham equation remains a major obstacle for dynamical studies of complex phenomena at-scale. Here, we propose an end-to-end machine learning (ML) model that emulates the essence of DFT by mapping the atomic structure of the system to its electronic charge density, followed by the prediction of other properties such as density of states, potential energy, atomic forces, and stress tensor, by using the atomic structure and charge density as input. Our deep learning model successfully bypasses the explicit solution of the Kohn-Sham equation with orders of magnitude speedup (linear scaling with system size with a small prefactor), while maintaining chemical accuracy. We demonstrate the capability of this ML-DFT concept for an extensive database of organic molecules, polymer chains, and polymer crystals.
more »
« less
Large scale dataset of real space electronic charge density of cubic inorganic materials from density functional theory (DFT) calculations
Abstract Driven by the big data science, material informatics has attracted enormous research interests recently along with many recognized achievements. To acquire knowledge of materials by previous experience, both feature descriptors and databases are essential for training machine learning (ML) models with high accuracy. In this regard, the electronic charge density ρ ( r ), which in principle determines the properties of materials at their ground state, can be considered as one of the most appropriate descriptors. However, the systematic electronic charge density ρ ( r ) database of inorganic materials is still in its infancy due to the difficulties in collecting raw data in experiment and the expensive first-principles based computational cost in theory. Herein, a real space electronic charge density ρ ( r ) database of 17,418 cubic inorganic materials is constructed by performing high-throughput density functional theory calculations. The displayed ρ ( r ) patterns show good agreements with those reported in previous studies, which validates our computations. Further statistical analysis reveals that it possesses abundant and diverse data, which could accelerate ρ ( r ) related machine learning studies. Moreover, the electronic charge density database will also assists chemical bonding identifications and promotes new crystal discovery in experiments.
more »
« less
- PAR ID:
- 10326205
- Date Published:
- Journal Name:
- Scientific Data
- Volume:
- 9
- Issue:
- 1
- ISSN:
- 2052-4463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Thermoelectric materials harvest waste heat and convert it into reusable electricity. Thermoelectrics are also widely used in inverse ways such as refrigerators and cooling electronics. However, most popular and known thermoelectric materials to date were proposed and found by intuition, mostly through experiments. Unfortunately, it is extremely time and resource consuming to synthesize and measure the thermoelectric properties through trial-and-error experiments. Here, we develop a convolutional neural network (CNN) classification model that utilizes the fused orbital field matrix and composition descriptors to screen a large pool of materials to discover new thermoelectric candidates with power factor higher than 10 μW/cm K2. The model used our own data generated by high-throughput density functional theory calculations coupled with ab initio scattering and transport package to obtain electronic transport properties without assuming constant relaxation time of electrons, which ensures more reliable electronic transport properties calculations than previous studies. The classification model was also compared to some traditional machine learning algorithms such as gradient boosting and random forest. We deployed the classification model on 3465 cubic dynamically stable structures with non-zero bandgap screened from Open Quantum Materials Database. We identified many high-performance thermoelectric materials with ZT > 1 or close to 1 across a wide temperature range from 300 to 700 K and for both n- and p-type doping with different doping concentrations. Moreover, our feature importance and maximal information coefficient analysis demonstrates two previously unreported material descriptors, namely, mean melting temperature and low average deviation of electronegativity, that are strongly correlated with power factor and thus provide a new route for quickly screening potential thermoelectrics with high success rate. Our deep CNN model with fused orbital field matrix and composition descriptors is very promising for screening high power factor thermoelectrics from large-scale hypothetical structures.more » « less
-
While high-entropy alloys (HEAs) present exponentially large compositional space for alloy design, they also create enormous computational challenges to trace the compositional space, especially for the inherently expensive density functional theory calculations (DFT). Recent works have integrated machine learning into DFT to overcome these challenges. However, often these models require an intensive search of appropriate physics-based descriptors. In this paper, we employ a 3D convolutional neural network over just one descriptor, i.e., the charge density derived from DFT, to simplify and bypass the hunt for the descriptors. We show that the elastic constants of face-centered cubic multi-elemental alloys in the Ni–Cu–Au–Pd–Pt system can be predicted from charge density. In addition, using our recent PREDICT approach, we show that the model can be trained only on the charge densities of simpler binary and ternary alloys to effectively predict elastic constants in complex multi-elemental alloys, thereby further enabling easier property-tracing in the large compositional space of HEAs.more » « less
-
Discovering new materials with desired properties has been a dominant and crucial topic of interest in the field of materials science in the past few decades. In this work, novel carbon allotropes and ternary B–C–N structures were generated using the state-of-the-art RG 2 code. All structures were fully optimized using density functional theory with first-principles calculations. Several hundred carbon allotropes and ternary B–C–N structures were identified to be superhard materials. The thermodynamic stability of some randomly selected superhard materials was confirmed by evaluating the full phonon dispersions in the Brillouin zone. The new carbon allotropes and ternary B–C–N structures possess a wide range of mechanical properties generally and Vickers hardness specifically. Through 2D Pearson's correlation map, we first reproduced the well-accepted explanation and relationship of the Vickers hardness of the generated structures with other mechanical properties such as shear modulus, bulk modulus, Pugh's ratio, universal anisotropy, and Poisson's ratio. We then propose two fundamentally new descriptors from the electronic level, namely local potential and electron localization function averaged over a unit cell, both of which exhibit a strong correlation with Vickers hardness. More importantly, these descriptors are easy to access from first-principles calculations (at least two orders of magnitude faster than the traditional calculation of elastic constants), and thus can serve as a fast and accurate approach for screening superhard materials. We also combined these new descriptors with known composition and structural descriptors in the machine learning training process. The new descriptors significantly enhance the performance of the trained machine learning model in predicting the Vickers hardness of unknown materials, which provides strong evidence for local potential and electron localization function to be considered in future high-throughput computation. This work unravels more fundamental but previously unexplored knowledge about superhard materials and the newly proposed electronic level descriptors are expected to accelerate the discovery of new superhard materials.more » « less
-
By leveraging the fundamental doctrine of the quantum theory of atoms in molecules — the partitioning of the electron charge density (ρ) into regions bounded by surfaces of zero flux — we map the gradient field of ρ onto a two-dimensional space called the gradient bundle condensed charge density ([Formula: see text]). The topology of [Formula: see text] appears to correlate with regions of chemical significance in ρ. The bond wedge is defined as the image in ρ of the basin of attraction in [Formula: see text], analogous to the Bader atom, which is the basin of attraction in ρ. A bond bundle is defined as the union of bond wedges that share interatomic surfaces. We show that maxima in [Formula: see text] typically map to bond paths in ρ, though this is not necessarily always true. This observation addresses many of the concerns regarding the chemical significance of bond critical points and bond paths in the quantum theory of atoms in molecules.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1038/s41597-022-01158-z
