An official website of the United States government
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.
more »
« less
Deep Learning Based Prediction of Perovskite Lattice Parameters from Hirshfeld Surface Fingerprints
This Letter describes the use of deep learning methods on Hirshfeld surface representations of crystal structure, as an automated means of predicting lattice parameters in cubic inorganic perovskites. While Hirshfeld Surface Analysis is a well-established tool in organic crystallography, we also introduce modified computational protocols for Hirshfeld Surface Analysis tailored specifically to account for nuanced but important differences dealing with inorganic crystals. We demonstrate how two-dimensional Hirshfeld surface fingerprints can serve as a rich “database” of information encoding the complexity of relationships between chemical bonding and bond geometry characteristics of perovskites. Our results are compared with other studies on lattice parameter prediction involving both experimental and computationally derived data, and it is shown that our approach is an improvement over other reported methods. The paper concludes by discussing how this work opens new avenues for data-driven high throughput computational predictions of structure–property relationships involving complex crystal chemistries.
more »
« less
- Award ID(s):
- 1640867
- PAR ID:
- 10189009
- Date Published:
- Journal Name:
- The Journal of Physical Chemistry Letters
- ISSN:
- 1948-7185
- Page Range / eLocation ID:
- 7462 to 7468
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Low-dimensional organic/inorganic hybrid perovskites (OIHPs) are a promising class of materials with a wide range of potential applications in optoelectronics and other fields since these materials can synergistically combine individual features of organic molecules and inorganics into unique properties. Non-covalent interactions are commonly observed in OIHPs, in particular, π-effect interactions between the organic cations. Such non-covalent interactions can significantly influence important properties of the low-dimensional OIHPs, including dielectric confinement, bandgap, photoluminescence, quantum efficiency, charge mobility, trap density, stability, and chirality. This perspective reviews recent studies of non-covalent interactions involving the π systems of organic cations in low-dimensional OIHPs. The analysis of crystal structures of low-dimensional OIHPs offers significant insight into understanding such non-covalent interactions and their impacts on specific properties of these OIHPs. The developed structure–property relationships can be used to engineer non-covalent interactions in low-dimensional OIHPs for applications.more » « less
-
Abstract This article describes a machine learning guided framework for screening the potential toxicity impact of amine chemistries used in the synthesis of hybrid organic–inorganic perovskites. Using a combination of a probabilistic molecular fingerprint technique that encodes bond connectivity (MinHash) coupled to non‐linear data dimensionality reduction methods (Uniform Manifold Approximation and Projection), we develop an “Amine Atlas.” We show how the Amine Atlas can be used to rapidly screen the relative toxicity levels of amine molecules used in the synthesis of 2D and 3D perovskites and help identify safer alternatives. Our work also serves as a framework for rapidly identifying molecular similarity guided, structure–function relationships for safer materials chemistries that also incorporate sustainability/toxicity concerns.more » « less
-
Bragg coherent X-ray diffractive imaging is a cutting-edge method for recovering three-dimensional crystal structure with nanoscale resolution. Phase retrieval provides an atomic displacement parallel to the Bragg peak reciprocal lattice vector. The derivative of the displacement along the same vector provides the normal strain field, which typically serves as a proxy for any structural changes. In this communication it is found that the other component of the displacement gradient, perpendicular to the reciprocal lattice vector, provides additional information from the experimental data collected from nanocrystals with mobile dislocations. Demonstration on published experimental data show how the perpendicular component of the displacement gradient adds to existing analysis, enabling an estimate for the external stresses, pinpointing the location of surface dislocations, and predicting the dislocation motion in in situ experiments.more » « less
-
Two-dimensional (2D) organic–inorganic hybrid halide perovskites exhibit unique properties, such as long charge carrier lifetimes, high photoluminescence quantum efficiencies, and great tolerance to defects. Over the last several decades tremendous progress has occurred in the development of 2D layered halide perovskite semiconductor materials and devices. Chemical functionalization of 2D halide perovskites is an effective approach for tuning their electronic properties. A large amount of effort has been made in compositional engineering of the cations and anions in the perovskite lattice. However, few efforts have incorporated rationally designed semiconducting organic moieties into these systems to alter the overall chemical and optoelectronic properties of 2D perovskites. In fact, incorporation of large conjugated organic groups in the spatially confined inorganic perovskite matrix was found to be challenging, and this synthetic challenge hinders a deeper understanding of the materials’ structure–property relationships. Recently, exciting progress has been made regarding the molecular design, optical characterization, and device fabrication of novel 2D halide perovskite materials that incorporate functional organic semiconducting building blocks. In this article, we provide a timely review regarding this recent progress. Moreover, we discuss successes and current challenges regarding the synthesis, characterization, and device applications of such hybrid materials and provide a perspective on the true future promise of these advanced nanomaterials.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1021/acs.jpclett.0c02201
