Deep learning-assisted focused ion beam nanofabrication
Deep learning-assisted focused ion beam nanofabrication
Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.
deep learning, focused ion beam milling, nanofabrication
2734-2739
Buchnev, Oleksandr
60cdb0d2-3388-47be-a066-61b3b396f69d
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Eason, R.W.
e38684c3-d18c-41b9-a4aa-def67283b020
Zheludev, Nikolai
32fb6af7-97e4-4d11-bca6-805745e40cc6
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
MacDonald, Kevin F.
76c84116-aad1-4973-b917-7ca63935dba5
13 April 2022
Buchnev, Oleksandr
60cdb0d2-3388-47be-a066-61b3b396f69d
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Eason, R.W.
e38684c3-d18c-41b9-a4aa-def67283b020
Zheludev, Nikolai
32fb6af7-97e4-4d11-bca6-805745e40cc6
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
MacDonald, Kevin F.
76c84116-aad1-4973-b917-7ca63935dba5
Buchnev, Oleksandr, Grant-Jacob, James, Eason, R.W., Zheludev, Nikolai, Mills, Benjamin and MacDonald, Kevin F.
(2022)
Deep learning-assisted focused ion beam nanofabrication.
Nano Letters, 22 (7), .
(doi:10.1021/acs.nanolett.1c04604).
Abstract
Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.
Text
accepted manuscript
- Accepted Manuscript
More information
Accepted/In Press date: 23 February 2022
Published date: 13 April 2022
Additional Information:
This work was supported by the Engineering and Physical Sciences Research Council, UK [grant numbers EP/N03368 X/1, EP/T026197/1, EP/M009122/1, EP/T02643 X/1, and EP/N00762 X/1], and the Singapore Ministry of Education [MOE2016-T3-1-006]. We acknowledge the NVIDIA Academic Hardware Grant Program for donation of the Nvidia Titan Xp GPU.
Keywords:
deep learning, focused ion beam milling, nanofabrication
Identifiers
Local EPrints ID: 455923
URI: http://eprints.soton.ac.uk/id/eprint/455923
ISSN: 1530-6984
PURE UUID: d5991b99-019f-4cf7-9394-7fc18cb3cfac
Catalogue record
Date deposited: 08 Apr 2022 16:34
Last modified: 06 Jun 2024 04:09
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
