用量子动态精度构建二元潜在能量矩阵:基于神经网络的d-机器学习方法
Siting Hou1, Zejie Zhang1, Changjian Xie1
1Institute of Modern Physics, Shaanxi Key Laboratory for Theoretical Physics Frontiers, Northwest University, Xi'an 710127, China.
Journal of chemical theory and computation
|February 20, 2026
概括
一种基于神经网络 (NN) 的新型Delta机器学习 (Δ-ML) 方法有效地构建了分子系统的全球糖尿病潜在能量矩阵 (PEM). 这种方法显著降低了计算成本,同时保持了复杂化学反应和光解离过程的高精度.
科学领域:
- 计算化学计算化学
- 量子力学就是量子力学.
- 机器学习在化学中的应用
背景情况:
- 准确的潜在能量矩阵 (PEM) 对于理解分子动力学至关重要.
- 计算高水平的糖尿病PEM是计算上昂贵的.
- 现有的方法在合状态的全球准确性和效率方面扎.
研究的目的:
- 提出一种新的基于神经网络 (NN) 的Delta机器学习 (Δ-ML) 方法.
- 为分子系统构建全球糖尿病潜在能量矩阵 (PEM).
- 为了降低与高级能源计算相关的计算成本.
主要方法:
- 利用了廉价的低水平能量数据与一些高水平能量相结合.
- 开发了两个基于 NN 的 Δ-ML 方案 (A 和 B),用于训练附带电能数据.
- 应用了对非性反应 (Na + H2) 和光解离 (NH3) 的方法.
主要成果:
- 在两个例子系统中实现了有效和准确的全球糖尿病PEM.
- 降低了大约87%的高级计算成本.
- 成功地复制了非相应反应概率,吸收光谱和产品分支比率.
结论:
- 基于 NN 的 Δ-ML 方法为 PEM 构建提供了一个计算效率高,准确的方法.
- 方案B在NH3系统中表现出更高的训练效率,因为它具有更高的自由度.
- 这种方法对推进分子动力学和光谱学研究具有重大前景.
相关概念视频
Multimachine Stability
589
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
589
The Delta-to-Delta Circuit
1.2K
In a delta-delta configuration, the source and the load are connected in a delta manner, forming a closed loop that divides the network into three distinct phases. This configuration makes the phase voltages identical to line voltages. Assuming the sources are in positive sequence, the phase voltages can be expressed directly without having a neutral wire.
1.2K
The Power Flow Problem and Solution
899
Power flow problem analysis is fundamental for determining real and reactive power flows in network components, such as transmission lines, transformers, and loads. The power system's single-line diagram provides data on the bus, transmission line, and transformer. Each bus k in the system is characterized by four key variables: voltage magnitude Vk, phase angle δk, real power Pk, and reactive power Qk. Two of these four variables are inputs, while the power flow program computes...
899
