Discovery of New Plasmonic Metals via High‐Throughput Machine Learning

Shapera, Ethan P.; Schleife, André

doi:10.1002/adom.202200158

Cited by 3 publications

(4 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dielectric function, a fundamental spectral output from ab initio calculations, determines the material's response to electromagnetic waves. It also enables the calculation of crucial practical frequency-dependent optical properties, such as the refractive index, electron energy loss spectra, 22 quality factors for localized surface plasmon resonances and surface plasmon polaritons, 23 and the quantum efficiency of optical sensors and PV cells. 24 For material spectral properties such as phonon or electronic density of states, the full-energy density of occupied states is characterized by a known integral for each material, attributed to its atom or electron count.…”

Section: ■ Introductionmentioning

confidence: 99%

“…The dielectric function, a fundamental spectral output from ab initio calculations, determines the material’s response to electromagnetic waves. It also enables the calculation of crucial practical frequency-dependent optical properties, such as the refractive index, electron energy loss spectra, quality factors for localized surface plasmon resonances and surface plasmon polaritons, and the quantum efficiency of optical sensors and PV cells …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multioutput and Multifidelity Machine Learning Approach

Ibrahim,

Ataca

2024

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

The frequency-dependent optical spectrum is pivotal for a broad range of applications from material characterization to optoelectronics and energy harvesting. Data-driven surrogate models, trained on density functional theory (DFT) data, have effectively alleviated the scalability limitations of DFT while preserving its chemical accuracy, expediting material discovery. However, prevailing machine learning (ML) efforts often focus on scalar properties such as the band gap, overlooking the complexities of optical spectra. In this work, we employ deep graph neural networks (GNNs) to predict the frequency-dependent complexvalued dielectric function across the infrared, visible, and ultraviolet spectra directly from the crystal structures. We explore multiple architectures for the spectral multioutput representation of the dielectric function and utilize various multifidelity learning strategies, such as transfer learning and fidelity embedding, to address the challenges associated with the scarcity of high-fidelity DFT data. Additionally, we model key solar cell absorption efficiency metrics, demonstrating that learning these parameters is enhanced when integrated through a learning bias within the learning of the frequency-dependent absorption coefficient. This study demonstrates that leveraging multioutput and multifidelity ML techniques enables accurate predictions of optical spectra from crystal structures, providing a versatile tool for rapidly screening materials for optoelectronics, optical sensing, and solar energy applications across an extensive frequency spectrum.

show abstract

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multioutput and Multifidelity Machine Learning Approach

Ibrahim,

Ataca

2024

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

show abstract

“…Studies have also performed high-throughput screening using first-principles calculations and machine learning. 18,19) However, these studies only searched for conductive materials, and not carrier-doped semiconductors, as heat-shielding materials. A previous study proposed a prediction model that predicts the plasma frequency and visible light absorption from the chemical composition of a material.…”

Section: Introductionmentioning

confidence: 99%

“…A previous study proposed a prediction model that predicts the plasma frequency and visible light absorption from the chemical composition of a material. 18,19) However, this model could not easily be applied to carrier-doped semiconductors, because they were not included in the training data. Further, even if this model could be used to accurately predict semiconductors as a base material, they would not be suitable as a candidate heat-shielding material because of their lack of electrical conductivity.…”

Section: Introductionmentioning

confidence: 99%

High-throughput screening of heat-shielding carrier-doped semiconductor materials via first principles calculations

Yoshida

2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

Heat-shielding carrier-doped semiconductor materials that exploit the localized surface plasmon resonance of nanoparticles to absorb near-infrared light while transmitting visible light from sunlight were searched for using first-principles calculations. Carrier doping into semiconductors can be performed by element replacement/insertion; however, various replacement/insertion structures are possible, and consequently, many calculations are required. Therefore, in this study, we performed virtual carrier doping and calculated the heat-shielding characteristics with low computational cost. From among 2964 semiconductor materials, materials with low visible light absorption after carrier doping were extracted, and from among these, materials with high heat-shielding properties were extracted. For these materials, the bandgaps were calculated using hybrid functionals, and the dopability was evaluated using the branch point energy. Finally, 24 materials were proposed as candidates for heat-shielding materials.

show abstract