Deep Learning to Speed up the Development of Structure–Property Relations For Hexagonal Boron Nitride and Graphene

Abstract Structure–property maps play a key role in accelerated materials discovery. The current norm for developing these maps includes computationally expensive physics‐based simulations. Here, the capabilities of deep learning agents are explored such as convolutional neural networks (CNNs) and multilayer perceptrons (MLPs) to predict structure–property relations and reduce dependence on simulations. This study contains simulated hexagonal boron nitride (h‐BN) microstructures damaged by various levels of radiation and temperature, with the objective to predict their residual strengths from the final atomic positions. By developing low dimensional physical descriptors to statistically describe the defects, these results show that purpose‐specific microstructure representation can help in achieving a good prediction accuracy at low computational cost. Furthermore, the adaptability of the trained deep learning agents is explored to predict structure–property maps of other 2D materials using transfer learning. It is shown that in order to achieve good predictions accuracy (≈95% R²), an agent that is training for the first time (“learning from scratch”) requires 23–45% of simulated data, whereas an agent adapting to a different material (“transfer learning”) requires only about 10% or less. This suggests that transfer learning is a potential game changer in material discovery and characterization approaches.