arXiv：cs.LG· Siddharth Dhanpal, Peter Elliott, Paolo Emilio Trevisanutto, Alin M. Elena, Gilberto Teobaldi·· 5 小时前AI 评分32
机器学习预测分子吸收光谱：基态电子密度与分子几何输入的对比
Electronic Density versus Geometry for Machine-Learned Molecular Absorption Spectra
AI 导读
研究对比了以基态电子密度和分子几何作为机器学习模型输入来预测分子吸收光谱的效果，训练集为从 QM7 数据集中选取的 6874 个分子，密度用 DFT 计算、吸收光谱用 LR-TDDFT 计算。基于密度的卷积神经网络验证相关性达 0.9926，优于最佳几何图模型的 0.9795，残余去相关降低约 64%。
正文
Abstract:Molecular optical absorption spectroscopy provides a direct probe of electronic structure and is widely used for molecular identification, interpretation of photophysical behaviour, and planning of spectroscopy experiments. Calculating the absorption spectra using first-principle excited-state methods, however, is computationally demanding, at least compared to ground-state calculations, which limits their routine application across large molecular sets. Machine-learning (ML) surrogates can reduce this cost and allow rapid spectral prediction. However, their performance depends strongly on how molecular information is represented. Here, we compare using the ground-state electron density versus the molecular geometry as inputs to a ML model for predicting absorption spectra, for a training set of 6874 molecules selected from the QM7 dataset. For each of these molecules, the density was calculated using density functional theory (DFT) and the absorption spectrum was calculated using linear-response (LR) time-dependent DFT (TDDFT). Utilizing the ground-state density as the input to the ML model is motivated by the Hohenberg-Kohn and Runge-Gross theorems, and the fact that the ground-state density encodes information about bonding, charge localisation, and electronic delocalisation. Hence, it may be a more judicious starting point for the ML model compared to the geometry, as it effectively decouples the chemistry of the ground-state. The question we test is whether the benefits of using the density outweigh the (notprohibitive) penalty of requiring an additional single-point DFT calculation for the density. We find that the density-based convolutional neural network achieves a validation correlation of 0.9926, compared with 0.9795 for the best geometry-based graph model, reducing the residual decorrelation, by approximately 64%.
| Subjects: | Chemical Physics (physics.chem-ph); Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03444 [physics.chem-ph] |
| (or arXiv:2610.03444v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03444 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Peter Elliott [view email]
[v1]
Fri, 2 Oct 2026 15:26:08 UTC (1,307 KB)
来源：arXiv：cs.LG · arxiv.org