Materials Fingerprinting Classification

Spannaus, Adam; Law, Kody J. H.; Łuszczek, Piotr; Nasrin, Farzana; Micucci, Cassie Putman; Liaw, Peter K.; Santodonato, Louis J.; Keffer, David J.; Maroulas, Vasileios

doi:10.1016/j.cpc.2021.108019

Cited by 8 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There also exist applications to analyze the experimental results. Data from transmission electron microscopy, X-ray diffraction, and atom probe tomography have all been demonstrated to efficiently be used as the input to various ML models for crystal structure classification. ,, The extendibility and flexibility of our work also enable the possibility to adopt these descriptors as inputs, contributing to more meaningful insights for various materials and systems. Overall, we believe that this lightweight extendable stacking framework has shown great potential as a powerful scientific tool for effective structure classification in atomistic simulations.…”

Section: Discussionmentioning

confidence: 99%

Lightweight Extendable Stacking Framework for Structure Classification in Atomistic Simulations

Deng,

Wang,

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Identifying an atom's local crystal structure is one crucial step in many atomistic simulation analyses. However, many traditional methods are available to only a few limited types of structures, and their performance often relies on manually determined parameters, which may lead to poor classification results in complex material systems. Machine learning models can enhance accuracy and generalizability, but they typically require large amounts of data and computation. This issue could be more severe for deep-learning-based frameworks, especially when confronted with unfamiliar crystal structures. To address this challenge, we propose a lightweight and extendable stacked structure (LESS) classifier, which adopts bond orientational order parameters as features and assembles several efficient machine learning methods as based models. The LESS classifier can recognize a variety of crystal structures, e.g., amorphous, mono, and binary structures, with over 98.8% accuracy on our validation data set, outperforming many current methods even including some deep-learning methods. Our model can also conduct probabilistic classification that aids in the interpretation of atomic structures in complicated environments such as heterogeneous interfaces. Furthermore, when exposed to a completely unknown crystal structure, the LESS framework can efficiently incorporate this new knowledge with generative sampled data from the current model. Overall, our model exhibits great potential as an accurate and flexible atomic structure identification tool featuring high efficiency in both learning and retraining.

show abstract

Section: Discussionmentioning

confidence: 99%

Lightweight Extendable Stacking Framework for Structure Classification in Atomistic Simulations

Deng,

Wang,

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…These are exciting developments; however, there is still information lacunae on the creation of informative multiscale traits from 3D point cloud data. In this context, non-agricultural disciplines have reported a concept of fingerprinting using point cloud data ( Koutsoukas et al., 2014 ; Spannaus et al., 2021 ; Wang et al., 2021 ), but this is lacking in crop production and broader agriculture.…”

Section: Introductionmentioning

confidence: 99%

“Canopy fingerprints” for characterizing three-dimensional point cloud data of soybean canopies

et al. 2023

View full text Add to dashboard Cite

Advances in imaging hardware allow high throughput capture of the detailed three-dimensional (3D) structure of plant canopies. The point cloud data is typically post-processed to extract coarse-scale geometric features (like volume, surface area, height, etc.) for downstream analysis. We extend feature extraction from 3D point cloud data to various additional features, which we denote as ‘canopy fingerprints’. This is motivated by the successful application of the fingerprint concept for molecular fingerprints in chemistry applications and acoustic fingerprints in sound engineering applications. We developed an end-to-end pipeline to generate canopy fingerprints of a three-dimensional point cloud of soybean [Glycine max (L.) Merr.] canopies grown in hill plots captured by a terrestrial laser scanner (TLS). The pipeline includes noise removal, registration, and plot extraction, followed by the canopy fingerprint generation. The canopy fingerprints are generated by splitting the data into multiple sub-canopy scale components and extracting sub-canopy scale geometric features. The generated canopy fingerprints are interpretable and can assist in identifying patterns in a database of canopies, querying similar canopies, or identifying canopies with a certain shape. The framework can be extended to other modalities (for instance, hyperspectral point clouds) and tuned to find the most informative fingerprint representation for downstream tasks. These canopy fingerprints can aid in the utilization of canopy traits at previously unutilized scales, and therefore have applications in plant breeding and resilient crop production.

show abstract

“…Persistent homology is one of the central tools of topological data analysis and in recent years has found a number of applications to a diverse range of fields such as neuroscience [9,6], biology and biochemistry [8,20], materials science [23,17,21], and the study of sensor networks [10]. In order to apply persistent homology to a finite and discrete data set X, one must be able to convert X into a filtered simplicial complex for which the persistent homology groups can then be computed.…”

Section: Introductionmentioning

confidence: 99%

The homotopy category of acyclic complexes of pure-projective modules

Gillespie

2023

Forum Mathematicum

View full text Add to dashboard Cite

Let R be any ring with identity. We show that the homotopy category of all acyclic chain complexes of pure-projective R-modules is a compactly generated triangulated category. We do this by constructing abelian model structures that put this homotopy category into a recollement with two other compactly generated triangulated categories: The usual derived category of R and the pure derived category of R.

show abstract

Materials Fingerprinting Classification

Cited by 8 publications

References 45 publications

Lightweight Extendable Stacking Framework for Structure Classification in Atomistic Simulations

Lightweight Extendable Stacking Framework for Structure Classification in Atomistic Simulations

“Canopy fingerprints” for characterizing three-dimensional point cloud data of soybean canopies

The homotopy category of acyclic complexes of pure-projective modules

Contact Info

Product

Resources

About