Fossil charcoal particle training data for neural networks

Photographs taken using a DSLR and lens adapter through a stereomicroscope of fossil charcoal particles (>63 micron diameter) isolated from Holocene lake sediments. These images have been processed ready to use as a training dataset for neural networks, with binary masks (charcoal versus not charcoal).

    Data Record Details
    Data record related to this publication Fossil charcoal particle training data for neural networks
    Data Publication title Fossil charcoal particle training data for neural networks
  • Description

    Photographs taken using a DSLR and lens adapter through a stereomicroscope of fossil charcoal particles (>63 micron diameter) isolated from Holocene lake sediments. These images have been processed ready to use as a training dataset for neural networks, with binary masks (charcoal versus not charcoal).

  • Other Descriptors
    • Descriptor

      A zip file containing the photographs (28.6 GB) is available from the link below.

    • Descriptor type Note
  • Data type dataset
  • Keywords
    • fossil charcoal
    • palaeoenvironment
    • neural networks
    • anthracology
    • palaeolimnology
  • Funding source
  • Research grant(s)/Scheme name(s)
    • 23372 - (James Cook University Research Activities) Fire and Environmental Change in Northern Australia during the Late Holocene
    • 12143 - Australian Institute of Nuclear Science and Engineering Postgraduate Research Award
  • Research themes
    Tropical Ecosystems, Conservation and Climate Change
    FoR Codes (*)
    SEO Codes
    Specify spatial or temporal setting of the data
    Temporal (time) coverage
  • Start Date
  • End Date
  • Time Period Holocene
    Spatial (location) coverage
  • Locations
    • Arnhem Land, Northern Territory, Australia
    • Cape York Peninsula, Queensland, Australia
  • Related publications
      Name Rehn, E., Rehn, A. and Possermiers, A. (2019) Fossil charcoal particle identification and classification by two convolutional neural networks, Quaternary Science Reviews, 226: 106038.
    • URL https://doi.org/10.1016/j.quascirev.2019.106038
    • Notes
  • Related websites
      Name
    • URL
    • Notes
  • Related metadata (including standards, codebooks, vocabularies, thesauri, ontologies)
      Name
    • URL
    • Notes
  • Related data
      Name
    • URL
    • Notes
  • Related services
      Name
    • URL
    • Notes
    Citation Rehn, Emma; Rehn, Adam (2019): Fossil charcoal particle training data for neural networks. James Cook University. https://doi.org/10.25903/5d006c1494cf9