Published April 18, 2024 | Version v1
Journal article Open

DeepDive: Estimating global biodiversity patterns through time using deep learning

Authors/Creators

  • 1. ROR icon University of Fribourg
  • 2. ROR icon SIB Swiss Institute of Bioinformatics
  • 3. ROR icon University of Gothenburg
  • 4. ROR icon University of Birmingham

Description

Software, data and code to run analyses presented in the paper 'DeepDive: Estimating global biodiversity patterns through time using deep learning', Nature Communications (2024). 

The deepdive.zip folder contains the software, while example_files.zip contains the materials for the analyses of proboscideans in the Cenozoic and for the Permian-Triassic marine animals. The folder simulation_tests.zip contains the scripts used to simulate data, then train and asses models built using the DeepDive software under different bias conditions as presented in the paper.

Files

deepdive.zip

Files (234.9 MB)

Name Size Download all
md5:ddbe1a2a34dc1103d24de3b0f1ecc90d
62.7 kB Preview Download
md5:056409d7bb33e4811a00b37ce45d30ef
69.6 MB Preview Download
md5:827b370290193910b55f0021d93bcdee
165.2 MB Preview Download

Additional details

Software

Repository URL
https://github.com/DeepDive-project
Programming language
Python , R