---
_id: '17910'
abstract:
- lang: eng
  text: The scanning tunneling microscope-based break junction (STM-BJ) is used widely
    to create and characterize single metal-molecule-metal junctions. In this technique,
    conductance is continuously recorded as a metal point contact is broken in a solution
    of molecules. Conductance plateaus are seen when stable molecular junctions are
    formed. Typically, thousands of junctions are created and measured, yielding thousands
    of distinct conductance versus extension traces. However, such traces are rarely
    analyzed individually to recognize the types of junctions formed. Here, we present
    a deep learning-based method to identify molecular junctions and show that it
    performs better than several commonly used and recently reported techniques. We
    demonstrate molecular junction identification from mixed solution measurements
    with accuracies as high as 97%. We also apply this model to an in situ electric
    field-driven isomerization reaction of a [3]cumulene to follow the reaction over
    time. Furthermore, we demonstrate that our model can remain accurate even when
    a key parameter, the average junction conductance, is eliminated from the analysis,
    showing that our model goes beyond conventional analysis in existing methods.
article_processing_charge: No
article_type: letter_note
author:
- first_name: Tianren
  full_name: Fu, Tianren
  last_name: Fu
- first_name: Yaping
  full_name: Zang, Yaping
  last_name: Zang
- first_name: Qi
  full_name: Zou, Qi
  last_name: Zou
- first_name: Colin
  full_name: Nuckolls, Colin
  last_name: Nuckolls
- first_name: Latha
  full_name: Venkataraman, Latha
  id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
  last_name: Venkataraman
  orcid: 0000-0002-6957-6089
citation:
  ama: Fu T, Zang Y, Zou Q, Nuckolls C, Venkataraman L. Using deep learning to identify
    molecular junction characteristics. <i>Nano Letters</i>. 2020;20(5):3320-3325.
    doi:<a href="https://doi.org/10.1021/acs.nanolett.0c00198">10.1021/acs.nanolett.0c00198</a>
  apa: Fu, T., Zang, Y., Zou, Q., Nuckolls, C., &#38; Venkataraman, L. (2020). Using
    deep learning to identify molecular junction characteristics. <i>Nano Letters</i>.
    American Chemical Society. <a href="https://doi.org/10.1021/acs.nanolett.0c00198">https://doi.org/10.1021/acs.nanolett.0c00198</a>
  chicago: Fu, Tianren, Yaping Zang, Qi Zou, Colin Nuckolls, and Latha Venkataraman.
    “Using Deep Learning to Identify Molecular Junction Characteristics.” <i>Nano
    Letters</i>. American Chemical Society, 2020. <a href="https://doi.org/10.1021/acs.nanolett.0c00198">https://doi.org/10.1021/acs.nanolett.0c00198</a>.
  ieee: T. Fu, Y. Zang, Q. Zou, C. Nuckolls, and L. Venkataraman, “Using deep learning
    to identify molecular junction characteristics,” <i>Nano Letters</i>, vol. 20,
    no. 5. American Chemical Society, pp. 3320–3325, 2020.
  ista: Fu T, Zang Y, Zou Q, Nuckolls C, Venkataraman L. 2020. Using deep learning
    to identify molecular junction characteristics. Nano Letters. 20(5), 3320–3325.
  mla: Fu, Tianren, et al. “Using Deep Learning to Identify Molecular Junction Characteristics.”
    <i>Nano Letters</i>, vol. 20, no. 5, American Chemical Society, 2020, pp. 3320–25,
    doi:<a href="https://doi.org/10.1021/acs.nanolett.0c00198">10.1021/acs.nanolett.0c00198</a>.
  short: T. Fu, Y. Zang, Q. Zou, C. Nuckolls, L. Venkataraman, Nano Letters 20 (2020)
    3320–3325.
date_created: 2024-09-09T07:20:52Z
date_published: 2020-04-03T00:00:00Z
date_updated: 2024-12-10T12:08:53Z
day: '03'
doi: 10.1021/acs.nanolett.0c00198
extern: '1'
external_id:
  pmid:
  - '32242671'
intvolume: '        20'
issue: '5'
language:
- iso: eng
month: '04'
oa_version: None
page: 3320-3325
pmid: 1
publication: Nano Letters
publication_identifier:
  eissn:
  - 1530-6992
  issn:
  - 1530-6984
publication_status: published
publisher: American Chemical Society
quality_controlled: '1'
scopus_import: '1'
status: public
title: Using deep learning to identify molecular junction characteristics
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 20
year: '2020'
...