Machine Learning Enabled Discovery of Application Dependent Design Principles for Two-dimensional Materials
This work addresses the problem of efficient material discovery for applications such as composites and photovoltaics, representing an incremental improvement by generalizing existing methods to new systems.
The researchers tackled the challenge of large-scale screening for high-performing 2D materials by extending crystal graph convolutional neural networks to planar periodic systems, training an ensemble to predict properties, and screening nearly 45,000 structures for applications like composites and photovoltaics, with errors comparable to accurate first-principles calculations.
The large-scale search for high-performing candidate 2D materials is limited to calculating a few simple descriptors, usually with first-principles density functional theory calculations. In this work, we alleviate this issue by extending and generalizing crystal graph convolutional neural networks to systems with planar periodicity, and train an ensemble of models to predict thermodynamic, mechanical, and electronic properties. To demonstrate the utility of this approach, we carry out a screening of nearly 45,000 structures for two largely disjoint applications: namely, mechanically robust composites and photovoltaics. An analysis of the uncertainty associated with our methods indicates the ensemble of neural networks is well-calibrated and has errors comparable with those from accurate first-principles density functional theory calculations. The ensemble of models allows us to gauge the confidence of our predictions, and to find the candidates most likely to exhibit effective performance in their applications. Since the datasets used in our screening were combinatorically generated, we are also able to investigate, using an innovative method, structural and compositional design principles that impact the properties of the structures surveyed and which can act as a generative model basis for future material discovery through reverse engineering. Our approach allowed us to recover some well-accepted design principles: for instance, we find that hybrid organic-inorganic perovskites with lead and tin tend to be good candidates for solar cell applications.