Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra
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.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra ; volume:6 ; number:9 ; year:2019 ; extent:7
Advanced science ; 6, Heft 9 (2019) (gesamt 7)
- Creator
-
Ghosh, Kunal
Stuke, Annika
Todorović, Milica
Jørgensen, Peter Bjørn
Schmidt, Mikkel N.
Vehtari, Aki
Rinke, Patrick
- DOI
-
10.1002/advs.201801367
- URN
-
urn:nbn:de:101:1-2022072510154611576295
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:23 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Ghosh, Kunal
- Stuke, Annika
- Todorović, Milica
- Jørgensen, Peter Bjørn
- Schmidt, Mikkel N.
- Vehtari, Aki
- Rinke, Patrick
Other Objects (12)
Machine Learning: Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra (Adv. Sci. 9/2019)
Deep convolutional neural network recovers pure absorbance spectra from highly scatter‐distorted spectra of cells
Single-molecule fluorescence excitation spectroscopy
Using Deep Neural Networks to Reconstruct Non-uniformly Sampled NMR Spectra
Computation of Electronic Excitation Spectra of Large Biomolecular Systems
Kink excitation spectra in the (1+1)-dimensional φ 8 model
Deep Neural Network Predicts Ti‐6Al‐4V Dissolution State Using Near‐Field Impedance Spectra
Fast Pure Shift NMR Spectroscopy Using Attention‐Assisted Deep Neural Network
Probing the excitation spectra of ultracold 2D and 3D fermionic superfluids
DEEP-squared: deep learning powered De-scattering with Excitation Patterning
Deep learning assisted XRF spectra classification
Raman spectroscopy of graphene under ultrafast laser excitation
Machine Learning: Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra (Adv. Sci. 9/2019)
Deep convolutional neural network recovers pure absorbance spectra from highly scatter‐distorted spectra of cells
Single-molecule fluorescence excitation spectroscopy
Using Deep Neural Networks to Reconstruct Non-uniformly Sampled NMR Spectra
Computation of Electronic Excitation Spectra of Large Biomolecular Systems
Kink excitation spectra in the (1+1)-dimensional φ 8 model
Deep Neural Network Predicts Ti‐6Al‐4V Dissolution State Using Near‐Field Impedance Spectra
Fast Pure Shift NMR Spectroscopy Using Attention‐Assisted Deep Neural Network
Probing the excitation spectra of ultracold 2D and 3D fermionic superfluids
DEEP-squared: deep learning powered De-scattering with Excitation Patterning
Deep learning assisted XRF spectra classification
Raman spectroscopy of graphene under ultrafast laser excitation
Machine Learning: Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra (Adv. Sci. 9/2019)
Deep convolutional neural network recovers pure absorbance spectra from highly scatter‐distorted spectra of cells
Single-molecule fluorescence excitation spectroscopy
Using Deep Neural Networks to Reconstruct Non-uniformly Sampled NMR Spectra
Computation of Electronic Excitation Spectra of Large Biomolecular Systems
Kink excitation spectra in the (1+1)-dimensional φ 8 model
Deep Neural Network Predicts Ti‐6Al‐4V Dissolution State Using Near‐Field Impedance Spectra
Fast Pure Shift NMR Spectroscopy Using Attention‐Assisted Deep Neural Network
Probing the excitation spectra of ultracold 2D and 3D fermionic superfluids
DEEP-squared: deep learning powered De-scattering with Excitation Patterning
Deep learning assisted XRF spectra classification