Revealing the Spectrum of Unknown Layered Materials with Superhuman Predictive Abilities

Cheon, Gowoon; Cubuk, Ekin D.; Antoniuk, Evan R.; Blumberg, Lavi; Goldberger, Joshua E.; Reed, Evan J.

doi:10.1021/acs.jpclett.8b03187

Cited by 28 publications

(17 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental realization of graphene in 2004 [ 1,2 ] inspired an ongoing search for novel energetically stable quasi‐2D materials and a detailed experimental and theoretical study of the influence of their reduced dimensionality. Recent theoretical reports based on high‐throughput screening and machine‐learning methods suggest that several thousand exfoliable, and largely unsynthesized, materials exist, [ 3,4 ] offering a rich pool of materials with diverse physical properties.…”

Section: Introductionmentioning

confidence: 99%

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers

Gillen

2021

Physica Status Solidi (b)

View full text Add to dashboard Cite

The optical spectra of vertically stacked MoSe2/WSe2 heterostructures contain additional “interlayer” excitonic peaks that are absent in the individual monolayer materials and exhibit a significant spatial charge separation in out‐of‐plane direction. A many‐body perturbation theory approach is used to simulate the excitonic spectra of MoSe2/WSe2 heterobilayers with three stacking orders, considering both momentum‐direct and momentum‐indirect excitons. The small oscillator strengths and the optical responses of the interlayer excitons are significantly stacking‐dependent and give rise to high radiative lifetimes in the range of 5–200 ns at low temperature for the “bright” interlayer excitons. Solving the finite‐momentum Bethe–Salpeter Equation (BSE), the lowest energy excitation is predicted to be an exciton over the fundamental indirect band gap, with a binding energy of 220 meV. However, in agreement with recent magneto‐optics experiments and previous theoretical studies, the simulations of the effective excitonic g‐factors suggest that the low energy momentum‐indirect excitons are not experimentally observed. The existence of “interlayer” C excitons with significant exciton binding energies and optical oscillator strengths is further revealed, which are analogous to the prominent band nesting excitons in mono‐ and few‐layer transition‐metal dichalcogenides.

show abstract

Section: Introductionmentioning

confidence: 99%

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers

Gillen

2021

Physica Status Solidi (b)

View full text Add to dashboard Cite

show abstract

“…Machine learning has already emerged as a promising tool for materials design [40][41][42][43] as well as building conceptual models [44][45][46]. The ability to find predictive, compressed representations of physical data using machine learning becomes truly useful to theoretical physics if we can use those representations to build new models.…”

mentioning

confidence: 99%

Unifying framework for strong and fragile liquids via machine learning: a study of liquid silica

Cubuk,

Liu,

Kaxiras

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The fragility of a glassforming liquid characterizes how rapidly its relaxation dynamics slow down with cooling. The viscosity of strong liquids follows an Arrhenius law with a temperatureindependent barrier height to rearrangements responsible for relaxation, whereas fragile liquids experience a much faster increase in their dynamics, suggesting a barrier height that increases with decreasing temperature. Strong glassformers are typically network glasses, while fragile glassformers are typically molecular or hard-sphere-like. As a result of these differences at the microscopic level, strong and fragile glassformers are usually treated separately from a theoretical point of view. Silica is the archetypal strong glassformer at low temperatures, but also exhibits a mysterious strong-tofragile crossover at higher temperatures. Here we show that softness, a structure-based machine learned parameter that has previously been applied to fragile glassformers provides a useful description of model liquid silica in the strong and fragile regimes, and through the strong-to-fragile crossover. Just as for fragile glassformers, the relationship between softness and dynamics is invariant and Arrhenius in all regimes, but the average softness changes with temperature. The strong-to-fragile crossover in silica is not due to a sudden, qualitative change in structure, but can be explained by a simple Arrhenius form with a continuously and linearly changing local structure. Our results unify the study of liquid silica under a single simple conceptual picture.

show abstract

“…The importance of the descriptor selection from physical considerations has been observed for a diverse set of materials science applications; [1][2][3][4][5][16][17][18][19][20][21][22][23][24][25][26] however, it is not always possible to find the relevant physical descriptors for the desired application. Furthermore, even if physical descriptors have been identified, they are not always easily accessible.…”

Section: Article Scitationorg/journal/jcpmentioning

confidence: 99%

Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data

Cubuk

Sendek

Reed

2019

The Journal of Chemical Physics

Self Cite

118

101

View full text Add to dashboard Cite

Machine learning (ML) methods have the potential to revolutionize materials design, due to their ability to screen materials efficiently. Unlike other popular applications such as image recognition or language processing, large volumes of data are not available for materials design applications. Here, we first show that a standard learning approach using generic descriptors does not work for small data, unless it is guided by insights from physical equations. We then propose a novel method for transferring such physical insights onto more generic descriptors, allowing us to screen billions of unknown compositions for Li-ion conductivity, a scale which was previously unfeasible. This is accomplished by using the accurate model trained with physical insights to create a large database, on which we train a new ML model using the generic descriptors. Unlike previous applications of ML, this approach allows us to screen materials which have not necessarily been tested before (i.e., not on ICSD or Materials Project). Our method can be applied to any materials design application where a small amount of data is available, combined with high details of physical understanding.

show abstract

Revealing the Spectrum of Unknown Layered Materials with Superhuman Predictive Abilities

Cited by 28 publications

References 41 publications

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers

Unifying framework for strong and fragile liquids via machine learning: a study of liquid silica

Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data

Contact Info

Product

Resources

About

Revealing the Spectrum of Unknown Layered Materials with Superhuman Predictive Abilities

Cited by 28 publications

References 41 publications

Interlayer Excitonic Spectra of Vertically Stacked MoSe2/WSe2 Heterobilayers

Interlayer Excitonic Spectra of Vertically Stacked MoSe2/WSe2 Heterobilayers

Unifying framework for strong and fragile liquids via machine learning: a study of liquid silica

Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data

Contact Info

Product

Resources

About

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers

Interlayer Excitonic Spectra of Vertically Stacked MoSe₂/WSe₂ Heterobilayers