你只需要一个描述符:准确的机器学习非adiabatic合向量
Jakub Martinka1,2, Lina Zhang3, Yi-Fan Hou3
1J. Heyrovský Institute of Physical Chemistry, Academy of Sciences of the Czech Republic, v.v.i., Dolejškova 3, 18223 Prague 8 Prague, Czech Republic.
The journal of physical chemistry letters
|November 3, 2025
概括
机器学习非adiabatic合 (NACs) 加快光化学过程的模拟. 我们的新型NAC特定描述器和ML相位校正在模拟中实现了前所未有的准确性 (R2>0.99).
科学领域:
- 计算化学的计算化学
- 量子化学 是一个量子化学.
- 摄影化学的使用.
背景情况:
- 非adiabatic合 (NACs) 对于建模光化学和光物理过程至关重要.
- 目前的方法,如最少开关的表面跳跃 (FSSH),需要准确的NAC.
- 机器学习 (ML) NAC由于其复杂性质而具有挑战性.
研究的目的:
- 开发准确和高效的机器学习模型,用于非adiabatic合.
- 使用机器学习加速光化学动力学模拟.
- 克服与学习矢量和单数NACs相关的挑战.
主要方法:
- 根据领域专业知识设计新的NAC特定描述符.
- 实施新的机器学习阶段校正程序.
- 适用于完全ML驱动的FSSH模拟的富尔文和甲基酸盐.
主要成果:
- 在学习NAC中实现了前所未有的准确性,R2超过0.99.
- 证明了高效和强大的ML驱动的FSSH模拟.
- 在 fulvene 和成功的三态模拟中精确描述了 S1 衰变.
结论:
- 开发的ML方法显著提高了光化学模拟的准确性和效率.
- 该方法可用于具有多个电子状态的系统.
- 在MLatom中可用的开源实现有助于更广泛的采用.
相关概念视频
Linear Approximation in Time Domain
310
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
310
Vector Algebra: Method of Components
18.6K
It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...
In many applications, the magnitudes and directions of...
18.6K
Linear Approximation in Frequency Domain
328
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
328
Average and Instantaneous Velocity Vectors
8.4K
To calculate other physical quantities in kinematics, the time variable must be introduced. The time variable not only allows us to state where an object is (its position) during its motion, but also how fast it’s moving. The speed at which an object is moving is given by the rate at which the position changes with time. For each position, a particular time is assigned. If the details of the motion at each instant are not important, the rate is usually expressed as the average velocity v.
8.4K
Acceleration Vectors
21.6K
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h...
21.6K
Spin–Spin Coupling: Three-Bond Coupling (Vicinal Coupling)
1.4K
Vicinal or three-bond coupling is commonly observed between protons attached to adjacent carbons. Here, nuclear spin information is primarily transferred via electron spin interactions between adjacent C‑H bond orbitals. This generally favors the antiparallel arrangement of spins, so 3J values are usually positive.
The extent of coupling depends on the C‑C bond length, the two H‑C‑C angles, any electron-withdrawing substituents, and the dihedral angle between the involved orbitals. The...
The extent of coupling depends on the C‑C bond length, the two H‑C‑C angles, any electron-withdrawing substituents, and the dihedral angle between the involved orbitals. The...
1.4K


