Shotgun crystal structure prediction using machine-learned formation energies

by   Chang Liu, et al.

Stable or metastable crystal structures of assembled atoms can be predicted by finding the global or local minima of the energy surface with respect to the atomic configurations. Generally, this requires repeated first-principles energy calculations that are impractical for large systems, such as those containing more than 30 atoms in the unit cell. Here, we have made significant progress in solving the crystal structure prediction problem with a simple but powerful machine-learning workflow; using a machine-learning surrogate for first-principles energy calculations, we performed non-iterative, single-shot screening using a large library of virtually created crystal structures. The present method relies on two key technical components: transfer learning, which enables a highly accurate energy prediction of pre-relaxed crystalline states given only a small set of training samples from first-principles calculations, and generative models to create promising and diverse crystal structures for screening. Here, first-principles calculations were performed only to generate the training samples, and for the optimization of a dozen or fewer finally narrowed-down crystal structures. Our shotgun method was more than 5–10 times less computationally demanding and achieved an outstanding prediction accuracy that was 2–6 times higher than that of the conventional methods that rely heavily on iterative first-principles calculations.


page 1

page 6

page 21

page 22


Crystal structure prediction with machine learning-based element substitution

The prediction of energetically stable crystal structures formed by a gi...

Machine Learning-Aided Discovery of Superionic Solid-State Electrolyte for Li-Ion Batteries

Li-Ion Solid-State Electrolytes (Li-SSEs) are a promising solution that ...

AdsorbML: Accelerating Adsorption Energy Calculations with Machine Learning

Computational catalysis is playing an increasingly significant role in t...

Learned Force Fields Are Ready For Ground State Catalyst Discovery

We present evidence that learned density functional theory (“DFT”) force...

Fast and accessible first-principles calculations of vibrational properties of materials

We present example applications of an approach to first-principles calcu...

The basic principles and the structure and algorithmically software of computing by hypercomplex number

In article the basic principles put in a basis of algorithmicallysoftwar...

Catalyst design using actively learned machine with non-ab initio input features towards CO2 reduction reactions

In conventional chemisorption model, the d-band center theory (augmented...

Please sign up or login with your details

Forgot password? Click here to reset