2021
DOI: 10.1039/d1sc00503k
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning dielectric screening for the simulation of excited state properties of molecules and materials

Abstract: Machine learning can circumvent explicit calculation of dielectric response in first principles methods and accelerate simulations of optical properties of complex materials at finite temperature.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
19
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 25 publications
(19 citation statements)
references
References 105 publications
(168 reference statements)
0
19
0
Order By: Relevance
“…We are exploring the possibility to extend mixed-precision regions to other memoryintensive or compute-intensive portions of the code, e.g., the storage of the non-local part of the pseudopotential and the evaluation of the exact exchange needed in hybrid density functionals. 118 Work is in progress to optimize the performance on GPUs of the electronphonon, 42,45,46 the Bethe-Salpeter equation (BSE) in finite field, 47,48 and the quantum em- (118) Vinson, J. Faster exact exchange in periodic systems using single-precision arithmetic.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…We are exploring the possibility to extend mixed-precision regions to other memoryintensive or compute-intensive portions of the code, e.g., the storage of the non-local part of the pseudopotential and the evaluation of the exact exchange needed in hybrid density functionals. 118 Work is in progress to optimize the performance on GPUs of the electronphonon, 42,45,46 the Bethe-Salpeter equation (BSE) in finite field, 47,48 and the quantum em- (118) Vinson, J. Faster exact exchange in periodic systems using single-precision arithmetic.…”
Section: Discussionmentioning
confidence: 99%
“…32 The WEST code has been used to study excited states for a variety of systems, including molecules, nanoparticles, two-dimensional (2D) materials, solids, defects in solid, liquids, amorphous, and solid/liquid interfaces. [32][33][34][35][36][37][38][39][40][41][42][43][44] Recent developments within WEST include the computation of electron-phonon self-energies 45,46 and of absorption spectra, 47,48 and the formulation of a quantum embedding approach. [49][50][51] The GPU porting of WEST aims to further advance the simulation of electronic excitations in large, complex materials on a variety of GPU-powered, pre-exascale and exascale HPC systems.…”
Section: Introductionmentioning
confidence: 99%
“…The main advantage of ML models is that they allow predictions of molecular properties with improved efficiency at a lower computational cost compared to traditional quantum chemistry approaches. Method development in the field of QML is progressing rapidly, and it is increasingly influencing traditional methods. ,− Developments in molecular representations and QML models have paved the way for predicting energetic, electronic, and thermodynamic properties, such as atomization energies, dipole moments, polarizabilities, and harmonic frequencies. …”
Section: Introductionmentioning
confidence: 99%
“…The main advantage of ML models is that they allow predictions of molecular properties with improved efficiency at a lower computational cost compared to traditional quantum chemistry approaches. Method development in the field of QML is progressing rapidly and it is increasingly influencing traditional methods [6,[15][16][17][18]. Developments in molecular representations and QML models have paved the way for predicting energetic, electronic, and thermodynamic properties, such as atomization energies, dipole moments, polarizabilities, and harmonic frequencies [19][20][21].…”
Section: Introductionmentioning
confidence: 99%