Technical note: colab_zirc_dims: a Google Colab-compatible toolset for automated and semi-automated measurement of mineral grains in laser ablation–inductively coupled plasma–mass spectrometry images using deep learning models
<p>Collecting grain measurements for large detrital zircon age datasets is a time-consuming task, but a growing number of studies suggest such data are essential to understanding the complex roles of grain size and morphology in grain transport and as indicators for grain provenance. We develo...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2023-03-01
|
Series: | Geochronology |
Online Access: | https://gchron.copernicus.org/articles/5/109/2023/gchron-5-109-2023.pdf |
Summary: | <p>Collecting grain measurements for large detrital zircon age datasets is a
time-consuming task, but a growing number of studies suggest such data are
essential to understanding the complex roles of grain size and morphology in
grain transport and as indicators for grain provenance. We developed the
colab_zirc_dims Python package to automate
deep-learning-based segmentation and measurement of mineral grains from
scaled images captured during laser ablation at facilities that use Chromium
targeting software. The colab_zirc_dims
package is implemented in a collection of highly interactive Jupyter
notebooks that can be run either on a local computer or installation-free
via Google Colab. These notebooks also provide additional functionalities
for dataset preparation and for semi-automated grain segmentation and
measurement using a simple graphical user interface. Our automated grain
measurement algorithm approaches human measurement accuracy when applied to
a manually measured <span class="inline-formula"><i>n</i>=5004</span> detrital zircon dataset. Errors and
uncertainty related to variable grain exposure necessitate semi-automated
measurement for production of publication-quality measurements, but we
estimate that our semi-automated grain segmentation workflow will enable
users to collect grain measurement datasets for large (<span class="inline-formula"><i>n</i>≥5000</span>)
applicable image datasets in under a day of work. We hope that the
colab_zirc_dims toolset allows more
researchers to augment their detrital geochronology datasets with grain
measurements.</p> |
---|---|
ISSN: | 2628-3697 2628-3719 |