3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks
High-precision vector magnetic field detection has been widely used in the fields of celestial magnetic field detection, aeromagnetic detection, marine magnetic field detection and geomagnetic navigation. Due to the large amount of data, the 3D inversion of high-precision magnetic gradient vector da...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Minerals |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-163X/12/5/566 |
_version_ | 1797497587962478592 |
---|---|
author | Hua Deng Xiangyun Hu Hongzhu Cai Shuang Liu Ronghua Peng Yajun Liu Bo Han |
author_facet | Hua Deng Xiangyun Hu Hongzhu Cai Shuang Liu Ronghua Peng Yajun Liu Bo Han |
author_sort | Hua Deng |
collection | DOAJ |
description | High-precision vector magnetic field detection has been widely used in the fields of celestial magnetic field detection, aeromagnetic detection, marine magnetic field detection and geomagnetic navigation. Due to the large amount of data, the 3D inversion of high-precision magnetic gradient vector data often involves a large number of computational requirements and is very time-consuming. In this paper, a 3D magnetic gradient tensor (MGT) inversion method is developed, based on using a convolutional neural network (CNN) to automatically predict physical parameters from the 2D images of MGT. The information of geometry, depth and parameters such as magnetic inclination (I), magnetic declination (D) and magnetization susceptibility of magnetic anomalies is extracted, and a 3D model is obtained by comprehensive analysis. The method first obtains sufficient MGT data samples by forward modeling of different magnetic anomalies. Then, we use an improved CNN with shear layers to achieve the prediction of each magnetic parameter. The reliability of the algorithm is verified by numerical simulations of synthetic models of multiple magnetic anomalies. MGT data of the Tallawang magnetite diorite deposit in Australia are also predicted by using this method to obtain a slab model that matches the known geological information. The effects of sample size and noise level on the prediction accuracy are discussed. Compared with single-component prediction, the results of multi-component joint prediction are more reliable. From the numerical model study and the field data validation, we demonstrate the capability of using CNNs for inversing MGT data. |
first_indexed | 2024-03-10T03:21:22Z |
format | Article |
id | doaj.art-a7ee7a3c71e3483a8d6a90aa2bcd8e55 |
institution | Directory Open Access Journal |
issn | 2075-163X |
language | English |
last_indexed | 2024-03-10T03:21:22Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Minerals |
spelling | doaj.art-a7ee7a3c71e3483a8d6a90aa2bcd8e552023-11-23T12:18:38ZengMDPI AGMinerals2075-163X2022-04-0112556610.3390/min120505663D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural NetworksHua Deng0Xiangyun Hu1Hongzhu Cai2Shuang Liu3Ronghua Peng4Yajun Liu5Bo Han6Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaBadong National Observation and Research Station of Geohazards, China University of Geosciences, Wuhan 430074, ChinaInstitute of Geological Survey, China University of Geosciences, Wuhan 430074, ChinaHigh-precision vector magnetic field detection has been widely used in the fields of celestial magnetic field detection, aeromagnetic detection, marine magnetic field detection and geomagnetic navigation. Due to the large amount of data, the 3D inversion of high-precision magnetic gradient vector data often involves a large number of computational requirements and is very time-consuming. In this paper, a 3D magnetic gradient tensor (MGT) inversion method is developed, based on using a convolutional neural network (CNN) to automatically predict physical parameters from the 2D images of MGT. The information of geometry, depth and parameters such as magnetic inclination (I), magnetic declination (D) and magnetization susceptibility of magnetic anomalies is extracted, and a 3D model is obtained by comprehensive analysis. The method first obtains sufficient MGT data samples by forward modeling of different magnetic anomalies. Then, we use an improved CNN with shear layers to achieve the prediction of each magnetic parameter. The reliability of the algorithm is verified by numerical simulations of synthetic models of multiple magnetic anomalies. MGT data of the Tallawang magnetite diorite deposit in Australia are also predicted by using this method to obtain a slab model that matches the known geological information. The effects of sample size and noise level on the prediction accuracy are discussed. Compared with single-component prediction, the results of multi-component joint prediction are more reliable. From the numerical model study and the field data validation, we demonstrate the capability of using CNNs for inversing MGT data.https://www.mdpi.com/2075-163X/12/5/566vector magnetic field detectionmagnetic gradient tensor inversionCNNphysical parameter extraction |
spellingShingle | Hua Deng Xiangyun Hu Hongzhu Cai Shuang Liu Ronghua Peng Yajun Liu Bo Han 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks Minerals vector magnetic field detection magnetic gradient tensor inversion CNN physical parameter extraction |
title | 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks |
title_full | 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks |
title_fullStr | 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks |
title_full_unstemmed | 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks |
title_short | 3D Inversion of Magnetic Gradient Tensor Data Based on Convolutional Neural Networks |
title_sort | 3d inversion of magnetic gradient tensor data based on convolutional neural networks |
topic | vector magnetic field detection magnetic gradient tensor inversion CNN physical parameter extraction |
url | https://www.mdpi.com/2075-163X/12/5/566 |
work_keys_str_mv | AT huadeng 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT xiangyunhu 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT hongzhucai 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT shuangliu 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT ronghuapeng 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT yajunliu 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks AT bohan 3dinversionofmagneticgradienttensordatabasedonconvolutionalneuralnetworks |