期刊
COMMUNICATIONS PHYSICS
卷 4, 期 1, 页码 -出版社
NATURE RESEARCH
DOI: 10.1038/s42005-021-00609-0
关键词
-
资金
- MEXT Quantum Leap Flagship Program (MEXT Q-LEAP) [JPMXS0118067394, JPMXS0120319794]
- Japan Science and Technology Agency (JST) (Q-LEAP program)
- Japan Society for the Promotion of Science (JSPS) KAKENHI [18K14181]
- JST PRESTO [JPMJPR191A]
- Army Research Office (ARO) [W911NF-18-1-0358]
- Japan Science and Technology Agency (JST) (CREST) [JPMJCR1676]
- Japan Society for the Promotion of Science (JSPS) (KAKENHI) [JP20H00134]
- Japan Society for the Promotion of Science (JSPS) (JSPS-RFBR) [JPJSBP120194828]
- Asian Office of Aerospace Research and Development (AOARD) [FA2386-20-1-4069]
- Foundational Questions Institute Fund (FQXi) [FQXi-IAF19-06]
- NTT Research
- Grants-in-Aid for Scientific Research [18K14181] Funding Source: KAKEN
This study demonstrates the potential of artificial neural networks in predicting properties of solid systems, accurately simulating ground-state energies and quasiparticle band spectra, providing a new computational method for elucidating complex many-body phenomena in solid-state systems.
Establishing a predictive ab initio method for solid systems is one of the fundamental goals in condensed matter physics and computational materials science. The central challenge is how to encode a highly-complex quantum-many-body wave function compactly. Here, we demonstrate that artificial neural networks, known for their overwhelming expressibility in the context of machine learning, are excellent tool for first-principles calculations of extended periodic materials. We show that the ground-state energies in real solids in one-, two-, and three-dimensional systems are simulated precisely, reaching their chemical accuracy. The highlight of our work is that the quasiparticle band spectra, which are both essential and peculiar to solid-state systems, can be efficiently extracted with a computational technique designed to exploit the low-lying energy structure from neural networks. This work opens up a path to elucidate the intriguing and complex many-body phenomena in solid-state systems. Designing computational methods that can accurately predict useful material properties is an attractive alternative to cumbersome trial and error experimental approaches. Here, the authors present a computational method based on neural-network quantum states, which can reveal many-body quantum phenomena of a solid state system similar to first-principles calculations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据