Using an Autoencoder for Dimensionality Reduction in Quantum Dynamics

Reiter, Sebastian; Schnappinger, Thomas und de Vivie-Riedle, Regina (2019): Using an Autoencoder for Dimensionality Reduction in Quantum Dynamics. In: Artificial Neural Networks and Machine Learning - Icann 2019: Workshop and Special Sessions, Vol. 11731: pp. 783-787

Abstract

A key step in performing quantum dynamics for a chemical system is the reduction of dimensionality to allow a numerical treatment. Here, we introduce a machine learning approach for the (semi)automatic construction of reactive coordinates. After generating a meaningful data set from trajectory calculations, we train an autoencoder to find a low-dimensional set of non-linear coordinates for use in molecular quantum dynamics. We compare the wave packet dynamics of proton transfer reactions in both linear and non-linear coordinate spaces and find significant improvement for physical properties like reaction timescales.

• Item Type: Journal article
• Faculties: Chemistry and Pharmacy > Department of Chemistry
• Subjects: 500 Science > 540 Chemistry
• ISSN: 0302-9743
• Language: English