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.


  • NSF Public Access
  • Search Results
  • Development of a Robust CNN Model for Capturing Microstructure-Property Linkages and Building Property Closures Supporting Material Design
Title: Development of a Robust CNN Model for Capturing Microstructure-Property Linkages and Building Property Closures Supporting Material Design
Recent works have demonstrated the viability of convolutional neural networks (CNN) for capturing the highly non-linear microstructure-property linkages in high contrast composite material systems. In this work, we develop a new CNN architecture that utilizes a drastically reduced number of trainable parameters for building these linkages, compared to the benchmarks in current literature. This is accomplished by creating CNN architectures that completely avoid the use of fully connected layers, while using the 2-point spatial correlations of the microstructure as the input to the CNN. In addition to increased robustness (because of the much smaller number of trainable parameters), the CNN models developed in this work facilitate the construction of property closures at very low computational cost. This is because it allows for easy exploration of the space of valid 2-point spatial correlations, which is known to be a convex hull. Consequently, one can generate new sets of valid 2-point spatial correlations from previously available valid sets of 2-point spatial correlations, simply as convex combinations. This work demonstrates the significant benefits of utilizing 2-point spatial correlations as the input to the CNN, in place of the voxelated discrete microstructures used in current benchmarks.  more » « less
Award ID(s):
2027105
PAR ID:
10337651
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Frontiers in Materials
Volume:
9
ISSN:
2296-8016
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; (, Integrating Materials and Manufacturing Innovation)
    Abstract There are two broad modeling paradigms in scientific applications: forward and inverse. While forward modeling estimates the observations based on known causes, inverse modeling attempts to infer the causes given the observations. Inverse problems are usually more critical as well as difficult in scientific applications as they seek to explore the causes that cannot be directly observed. Inverse problems are used extensively in various scientific fields, such as geophysics, health care and materials science. Exploring the relationships from properties to microstructures is one of the inverse problems in material science. It is challenging to solve the microstructure discovery inverse problem, because it usually needs to learn a one-to-many nonlinear mapping. Given a target property, there are multiple different microstructures that exhibit the target property, and their discovery also requires significant computing time. Further, microstructure discovery becomes even more difficult because the dimension of properties (input) is much lower than that of microstructures (output). In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling of structure–property linkages in materials, i.e., microstructure discovery for a given property. The results demonstrate that compared to baseline methods, the proposed framework can overcome the above-mentioned challenges and discover multiple promising solutions in an efficient manner. 
    more » « less
  2. ; ; (, Mobile Multimedia/Image Processing, Security, and Applications 2020)
    Agaian, Sos S.; Jassim, Sabah A.; DelMarco, Stephen P.; Asari, Vijayan K. (Ed.)
    Neural networks have emerged to be the most appropriate method for tackling the classification problem for hyperspectral images (HIS). Convolutional neural networks (CNNs), being the current state-of-art for various classification tasks, have some limitations in the context of HSI. These CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper. The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels, making it suitable for HSI datasets that are small and diverse. Experimental results on three HSI datasets demonstrate that the QHIC Net performs on par with the traditional CNN based methods for HSI Classification with a far fewer number of parameters. Keywords: Classification, deep learning, hyperspectral imaging, spectral-spatial feature learning 
    more » « less
  3. ; (, Canadian Conference on Computational Geometry)
    Caratheodory’s theorem says that any point in the convex hull of a set $$P$$ in $R^d$ is in the convex hull of a subset $P'$ of $$P$$ such that $$|P'| \le d + 1$$. For some sets P, the upper bound d + 1 can be improved. The best upper bound for P is known as the Caratheodory number [2, 15, 17]. In this paper, we study a computational problem of finding the smallest set $P'$ for a given set $$P$$ and a point $$p$$. We call the size of this set $P'$, the Caratheodory number of a point p or CNP. We show that the problem of deciding the Caratheodory number of a point is NP-hard. Furthermore, we show that the problem is k-LDT-hard. We present two algorithms for computing a smallest set $P'$, if CNP= 2,3. Bárány [1] generalized Caratheodory’s theorem by using d+1 sets (colored sets) such that their convex hulls intersect. We introduce a Colorful Caratheodory number of a point or CCNP which can be smaller than d+1. Then we extend our results for CNP to CCNP. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; (, Molecular Systems Design & Engineering)
    Data-driven methods have attracted increasingly more attention in materials research since the advent of the material genome initiative. The combination of materials science with computer science, statistics, and data-driven methods aims to expediate materials research and applications and can utilize both new and archived research data. In this paper, we present a data driven and deep learning approach that builds a portion of the structure–property relationship for polymer nanocomposites. Analysis of archived experimental data motivates development of a computational model which allows demonstration of the approach and gives flexibility to sufficiently explore a wide range of structures. Taking advantage of microstructure reconstruction methods and finite element simulations, we first explore qualitative relationships between microstructure descriptors and mechanical properties, resulting in new findings regarding the interplay of interphase, volume fraction and dispersion. Then we present a novel deep learning approach that combines convolutional neural networks with multi-task learning for building quantitative correlations between microstructures and property values. The performance of the model is compared with other state-of-the-art strategies including two-point statistics and structure descriptor-based approaches. Lastly, the interpretation of the deep learning model is investigated to show that the model is able to capture physical understandings while learning. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, Land Economics)
    We discuss data quality and modeling issues inherent in the use of nationwide property data to value environmental amenities. By example of ZTRAX, a U.S.-wide real estate database, we identify challenges and propose guidance for: (1) the identification of arm’s-length sales, (2) the geo-location of parcels and buildings, (3) temporal linkages between transaction, assessor, and parcel data, (4) the identification of property types, such as single-family homes and vacant lands, and (5) dealing with missing or mismeasured data for standard housing attributes. We review current practice and show that how researchers address these issues can meaningfully influence research findings. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email