Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures

no code implementations • npj Computational Materials 2021 • Long T., Fortunato N.M., Opahle I., Zhang Y., Samathrakis I., Shen C., Gutfleisch O., Zhang H.

Autonomous materials discovery with desired properties is one of the ultimate goals for materials science, and the current studies have been focusing mostly on high-throughput screening based on density functional theory calculations and forward modeling of physical properties using machine learning.

Formation Energy Generative Adversarial Network