Deep potentials for materials science
To fill the gap between accurate (and expensive) ab initio calculations and efficient atomistic
simulations based on empirical interatomic potentials, a new class of descriptions of atomic …
simulations based on empirical interatomic potentials, a new class of descriptions of atomic …
Weinan E, David J Srolovitz. Deep potentials for materials science
To fill the gap between accurate (and expensive) ab initio calculations and efficient atomistic
simulations based on empirical interatomic potentials, a new class of descriptions of atomic …
simulations based on empirical interatomic potentials, a new class of descriptions of atomic …
Resolution-of-identity approach to Hartree–Fock, hybrid density functionals, RPA, MP2 and GW with numeric atom-centered orbital basis functions
The efficient implementation of electronic structure methods is essential for first principles
modeling of molecules and solids. We present here a particularly efficient common …
modeling of molecules and solids. We present here a particularly efficient common …
Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with ab initio accuracy
Simulating electronic behavior in materials and devices with realistic large system sizes
remains a formidable task within the ab initio framework due to its computational intensity …
remains a formidable task within the ab initio framework due to its computational intensity …
Methods in electronic structure calculations
Linear-scaling methods, or methods, have computational and memory requirements which
scale linearly with the number of atoms in the system, N, in contrast to standard approaches …
scale linearly with the number of atoms in the system, N, in contrast to standard approaches …
DPA-2: a large atomic model as a multi-task learner
D Zhang, X Liu, X Zhang, C Zhang, C Cai… - npj Computational …, 2024 - nature.com
The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes
in atomic modeling, simulation, and design. AI-driven potential energy models have …
in atomic modeling, simulation, and design. AI-driven potential energy models have …
A deep equivariant neural network approach for efficient hybrid density functional calculations
Hybrid density functional calculations are essential for accurate description of electronic
structure, yet their widespread use is restricted by the substantial computational cost. Here …
structure, yet their widespread use is restricted by the substantial computational cost. Here …
Investigating interfacial segregation of Ω/Al in Al–Cu alloys: A comprehensive study using density functional theory and machine learning
Solute segregation at the interface between the aluminum (Al) matrix and the Ω (Al 2 Cu)
phase decreases the interfacial energy, impedes the coarsening of precipitates, and …
phase decreases the interfacial energy, impedes the coarsening of precipitates, and …
Universal interatomic potential for perovskite oxides
With their celebrated structural and chemical flexibility, perovskite oxides have served as a
highly adaptable material platform for exploring emergent phenomena arising from the …
highly adaptable material platform for exploring emergent phenomena arising from the …
Accelerating the calculation of electron–phonon coupling strength with machine learning
The calculation of electron–phonon couplings (EPCs) is essential for understanding various
fundamental physical properties, including electrical transport, optical and superconducting …
fundamental physical properties, including electrical transport, optical and superconducting …