Abstract
We present a novel deep learning (DL) approach to produce highly accurate predictions of macroscopic physical properties of solid solution binary alloys and magnetic systems. The major idea is to make use of the correlations between different physical properties in alloy systems to improve the prediction accuracy of neural network (NN) models. We use multitasking NN models to simultaneously predict the total energy, charge density and magnetic moment. These physical properties mutually serve as constraints during the training of the multitasking NN, resulting in more reliable DL models because multiple physics properties are correctly learned by a single model. Two binary alloys, copper-gold (CuAu) and iron-platinum (FePt), were studied. Our results show that once the multitasking NN's are trained, they can estimate the material properties for a specific configuration hundreds of times faster than first-principles density functional theory calculations while retaining comparable accuracy. We used a simple measure based on the root-mean-squared errors to quantify the quality of the NN models, and found that the inclusion of charge density and magnetic moment as physical constraints leads to more stable models that exhibit improved accuracy and reduced uncertainty for the energy predictions.
Original language | English |
---|---|
Article number | 084005 |
Journal | Journal of Physics Condensed Matter |
Volume | 33 |
Issue number | 8 |
DOIs | |
State | Published - 2020 |
Keywords
- alloy
- first principles
- machine learning
Fingerprint
Dive into the research topics of 'Fast and stable deep-learning predictions of material properties for solid solution alloys'. Together they form a unique fingerprint.Datasets
-
CuAu binary alloy with 32 atoms - LSMS-3 data
Lupo Pasini, M. (Creator) & Eisenbach, M. (Creator), Constellation by Oak Ridge Leadership Computing Facility (OLCF), Feb 15 2021
Dataset
-
FeSi binary alloy electronic structure low-Si dataset (1024 atoms)
Lupo Pasini, M. (Creator), Reeve, S. T. (Creator), Samolyuk, G. (Creator), Ellis, D. (Creator) & Eisenbach, M. (Creator), Constellation by Oak Ridge Leadership Computing Facility (OLCF), Feb 15 2021
DOI: 10.13139/ORNLNCCS/1765080
Dataset
-
FePt binary alloy with 32 atoms - LSMS-3 data
Lupo Pasini, M. (Creator) & Eisenbach, M. (Creator), Constellation by Oak Ridge Leadership Computing Facility (OLCF), Feb 15 2021
Dataset