Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images

In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified regarding fidelity, quality, and a survey tak...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel Gelman, Irit Rosenhek-Goldian, Nir Kampf, Marek Patočka, Maricarmen Rios, Marcos Penedo, Georg Fantner, Amir Beker, Sidney R. Cohen, Ido Azuri
Format: Article
Language:English
Published: Beilstein-Institut 2025-07-01
Series:Beilstein Journal of Nanotechnology
Subjects:
Online Access:https://doi.org/10.3762/bjnano.16.83
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717645822132224
author Samuel Gelman
Irit Rosenhek-Goldian
Nir Kampf
Marek Patočka
Maricarmen Rios
Marcos Penedo
Georg Fantner
Amir Beker
Sidney R. Cohen
Ido Azuri
author_facet Samuel Gelman
Irit Rosenhek-Goldian
Nir Kampf
Marek Patočka
Maricarmen Rios
Marcos Penedo
Georg Fantner
Amir Beker
Sidney R. Cohen
Ido Azuri
author_sort Samuel Gelman
collection DOAJ
description In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified regarding fidelity, quality, and a survey taken by AFM experts. The deep learning models outperform the traditional methods and yield better results. Additionally, some common AFM artifacts, such as streaking, are present in the ground truth high-resolution images. These artifacts are partially attenuated by the traditional methods but are completely eliminated by the deep learning models. This work shows deep learning models to be superior for super-resolution tasks and enables significant reduction in AFM measurement time, whereby low-pixel-resolution AFM images are enhanced in both resolution and fidelity through deep learning.
format Article
id doaj-art-bc7a212a7ac7483cafc3ae87368d09ea
institution DOAJ
issn 2190-4286
language English
publishDate 2025-07-01
publisher Beilstein-Institut
record_format Article
series Beilstein Journal of Nanotechnology
spelling doaj-art-bc7a212a7ac7483cafc3ae87368d09ea2025-08-20T03:12:35ZengBeilstein-InstitutBeilstein Journal of Nanotechnology2190-42862025-07-011611129114010.3762/bjnano.16.832190-4286-16-83Deep learning for enhancement of low-resolution and noisy scanning probe microscopy imagesSamuel Gelman0Irit Rosenhek-Goldian1Nir Kampf2Marek Patočka3Maricarmen Rios4Marcos Penedo5Georg Fantner6Amir Beker7Sidney R. Cohen8Ido Azuri9Department of Life Sciences Core Facilities, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Chemical Research Support, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Chemical Research Support, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Chemical Research Support, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Chemical Research Support, Weizmann Institute of Science, Rehovot, 7610001, Israel École Polytechnique Fédérale de Lausanne, Laboratory for Bio- and Nano-Instrumentation, CH1015 Lausanne, Switzerland École Polytechnique Fédérale de Lausanne, Laboratory for Bio- and Nano-Instrumentation, CH1015 Lausanne, Switzerland Bina, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Chemical Research Support, Weizmann Institute of Science, Rehovot, 7610001, Israel Department of Life Sciences Core Facilities, Weizmann Institute of Science, Rehovot, 7610001, Israel In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified regarding fidelity, quality, and a survey taken by AFM experts. The deep learning models outperform the traditional methods and yield better results. Additionally, some common AFM artifacts, such as streaking, are present in the ground truth high-resolution images. These artifacts are partially attenuated by the traditional methods but are completely eliminated by the deep learning models. This work shows deep learning models to be superior for super-resolution tasks and enables significant reduction in AFM measurement time, whereby low-pixel-resolution AFM images are enhanced in both resolution and fidelity through deep learning.https://doi.org/10.3762/bjnano.16.83atomic force microscopydeep learningfast scanninglow resolutionsuper resolution
spellingShingle Samuel Gelman
Irit Rosenhek-Goldian
Nir Kampf
Marek Patočka
Maricarmen Rios
Marcos Penedo
Georg Fantner
Amir Beker
Sidney R. Cohen
Ido Azuri
Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
Beilstein Journal of Nanotechnology
atomic force microscopy
deep learning
fast scanning
low resolution
super resolution
title Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
title_full Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
title_fullStr Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
title_full_unstemmed Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
title_short Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images
title_sort deep learning for enhancement of low resolution and noisy scanning probe microscopy images
topic atomic force microscopy
deep learning
fast scanning
low resolution
super resolution
url https://doi.org/10.3762/bjnano.16.83
work_keys_str_mv AT samuelgelman deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT iritrosenhekgoldian deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT nirkampf deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT marekpatocka deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT maricarmenrios deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT marcospenedo deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT georgfantner deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT amirbeker deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT sidneyrcohen deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages
AT idoazuri deeplearningforenhancementoflowresolutionandnoisyscanningprobemicroscopyimages