Replication Data for: The 3-billion fossil question: How to automate classification of microfossils (doi:10.18710/KWP9WA)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

(external link)

Document Description

Citation

Title:

Replication Data for: The 3-billion fossil question: How to automate classification of microfossils

Identification Number:

doi:10.18710/KWP9WA

Distributor:

DataverseNO

Date of Distribution:

2024-03-15

Version:

1

Bibliographic Citation:

Martinsen, Iver; Ricaud, Benjamin; Godtliebsen, Fred; Wade, David, 2024, "Replication Data for: The 3-billion fossil question: How to automate classification of microfossils", https://doi.org/10.18710/KWP9WA, DataverseNO, V1

Study Description

Citation

Title:

Replication Data for: The 3-billion fossil question: How to automate classification of microfossils

Identification Number:

doi:10.18710/KWP9WA

Authoring Entity:

Martinsen, Iver (UiT The Arctic University of Norway)

Ricaud, Benjamin (UiT The Arctic University of Norway)

Godtliebsen, Fred (UiT The Arctic University of Norway)

Wade, David (Equinor ASA)

Other identifications and acknowledgements:

Wade, David

Other identifications and acknowledgements:

Ricaud, Benjamin

Other identifications and acknowledgements:

Godtliebsen, Fred

Producer:

UiT The Arctic University of Norway

Date of Production:

2023-08-22

Software used in Production:

Python

Software used in Production:

VS Code

Grant Number:

309439

Distributor:

DataverseNO

Distributor:

UiT The Arctic University of Norway

Access Authority:

Martinsen, Iver

Depositor:

Martinsen, Iver

Date of Deposit:

2024-02-29

Holdings Information:

https://doi.org/10.18710/KWP9WA

Study Scope

Keywords:

Earth and Environmental Sciences, palynology, palynomorhps, microfossils, unlabeled, png, images, mikkel, wellbore, 6407-6-5, Self-supervised Learning, jurassic, cretaceous, paleogene, neogene

Abstract:

This dataset consists of 100,000 PNG images of individual microfossils extracted from whole slide images of fossils from a single wellbore. The well in question belongs to the Mikkel field on the Norwegian continental shelf. The wellbore is located at 64 degrees north-south, 7 degrees east-west with ID NO 6407-6-5. All images in this dataset are of RGB format with a 224-by-224 pixel resolution. There are no labels associated with these images, thus the number of different species represented in this dataset is unknown and likely to be in the order of 1000. The dataset was created using the method described in the associated paper. The purpose was to create a medium sized dataset of preprocessed microfossil crops for use in self-supervised training of small to medium sized deep learning models, for which this dataset is suffiently big. For large scale training of e.g. Vision Transformers, more data will be required. See the following fact page for more geological information: https://factpages.sodir.no/en/wellbore/PageView/Exploration/With/PalySlides/3921. Note that the original whole slide images from which this dataset is created were provided by the Norwegian national data repository for petroleum data (Diskos) under the Norwegian Licence for Open Government Data (NLOD) 2.0.

Time Period:

1999-11-15-1999-12-27

Date of Collection:

2022-04-01-2023-12-31

Country:

Norway

Geographic Bounding Box:

  • West Bounding Longitude: 7.667742
  • East Bounding Longitude: 7.667742
  • South Bounding Latitude: 64.642997
  • North Bounding Latitude: 64.642997

Kind of Data:

Curated survey data

Kind of Data:

PNG images

Methodology and Processing

Sources Statement

Data Sources:

The image files in this dataset are crops/excerpts from whole slide images. The source data is hosted by https://www.sodir.no/en/diskos/. See https://www.sodir.no/en/facts/geology/geobank/palyslides/palynology-slides-available-in-diskos/ for more information. To gain access to the source data, one can send an email to palyslides@sodir.no and request palyslides from well 6407/6-5 (218 scans, each scan 1GB+ in size). The source data is shared through the Norwegian Licence for Open Government Data (NLOD) 2.0. Fact page about data source: https://factpages.sodir.no/en/wellbore/PageView/Exploration/All/3921

Data Access

Notes:

This data is a modification of public data, and contains data under the Norwegian licence for Open Government Data (NLOD) distributed by the Norwegian Offshore Directorate (NOD). The authors has changed the source data (whole slide images) by creating a dataset that contains cropped out parts of the original images. See https://data.norge.no/nlod/en/2.0 for the full license text.

Other Study Description Materials

Related Publications

Citation

Title:

Martinsen, I., Wade, D., Ricaud, B., & Godtliebsen, F. (2024). The 3-billion fossil question: How to automate classification of microfossils. Artificial Intelligence in Geosciences, 5. https://doi.org/10.1016/j.aiig.2024.100080

Identification Number:

10.1016/j.aiig.2024.100080

Bibliographic Citation:

Martinsen, I., Wade, D., Ricaud, B., & Godtliebsen, F. (2024). The 3-billion fossil question: How to automate classification of microfossils. Artificial Intelligence in Geosciences, 5. https://doi.org/10.1016/j.aiig.2024.100080

Other Study-Related Materials

Label:

00_README.txt

Notes:

text/plain

Other Study-Related Materials

Label:

images.zip

Text:

Folder of images

Notes:

application/zip