Taher-Ghahramani Farhad, Zheng Fulu, Eisfeld Alexander
Max Planck Institute for the Physics of Complex Systems, Nöthnitzer Str 38, Dresden, Germany.
Bremen Center for Computational Materials Science, University of Bremen, Am Fallturm 1, 28359 Bremen, Germany.
Spectrochim Acta A Mol Biomol Spectrosc. 2022 Jul 5;275:121091. doi: 10.1016/j.saa.2022.121091. Epub 2022 Mar 1.
A common task is the determination of system parameters from spectroscopy, where one compares the experimental spectrum with calculated spectra, that depend on the desired parameters. Here we discuss an approach based on a machine learning technique, where the parameters for the numerical calculations are chosen from Gaussian Process Regression (GPR). This approach does not only quickly converge to an optimal parameter set, but in addition provides information about the complete parameter space, which allows for example to identify extended parameter regions where numerical spectra are consistent with the experimental one. We consider as example dimers of organic molecules and aim at extracting in particular the interaction between the monomers, and their mutual orientation. We find that indeed the GPR gives reliable results which are in agreement with direct calculations of these parameters using quantum chemical methods.
一个常见的任务是从光谱学中确定系统参数，即把实验光谱与依赖于所需参数的计算光谱进行比较。在此，我们讨论一种基于机器学习技术的方法，其中数值计算的参数是从高斯过程回归（GPR）中选取的。这种方法不仅能快速收敛到最优参数集，还能提供关于整个参数空间的信息，例如可以识别出数值光谱与实验光谱一致的扩展参数区域。我们以有机分子二聚体为例，特别旨在提取单体之间的相互作用及其相互取向。我们发现，GPR确实给出了可靠的结果，这些结果与使用量子化学方法对这些参数进行的直接计算结果一致。
