Articles | Volume 39, issue 2
https://doi.org/10.5194/jm-39-183-2020
https://doi.org/10.5194/jm-39-183-2020
Research article
 | 
15 Oct 2020
Research article |  | 15 Oct 2020

Automated analysis of foraminifera fossil records by image classification using a convolutional neural network

Ross Marchant, Martin Tetard, Adnya Pratiwi, Michael Adebayo, and Thibault de Garidel-Thoron

Data sets

Endless Forams, MD022508 and MD9712138 training datasets Ross Marchant, Martin Tetard, Adnya Pratiwi, Michael Adebayo, and Thibault de Garidel-Thoron https://doi.org/10.5281/zenodo.3996436

ParticleTrieur and MISO help and tutorials Ross Marchant http://particle-classification.readthedocs.io

Model code and software

Particle Classification Library Ross Marchant https://doi.org/10.5281/zenodo.3996358

Download
Short summary
Foraminifera are marine microorganisms with a calcium carbonate shell. Their fossil remains build up on the seafloor, forming kilometres of sediment over time. From analysis of the foraminiferal record we can estimate past climate conditions and the geological history of the Earth. We have developed an artificial intelligence system for automatically identifying foraminifera species, replacing the time-consuming manual approach and thus helping to make these analyses more efficient and accurate.