Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra

Research output: Contribution to journalArticleScientificpeer-review

Researchers

Research units

  • Danmarks Tekniske Universitet
  • Technische Universität München

Abstract

Deep learning methods for the prediction of molecular excitation spectra are presented. For the example of the electronic density of states of 132k organic molecules, three different neural network architectures: multilayer perceptron (MLP), convolutional neural network (CNN), and deep tensor neural network (DTNN) are trained and assessed. The inputs for the neural networks are the coordinates and charges of the constituent atoms of each molecule. Already, the MLP is able to learn spectra, but the root mean square error (RMSE) is still as high as 0.3 eV. The learning quality improves significantly for the CNN (RMSE = 0.23 eV) and reaches its best performance for the DTNN (RMSE = 0.19 eV). Both CNN and DTNN capture even small nuances in the spectral shape. In a showcase application of this method, the structures of 10k previously unseen organic molecules are scanned and instant spectra predictions are obtained to identify molecules for potential applications.

Details

Original languageEnglish
Article number1801367
Pages (from-to)1-7
Number of pages7
JournalAdvanced Science
Volume6
Issue number9
Publication statusPublished - 3 May 2019
MoE publication typeA1 Journal article-refereed

    Research areas

  • artificial intelligence, DFT calculations, excitation spectra, neural networks, organic molecules

Download statistics

No data available

ID: 31971551