Scalable Graphene Defect Prediction Using Transferable Learning

Abstract

Notably known for its extraordinary thermal and mechanical properties, graphene is a favorable building block in various cutting-edge technologies such as flexible electronics and supercapacitors. However, the almost inevitable existence of defects severely compromises the properties of graphene, and defect prediction is a difficult, yet important, task. Emerging machine learning approaches offer opportunities to predict target properties such as defect distribution by exploiting readily available data, without incurring much experimental cost. Most previous machine learning techniques require the size of training data and predicted material systems of interest to be identical. This limits their broader application, because in practice a newly encountered material system may have a different size compared with the previously observed ones. In this paper, we develop a transferable learning approach for graphene defect prediction, which can be used on graphene with various sizes or shapes not seen in the training data. The proposed approach employs logistic regression and utilizes data on local vibrational energy distributions of small graphene from molecular dynamics simulations, in the hopes that vibrational energy distributions can reflect local structural anomalies. The results show that our machine learning model, trained only with data on smaller graphene, can achieve up to 80% prediction accuracy of defects in larger graphene under different practical metrics. The present research sheds light on scalable graphene defect prediction and opens doors for data-driven defect detection for a broad range of two-dimensional materials.

Designing mechanically tough graphene oxide materials using deep reinforcement learning

“…Graphene, a monolayer carbon allotrope, has been regarded as a cornerstone in materials science research ever since its discovery 1 . As such, there are several research directions related to graphene in both computational and experimental works in science and engineering applications [2][3][4][5] . Graphene oxide (GO), one of the bestknown graphene derivatives, inherits many unique and exquisite properties of graphene and is playing an increasingly important role in various research areas such as electronics, energy storage, and biomedical applications [6][7][8][9][10][11][12] .…”

Uncertainty quantification and prediction for mechanical properties of graphene aerogels via Gaussian process metamodels

“…Nanomaterials have influenced the energy and healthcare fields due to their unique optical, electronic, and mechanical properties [1][2][3][4][5][6]. For instance, graphene sheets are considered the strongest material ever tested due to their planar hexagonal lattice structure and the covalent bonding between carbon atoms and have been widely studied in the literature [7][8][9][10]. As a 3D extension of graphene, graphene aerogels (GAs), 3D porous assemblies of 2D graphene sheets, inherit many properties of graphene and manifest a desirable combination of low density and high strength [11,12].…”