FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks

Abstract First‐order reversal curve (FORC) diagrams are a standard rock magnetic tool for analyzing bulk magnetic hysteresis behaviors, which are used to estimate the magnetic mineralogies and magnetic domain states of grains within natural materials. However, the interpretation of FORC distribution...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaowen Pei, Wyn Williams, Lesleis Nagy, Greig A. Paterson, Roberto Moreno, Adrian R. Muxworthy, Liao Chang
Format: Article
Language:English
Published: Wiley 2025-02-01
Series:Geophysical Research Letters
Online Access:https://doi.org/10.1029/2024GL112769
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053576159657984
author Zhaowen Pei
Wyn Williams
Lesleis Nagy
Greig A. Paterson
Roberto Moreno
Adrian R. Muxworthy
Liao Chang
author_facet Zhaowen Pei
Wyn Williams
Lesleis Nagy
Greig A. Paterson
Roberto Moreno
Adrian R. Muxworthy
Liao Chang
author_sort Zhaowen Pei
collection DOAJ
description Abstract First‐order reversal curve (FORC) diagrams are a standard rock magnetic tool for analyzing bulk magnetic hysteresis behaviors, which are used to estimate the magnetic mineralogies and magnetic domain states of grains within natural materials. However, the interpretation of FORC distributions is challenging due to complex domain‐state responses, which introduce well‐documented uncertainties and subjectivity. Here, we propose a neural network algorithm (FORCINN) to invert the size and aspect ratio distribution from measured FORC data. We trained and tested the FORCINN model using a data set of synthetic numerical FORCs for single magnetite grains with various grain‐sizes (45–400 nm) and aspect ratios (oblate and prolate grains). In addition to successfully testing against synthetic data sets, FORCINN was found to provide good estimates of the grain‐size distributions for basalt samples and identify sample size differences in marine sediments.
format Article
id doaj-art-cd58114e68124420bafaaed0ce031f23
institution DOAJ
issn 0094-8276
1944-8007
language English
publishDate 2025-02-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-cd58114e68124420bafaaed0ce031f232025-08-20T02:52:30ZengWileyGeophysical Research Letters0094-82761944-80072025-02-01523n/an/a10.1029/2024GL112769FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural NetworksZhaowen Pei0Wyn Williams1Lesleis Nagy2Greig A. Paterson3Roberto Moreno4Adrian R. Muxworthy5Liao Chang6School of GeoSciences The University of Edinburgh Edinburgh UKSchool of GeoSciences The University of Edinburgh Edinburgh UKDepartment of Earth Ocean and Ecological Sciences The University of Liverpool Liverpool UKDepartment of Earth Ocean and Ecological Sciences The University of Liverpool Liverpool UKSchool of GeoSciences The University of Edinburgh Edinburgh UKDepartment of Earth Science and Engineering Imperial College London London UKLaboratory of Orogenic Belts and Crustal Evolution School of Earth and Space Sciences Peking University Beijing P. R. ChinaAbstract First‐order reversal curve (FORC) diagrams are a standard rock magnetic tool for analyzing bulk magnetic hysteresis behaviors, which are used to estimate the magnetic mineralogies and magnetic domain states of grains within natural materials. However, the interpretation of FORC distributions is challenging due to complex domain‐state responses, which introduce well‐documented uncertainties and subjectivity. Here, we propose a neural network algorithm (FORCINN) to invert the size and aspect ratio distribution from measured FORC data. We trained and tested the FORCINN model using a data set of synthetic numerical FORCs for single magnetite grains with various grain‐sizes (45–400 nm) and aspect ratios (oblate and prolate grains). In addition to successfully testing against synthetic data sets, FORCINN was found to provide good estimates of the grain‐size distributions for basalt samples and identify sample size differences in marine sediments.https://doi.org/10.1029/2024GL112769
spellingShingle Zhaowen Pei
Wyn Williams
Lesleis Nagy
Greig A. Paterson
Roberto Moreno
Adrian R. Muxworthy
Liao Chang
FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
Geophysical Research Letters
title FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
title_full FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
title_fullStr FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
title_full_unstemmed FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
title_short FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks
title_sort forcinn first order reversal curve inversion of magnetite using neural networks
url https://doi.org/10.1029/2024GL112769
work_keys_str_mv AT zhaowenpei forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT wynwilliams forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT lesleisnagy forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT greigapaterson forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT robertomoreno forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT adrianrmuxworthy forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks
AT liaochang forcinnfirstorderreversalcurveinversionofmagnetiteusingneuralnetworks