Show simple item record

dc.contributor.authorPei, Z
dc.contributor.authorChang, L
dc.contributor.authorXue, P
dc.contributor.authorHarrison, Richard
dc.date.accessioned2022-06-06T23:30:50Z
dc.date.available2022-06-06T23:30:50Z
dc.date.issued2022-06-28
dc.identifier.issn0094-8276
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/337716
dc.description.abstractMorphometry (i.e., the quantitative determination of size and shape information) is an essential component of all rock and environmental magnetic studies. Electron microscopy is often used to image magnetic mineral grains, but the current lack of systematic image processing tools makes it challenging to quantify key morphological features of magnetic minerals in natural samples. Here, we present an easy-to-use machine learning framework MagNet for automated morphological recognition of magnetic mineral grains in microscopic images. This framework, based on convolutional neural network (CNN), performs well in the recognition and classification of magnetofossil nanoparticles in TEM images after training and testing. MagNet is open-source and can easily be extended to process different types of mineral images. This tool has the potential, therefore, to extract key quantitative information of magnetic mineral populations within heterogeneous terrestrial and meteoritic samples for the interpretations of Earth and planetary processes.
dc.description.sponsorshipRoyal Society RS NAF/R1/201096
dc.publisherAmerican Geophysical Union (AGU)
dc.rightsAll Rights Reserved
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.titleMagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network
dc.typeArticle
dc.publisher.departmentDepartment of Earth Sciences
dc.date.updated2022-06-06T06:57:14Z
prism.publicationNameGeophysical Research Letters
dc.identifier.doi10.17863/CAM.85125
dcterms.dateAccepted2022-05-31
rioxxterms.versionofrecord10.1029/2022GL099118
rioxxterms.versionVoR
dc.contributor.orcidPei, Z [0000-0003-4614-0730]
dc.contributor.orcidChang, L [0000-0002-0165-1310]
dc.contributor.orcidHarrison, Richard [0000-0003-3469-762X]
dc.identifier.eissn1944-8007
rioxxterms.typeJournal Article/Review
pubs.funder-project-idRoyal Society (NAF\R1\201096)
cam.issuedOnline2022-06-14
datacite.issupplementedby.doihttps://doi.org/10.5281/zenodo.6448124
cam.orpheus.success2022-07-01
cam.orpheus.counter3
cam.depositDate2022-06-06
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2022-12-06


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record