Download
rsos.201275.pdf 2,62MB
WeightNameValue
1000 Titel
  • Use of deep learning for structural analysis of computer tomography images of soil samples
1000 Autor/in
  1. Wieland, Ralf |
  2. Ukawa, Chinatsu |
  3. Joschko, Monika |
  4. Krolczyk, Adrian Josef |
  5. Fritsch, Guido |
  6. Hildebrandt, Thomas Bernd |
  7. Schmidt, Olaf |
  8. Filser, Juliane |
  9. Jiménez, Juan |
1000 Erscheinungsjahr 2021
1000 LeibnizOpen
1000 Publikationstyp
  1. Artikel |
1000 Online veröffentlicht
  • 2021-03-31
1000 Erschienen in
1000 Quellenangabe
  • 8(3):201275
1000 FRL-Sammlung
1000 Copyrightjahr
  • 2021
1000 Lizenz
1000 Verlagsversion
  • https://doi.org/10.1098/rsos.201275 |
1000 Ergänzendes Material
  • https://royalsocietypublishing.org/doi/10.1098/rsos.201275#d1e1244 |
1000 Publikationsstatus
1000 Begutachtungsstatus
1000 Sprache der Publikation
1000 Abstract/Summary
  • Soil samples from several European countries were scanned using medical computer tomography (CT) device and are now available as CT images. The analysis of these samples was carried out using deep learning methods. For this purpose, a VGG16 network was trained with the CT images (X). For the annotation (y) a new method for automated annotation, ‘surrogate’ learning, was introduced. The generated neural networks (NNs) were subjected to a detailed analysis. Among other things, transfer learning was used to check whether the NN can also be trained to other y-values. Visually, the NN was verified using a gradient-based class activation mapping (grad-CAM) algorithm. These analyses showed that the NN was able to generalize, i.e. to capture the spatial structure of the soil sample. Possible applications of the models are discussed.
1000 Sacherschließung
lokal deep learning
lokal transfer learning
lokal computer tomography image analysis
lokal soil structure analysis
lokal porosity
1000 Fächerklassifikation (DDC)
1000 Liste der Beteiligten
  1. https://orcid.org/0000-0002-2278-610X|https://orcid.org/0000-0002-9103-1392|https://orcid.org/0000-0002-4160-1481|https://orcid.org/0000-0002-1815-3908|https://frl.publisso.de/adhoc/uri/RnJpdHNjaCwgR3VpZG8=|https://orcid.org/0000-0001-8685-4733|https://orcid.org/0000-0003-0098-7960|https://orcid.org/0000-0003-1535-6168|https://orcid.org/0000-0003-2398-0796
1000 Label
1000 Fördernummer
  1. -
1000 Förderprogramm
  1. -
1000 Dateien
1000 Objektart article
1000 Beschrieben durch
1000 @id frl:6430255.rdf
1000 Erstellt am 2021-11-16T10:46:22.555+0100
1000 Erstellt von 317
1000 beschreibt frl:6430255
1000 Bearbeitet von 317
1000 Zuletzt bearbeitet 2022-07-01T08:24:41.576+0200
1000 Objekt bearb. Fri Jul 01 08:24:41 CEST 2022
1000 Vgl. frl:6430255
1000 Oai Id
  1. oai:frl.publisso.de:frl:6430255 |
1000 Sichtbarkeit Metadaten public
1000 Sichtbarkeit Daten public
1000 Gegenstand von

View source