Predicting single-molecule conductance through machine learning
Abstract
We present a robust machine learning model that is trained on the experimentally determined electrical conductance values of approximately 120 single-molecule junctions used in scanning tunnelling microscope molecular break junction (STM-MBJ) experiments. Quantum mechanical, chemical, and topological descriptors are used to correlate each molecular structure with a conductance value, and the resulting machine-learning model can predict the corresponding value of conductance with correlation coefficients of r2=0.95 for the training set and r2=0.78 for a blind testing set. While neglecting entirely the effects of the metal contacts, this work demonstrates that single molecule conductance can be qualitatively correlated with a number of molecular descriptors through a suitably trained machine learning model. The dominant features in the machine learning model include those based on the electronic wavefunction, the geometry/topology of the molecule as well as the surface chemistry of the molecule. This model can be used to identify promising molecular structures for use in single-molecule electronic circuits and can guide synthesis and experiments in the future.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Oct 06, 2016
- Source ID
- 10.1063/1.4964414
Entities
People
- Curt M. Breneman
- Nicholas A. Lanzillo
Organizations
- Office of Naval Research
- Rensselaer Polytechnic Institute