Monitoring the role of site chemistry on the formation energy of perovskites via deep learning analysis of Hirshfeld surfaces. Issue 34 (29th July 2021)

• Record Type: Journal Article
• Authors: Williams, Logan; Mukherjee, Arpan; Dasgupta, Aparajita; Rajan, Krishna
• Is Part Of: Journal of materials chemistry. Volume 9:Issue 34(2021)
• Page Start: 11153
• Page End: 11162
• Publication Date: 2021-07-29
• Subjects: Materials -- Periodicals; Chemistry, Analytic -- Periodicals; Optical materials -- Research -- Periodicals; Electronics -- Materials -- Research -- Periodicals; 543.0284
• DOI: 10.1039/d1tc01972d
• Languages: English
• ISSNs: 2050-7526

Abstract

Abstract : Machine learning based on atomic Hirshfeld surfaces shows promise for material property prediction of diverse crystal systems. Abstract : This paper presents a new approach for predicting thermodynamic properties of perovskites that harnesses deep learning and crystal structure fingerprinting based on Hirshfeld surface analysis. It is demonstrated that convolutional neural network methods capture critical features embedded in two-dimensional Hirshfeld surface fingerprints that enable a quantitative assessment of the formation energy of perovskites. Building on our recent work on lattice parameter prediction from Hirshfeld surface calculations, we show how transfer learning can be used to speed up the training of the neural network, allowing multiple properties to be trained using the same feature extraction layers. We also predict formation energies for various perovskite polymorphs, and our predictions are found to give generally improved performance over a well-established graph network method, but with the methods better suited to different types of datasets. Analysis of the structure types within the dataset reveals the Hirshfeld surface-based method to excel for the less symmetric and similar structures, while the graph network performs better for very symmetric and similar structures.