Understanding and Predicting the Cause of Defects in Graphene Oxide Nanostructures Using Machine Learning

Motevalli, Benyamin; Sun, Baichuan; Barnard, Amanda S.

doi:10.1021/acs.jpcc.9b10615

Cited by 39 publications

(35 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…39 By combining a sufficiently large and diverse ensemble of candidate nanostructures generated using conventional simulations with an appropriate regressor it is possible to identify the set of features that drive performance, 40 and in some cases conditions required to deliver the right structures in practice. 41 ML is also capable of determining classes of like-structures based on similarity, and then correlate these classes with some performance indicators to provide a more averaged response to structure/property prediction, akin to measuring a diverse mix of sizes and shapes. 42,43 Most importantly, ML is providing to be invaluable in the modern design of catalysts.…”

Section: Introductionmentioning

confidence: 99%

Classification of platinum nanoparticle catalysts using machine learning

Parker

Opletal

Barnard³

2020

Journal of Applied Physics

Self Cite

View full text Add to dashboard Cite

Computer simulations and machine learning provide complementary ways of identifying structure/property relationships that are typically targeting toward predicting the ideal singular structure to maximise the performance on a given application. This can be inconsistent with experimental observations that measure the collective properties of entire samples of structures that contain distributions or mixture of structures, even when synthesized and processed with care. Metallic nanoparticle catalysts are an important example. In this study we have used a multi-stage machine learning workflow to identify the correct structure/property relationships of Pt nanoparticles relevant to oxygen reduction (ORR), hydrogen oxidation (HOR) and hydrogen evolution (HER) reactions. By including classification prior to regression we identified two distinct classes of nanoparticles, and subsequently generate the class-specific models based on experimentally relevant criteria that are consistent with observations. These multi-structure/multi-property relationships, predicting properties averaged over a large sample of structures, provide a more accessible way to transfer data-driven predictions into the lab. File list (2) download file view on ChemRxiv Pt-classification_revised.pdf (4.35 MiB) download file view on ChemRxiv Pt-classification_SI.pdf (4.60 MiB) Classification of Platinum Nanoparticles

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of platinum nanoparticle catalysts using machine learning

Parker

Opletal

Barnard³

2020

Journal of Applied Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some attempts to create larger databases of ML-based GO structures have been made. 62 , 63 We focus here on a more limited set of structures, because of the computational demands of full electronic-structure computations. Moreover, given the intrinsic locality of core–electron excitations, the results obtained here, within periodic boundary conditions, and utilizing data clustering, are representative of larger systems and can be directly compared with experiment.…”

Section: Resultsmentioning

confidence: 99%

X-ray Spectroscopy Fingerprints of Pristine and Functionalized Graphene

et al. 2021

View full text Add to dashboard Cite

In this work, we demonstrate how to identify and characterize the atomic structure of pristine and functionalized graphene materials from a combination of computational simulation of X-ray spectra, on the one hand, and computer-aided interpretation of experimental spectra, on the other. Despite the enormous scientific and industrial interest, the precise structure of these 2D materials remains under debate. As we show in this study, a wide range of model structures from pristine to heavily oxidized graphene can be studied and understood with the same approach. We move systematically from pristine to highly oxidized and defective computational models, and we compare the simulation results with experimental data. Comparison with experiments is valuable also the other way around; this method allows us to verify that the simulated models are close to the real samples, which in turn makes simulated structures amenable to several computational experiments. Our results provide ab initio semiquantitative information and a new platform for extended insight into the structure and chemical composition of graphene-based materials.

show abstract

“…[101] In another recent study by Motevalli et al, machine learning algorithms were used to understand and predict the cause of defects in graphene nanosheets. [102] Several such clever amalgamations of disciplines would provide us with valuable insights into graphene nanostructure fabrication and properties. In the future, graphene would, thus, inevitably be the "magic lamp" of nanotechnology with utmost promise.…”

Section: Discussionmentioning

confidence: 99%

Graphene‐Based Nanomaterials for Biomedical, Catalytic, and Energy Applications

Basak

Gopinath

2021

ChemistrySelect

View full text Add to dashboard Cite

Nanotechnology has provided us with unimaginable possibilities in addressing worldly challenges. Since its discovery in 2004, Graphene has been considered a "Holy Grail" of nanomaterials for its unprecedented applicability in different fields, including biomedical, energy harvest and storage, sensing applications. Throughout the world, tremendous waves of research have been going on to exploit graphene's unique thermal, mechanical, electrical, catalytic, and biological properties. Besides, efficient and tunable techniques of graphene's bulk manufacturing have been under thorough investigation. This article reviews various recent studies on large-scale graphene synthesis with tunable properties. Several different ways of graphene's use in various catalytic platforms are also reviewed. Furthermore, recent biomedical and energy (storage and harvest) applications of graphene, especially in microbial fuel cell technology, bio-sensing, antimicrobial applications, have been discussed in this article.

show abstract

Understanding and Predicting the Cause of Defects in Graphene Oxide Nanostructures Using Machine Learning

Cited by 39 publications

References 44 publications

Classification of platinum nanoparticle catalysts using machine learning

Classification of platinum nanoparticle catalysts using machine learning

X-ray Spectroscopy Fingerprints of Pristine and Functionalized Graphene

Graphene‐Based Nanomaterials for Biomedical, Catalytic, and Energy Applications

Contact Info

Product

Resources

About