MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network
Abstract Morphometry (i.e., the quantitative determination of grain size and shape information) is an essential component of all rock and environmental magnetic studies. Electron microscopy is often used to image magnetic mineral grains, but the current lack of systematic image processing tools make...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | Geophysical Research Letters |
| Online Access: | https://doi.org/10.1029/2022GL099118 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591265730920448 |
|---|---|
| author | Zhaowen Pei Liao Chang Pengfei Xue Richard J. Harrison |
| author_facet | Zhaowen Pei Liao Chang Pengfei Xue Richard J. Harrison |
| author_sort | Zhaowen Pei |
| collection | DOAJ |
| description | Abstract Morphometry (i.e., the quantitative determination of grain size and shape information) is an essential component of all rock and environmental magnetic studies. Electron microscopy is often used to image magnetic mineral grains, but the current lack of systematic image processing tools makes it challenging to quantify key morphological features of magnetic minerals in natural samples. Here, we present an easy‐to‐use machine learning framework MagNet for automated morphological recognition of magnetic mineral grains in microscopic images. This framework, based on a convolutional neural network, performs well in the recognition and classification of magnetofossil nanoparticles in transmission electron microscopy images after training and testing. MagNet is open‐source and can easily be extended to process different types of mineral images. This tool has the potential, therefore, to extract key quantitative information of magnetic mineral populations within heterogeneous terrestrial and meteoritic samples for the interpretations of Earth and planetary processes. |
| format | Article |
| id | doaj-art-d50976d54a094b77b7ba66549cc6bfd2 |
| institution | Kabale University |
| issn | 0094-8276 1944-8007 |
| language | English |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Geophysical Research Letters |
| spelling | doaj-art-d50976d54a094b77b7ba66549cc6bfd22025-01-22T14:38:16ZengWileyGeophysical Research Letters0094-82761944-80072022-06-014912n/an/a10.1029/2022GL099118MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural NetworkZhaowen Pei0Liao Chang1Pengfei Xue2Richard J. Harrison3Laboratory of Orogenic Belts and Crustal Evolution School of Earth and Space Sciences Peking University Beijing P. R. ChinaLaboratory of Orogenic Belts and Crustal Evolution School of Earth and Space Sciences Peking University Beijing P. R. ChinaLaboratory of Orogenic Belts and Crustal Evolution School of Earth and Space Sciences Peking University Beijing P. R. ChinaDepartment of Earth Sciences University of Cambridge Cambridge UKAbstract Morphometry (i.e., the quantitative determination of grain size and shape information) is an essential component of all rock and environmental magnetic studies. Electron microscopy is often used to image magnetic mineral grains, but the current lack of systematic image processing tools makes it challenging to quantify key morphological features of magnetic minerals in natural samples. Here, we present an easy‐to‐use machine learning framework MagNet for automated morphological recognition of magnetic mineral grains in microscopic images. This framework, based on a convolutional neural network, performs well in the recognition and classification of magnetofossil nanoparticles in transmission electron microscopy images after training and testing. MagNet is open‐source and can easily be extended to process different types of mineral images. This tool has the potential, therefore, to extract key quantitative information of magnetic mineral populations within heterogeneous terrestrial and meteoritic samples for the interpretations of Earth and planetary processes.https://doi.org/10.1029/2022GL099118 |
| spellingShingle | Zhaowen Pei Liao Chang Pengfei Xue Richard J. Harrison MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network Geophysical Research Letters |
| title | MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network |
| title_full | MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network |
| title_fullStr | MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network |
| title_full_unstemmed | MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network |
| title_short | MagNet: Automated Magnetic Mineral Grain Morphometry Using Convolutional Neural Network |
| title_sort | magnet automated magnetic mineral grain morphometry using convolutional neural network |
| url | https://doi.org/10.1029/2022GL099118 |
| work_keys_str_mv | AT zhaowenpei magnetautomatedmagneticmineralgrainmorphometryusingconvolutionalneuralnetwork AT liaochang magnetautomatedmagneticmineralgrainmorphometryusingconvolutionalneuralnetwork AT pengfeixue magnetautomatedmagneticmineralgrainmorphometryusingconvolutionalneuralnetwork AT richardjharrison magnetautomatedmagneticmineralgrainmorphometryusingconvolutionalneuralnetwork |