skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Topological representations of crystalline compounds for the machine-learning prediction of materials properties
Abstract Accurate theoretical predictions of desired properties of materials play an important role in materials research and development. Machine learning (ML) can accelerate the materials design by building a model from input data. For complex datasets, such as those of crystalline compounds, a vital issue is how to construct low-dimensional representations for input crystal structures with chemical insights. In this work, we introduce an algebraic topology-based method, called atom-specific persistent homology (ASPH), as a unique representation of crystal structures. The ASPH can capture both pairwise and many-body interactions and reveal the topology-property relationship of a group of atoms at various scales. Combined with composition-based attributes, ASPH-based ML model provides a highly accurate prediction of the formation energy calculated by density functional theory (DFT). After training with more than 30,000 different structure types and compositions, our model achieves a mean absolute error of 61 meV/atom in cross-validation, which outperforms previous work such as Voronoi tessellations and Coulomb matrix method using the same ML algorithm and datasets. Our results indicate that the proposed topology-based method provides a powerful computational tool for predicting materials properties compared to previous works.  more » « less
Award ID(s):
1761320 1900473
PAR ID:
10271879
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
npj Computational Materials
Volume:
7
Issue:
1
ISSN:
2057-3960
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Scientific Reports)
    Abstract Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties. 
    more » « less
  2. ; ; ; (, npj Computational Materials)
    Abstract The prediction of crystal properties plays a crucial role in materials science and applications. Current methods for predicting crystal properties focus on modeling crystal structures using graph neural networks (GNNs). However, accurately modeling the complex interactions between atoms and molecules within a crystal remains a challenge. Surprisingly, predicting crystal properties from crystal text descriptions is understudied, despite the rich information and expressiveness that text data offer. In this paper, we develop and make public a benchmark dataset (TextEdge) that contains crystal text descriptions with their properties. We then propose LLM-Prop, a method that leverages the general-purpose learning capabilities of large language models (LLMs) to predict properties of crystals from their text descriptions. LLM-Prop outperforms the current state-of-the-art GNN-based methods by approximately 8% on predicting band gap, 3% on classifying whether the band gap is direct or indirect, and 65% on predicting unit cell volume, and yields comparable performance on predicting formation energy per atom, energy per atom, and energy above hull. LLM-Prop also outperforms the fine-tuned MatBERT, a domain-specific pre-trained BERT model, despite having 3 times fewer parameters. We further fine-tune the LLM-Prop model directly on CIF files and condensed structure information generated by Robocrystallographer and found that LLM-Prop fine-tuned on text descriptions provides a better performance on average. Our empirical results highlight the importance of having a natural language input to LLMs to accurately predict crystal properties and the current inability of GNNs to capture information pertaining to space group symmetry and Wyckoff sites for accurate crystal property prediction. 
    more » « less
  3. ; ; ; (, American Society of Mechanical Engineers (ASME))
    The level set method has been widely applied in topology optimization of mechanical structures, primarily for linear materials, but its application to nonlinear hyperelastic materials, particularly for compliant mechanisms, remains largely unexplored. This paper addresses this gap by developing a comprehensive level set-based topology optimization framework specifically for designing compliant mechanisms using neo-Hookean hyperelastic materials. A key advantage of hyperelastic materials is their ability to undergo large, reversible deformations, making them well-suited for soft robotics and biomedical applications. However, existing nonlinear topology optimization studies using the level set method mainly focus on stiffness optimization and often rely on linear results as preliminary approximations. Our framework rigorously derives the shape sensitivity analysis using the adjoint method, including crucial higher-order displacement gradient terms often neglected in simplified approaches. By retaining these terms, we achieve more accurate boundary evolution during optimization, leading to improved convergence behavior and more effective structural designs. The proposed approach is first validated with a mean compliance problem as a benchmark, demonstrating its ability to generate optimized structural configurations while addressing the nonlinear behavior of hyperelastic materials. Subsequently, we extend the method to design a displacement inverter compliant mechanism that fully exploits the advantages of hyperelastic materials in achieving controlled large deformations. The resulting designs feature smooth boundaries and clear structural features that effectively leverage the material's nonlinear properties. This work provides a robust foundation for designing advanced compliant mechanisms with large deformation capabilities, extending the reach of topology optimization into new application domains where traditional linear approaches are insufficient. The developed methodology is expected to provide a timely solution to computational design for soft robotics, flexible mechanisms, and other emerging technologies that benefit from hyperelastic material properties. 
    more » « less
  4. ; ; ; ; (, Frontiers in Materials)
    Machine learning (ML) models have emerged as powerful tools for accelerating materials discovery and design by enabling accurate predictions of properties from compositional and structural data. These capabilities are vital for developing advanced technologies across fields such as energy, electronics, and biomedicine, potentially reducing the time and resources needed for new material exploration and promoting rapid innovation cycles. Recent efforts have focused on employing advanced ML algorithms, including deep learning-based graph neural networks, for property prediction. Additionally, ensemble models have proven to enhance the generalizability and robustness of ML and Deep Learning (DL). However, the use of such ensemble strategies in deep graph networks for material property prediction remains underexplored. Our research provides an in-depth evaluation of ensemble strategies in deep learning-based graph neural network, specifically targeting material property prediction tasks. By testing the Crystal Graph Convolutional Neural Network (CGCNN) and its multitask version, MT-CGCNN, we demonstrated that ensemble techniques, especially prediction averaging, substantially improve precision beyond traditional metrics for key properties like formation energy per atom ( Δ E f ) , band gap ( E g ) , density ( ρ ) , equivalent reaction energy per atom ( E rxn,atom ) , energy per atom ( E atom ) and atomic density ( ρ atom ) in 33,990 stable inorganic materials. These findings support the broader application of ensemble methods to enhance predictive accuracy in the field. 
    more » « less
  5. ; ; ; (, Advanced Materials)
    Abstract Optical properties in solids, such as refractive index and absorption, hold vast applications ranging from solar panels to sensors, photodetectors, and transparent displays. However, first‐principles computation of optical properties from crystal structures is a complex task due to the high convergence criteria and computational cost. Recent progress in machine learning shows promise in predicting material properties, yet predicting optical properties from crystal structures remains challenging due to the lack of efficient atomic embeddings. Here, Graph Neural Network for Optical spectra prediction (GNNOpt) is introduced, an equivariant graph‐neural‐network architecture featuring universal embedding with automatic optimization. This enables high‐quality optical predictions with a dataset of only 944 materials. GNNOpt predicts all optical properties based on the Kramers‐Krönig relations, including absorption coefficient, complex dielectric function, complex refractive index, and reflectance. The trained model is applied to screen photovoltaic materials based on spectroscopic limited maximum efficiency and search for quantum materials based on quantum weight. First‐principles calculations validate the efficacy of the GNNOpt model, demonstrating excellent agreement in predicting the optical spectra of unseen materials. The discovery of new quantum materials with high predicted quantum weight, such as SiOs, which host exotic quasiparticles with multifold nontrivial topology, demonstrates the potential of GNNOpt in predicting optical properties across a broad range of materials and applications. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email