高精度机器学习原子间潜力的数据效率多忠实训练
Jaesun Kim1, Jisu Kim1, Jaehoon Kim1
1Department of Materials Science and Engineering, Seoul National University, Seoul 08826, Korea.
Journal of the American Chemical Society
|December 17, 2024
概括
这项研究引入了一种机器学习的原子间潜能 (MLIP) 框架,该框架使用多真实数据库高效地学习精确的潜在能量表面. 该方法显著减少了对昂贵的高准确度数据的需求,提高了MLIP的准确性和适用性.
科学领域:
- 计算材料科学
- 化学中的机器学习
- 量子力学
背景情况:
- 机器学习的原子间潜能 (MLIP) 从初始计算中估计潜在能量表面 (PES),以较低的计算成本提供近量子精度.
- 高准确度的数据库对于MLIP准确性至关重要,但其创建成本昂贵,使其仅适用于需要高化学准确度的系统.
研究的目的:
- 开发一个MLIP框架,能够同时培训多真实数据库.
- 通过利用低保真度数据,使用最小的高保真度数据来实现高保真度 PES 的准确学习.
主要方法:
- 在MLIP框架中使用等价图神经网络.
- 采用多忠度训练方法,使用通用梯度近似 (GGA) 作为低忠度数据,并使用元GGA作为高忠度数据.
- 在Li6PS5Cl和InGa1-N系统上测试了框架.
主要成果:
- 与低准确度数据相比,高准确度数据仅为10%.
- 在离子导电性预测 (10%的误差) 和InGa1-N混合能量 (R2的0.98) 中表现出高精度.
- 显示低准确度GGA数据有效地推断了未覆盖的高准确度空间的信息,提高了准确度和分子动态稳定性.
结论:
- 多真实性学习框架显著提高了高精度任务的MLIP性能,超过了转移学习和Δ学习.
- 该方法具有多功能,适用于各种系统,并可扩展到更高的保真度,包括合集群.
- 这种方法有望通过有效扩展高准确度数据集来开发高度准确,定制或通用的MLIP.
更多相关视频
10:52Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics
Published on: April 12, 2019
12.7K
06:37Analyzing Melts and Fluids from Ab Initio Molecular Dynamics Simulations with the UMD Package
Published on: September 17, 2021
4.4K
相关概念视频
Improving Translational Accuracy
8.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
8.8K
Hybridization of Atomic Orbitals II
31.8K
sp3d and sp3d 2 Hybridization
31.8K
Hybridization of Atomic Orbitals I
46.5K
The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...
46.5K
Predicting Molecular Geometry
34.1K
VSEPR Theory for Determination of Electron Pair Geometries
34.1K
Fermi Level Dynamics
221
The vacuum level denotes the energy threshold required for an electron to escape from a material surface. It is usually positioned above the conduction band of a semiconductor and acts as a benchmark for comparing electron energies within various materials.
Electron affinity in semiconductors refers to the energy gap between the minimum of its conduction band and the vacuum level and it is a critical parameter in determining how easily a semiconductor can accept additional electrons.
The work...
Electron affinity in semiconductors refers to the energy gap between the minimum of its conduction band and the vacuum level and it is a critical parameter in determining how easily a semiconductor can accept additional electrons.
The work...
221
Multicompartment Models: Overview
93
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
93
