This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Three-Dimension Inversion of Magnetic Data Based on Multi-Constraint UNet++
by
Jian Jiao
Jian Jiao
Dr. Jian Jiao received a Ph.D. degree in measurement technology and instruments from Jilin China, [...]
Dr. Jian Jiao received a Ph.D. degree in measurement technology and instruments from Jilin University, Changchun, China, in 2004. He is currently an Associate Professor with Jilin University, engaged in mobile platform detection techniques. Dr. Jian Jiao is engaged in the processing and interpretation of gravity and magnetic data. His research interests include the development and data processing technology of aeromagnetic systems based on the UAV platform, interpretation technology of shipload magnetic data, and multi-parameter constrained inversion technology of potential field data.
1,
Xiangcheng Zeng
Xiangcheng Zeng
Xiangcheng Zeng received a bachelor's degree in exploration technology and engineering (applied the [...]
Xiangcheng Zeng received a bachelor's degree in exploration technology and engineering (applied geophysics) from the Institute of Disaster Prevention, China, in 2022. He is currently a master's candidate at Jilin University, engaged in the processing and interpretation of gravity and magnetic data. His research interests include gravity and magnetic data inverse problems and deep learning.
1
,
Hui Liu
Hui Liu 2,3,
Ping Yu
Ping Yu
Prof. Dr. Ping Yu currently holds the office of Associate Dean of the Graduate School, Associate of [...]
Prof. Dr. Ping Yu currently holds the office of Associate Dean of the Graduate School, Associate Dean of the College of Humanities, and professor and Ph.D. supervisor of the School of International Chinese Language Education at Jilin University. She holds a PhD in history and is a member of the China Democratic League. Prof. Dr. Ping Yu's major research area is the history of Chinese ancient culture and the international education of Chinese. She has had more than 20 essays published in the Journal of Social Science Front, Nankai Journal, Journal of Jilin University, etc. She has also undertaken and accomplished more than 10 programs in Projects of the National Social Science Foundation of China, the Project of Humanities and Social Sciences of the Ministry of Education of China, the Social Science Foundation of Jilin Province, Promoting the Internationalization of the Chinese Language of Confucius Institute Headquarters, the Language Commission of Jilin Province, and the Special Program of Jilin University. She was awarded the 4th and 5th First Prize for the Outstanding Achievement in Social Science of Changchun, Second Prize for Outstanding Achievement in Social Science Foundation of Jilin Province, and First Prize for Outstanding Achievement in Social Science of Jilin Province. She was also honored as an Advanced Individual in the 3rd election and assessment of Teacher’s Virtue in Jilin Province.
1,
Tao Lin
Tao Lin
Tao Lin received a bachelor’s degree in a prospecting and engineering technology program (applied [...]
Tao Lin received a bachelor’s degree in a prospecting and engineering technology program (applied geophysics) from Jilin University, China, in 2019. He is currently a master’s candidate at Jilin University engaged in the processing and interpretation of gravity and magnetic data.His research interests include inverse problems, multiparameter constrained inversion methods and machine learning.
1 and
Shuai Zhou
Shuai Zhou
Dr. Shuai Zhou is currently an associate professor at the College of Geo−Exploration Science and [...]
Dr. Shuai Zhou is currently an associate professor at the College of Geo−Exploration Science and Technology, at Jilin University. He received a Ph.D. degree in solid geophysics from Jilin University in 2017. Dr. Shuai Zhou has engaged in the processing and interpretation of gravity and magnetic data. His research interests include development and data processing technology of aeromagnetic systems based on the UAV platform, interpretation technology of shipload magnetic data, and multi-parameter constrained inversion technology of potential field data.
1,*
1
College of Geo−Exploration Science and Technology, Jilin University, 938 Ximinzhu Street, Changchun 130026, China
2
School of Information Science and Technology, Fudan University, Shanghai 200433, China
3
Kunming Shipborne Equipment Research and Test Center, Kunming 650051, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2024, 14(13), 5730; https://doi.org/10.3390/app14135730 (registering DOI)
Submission received: 4 June 2024
/
Revised: 25 June 2024
/
Accepted: 27 June 2024
/
Published: 30 June 2024
Abstract
The three-dimension (3D) inversion of magnetic data is an effective method of recovering underground magnetic susceptibility distributions using magnetic anomaly data. The conventional regularization inversion method has good data fitting; however, its inversion model has the problem of a poor model-fitting ability due to a low depth resolution. The 3D inversion method based on deep learning can effectively improve the model-fitting accuracy, but it is difficult to guarantee the data-fitting accuracy of the inversion results. The loss function of traditional deep learning 3D inversion methods usually adopts the metric of the absolute mean squared error (MSE). In order to improve the accuracy of the data fitting, we added a forward-fitting constraint term (FFit) on the basis of the MSE. Meanwhile, in order to further improve the accuracy of the model fitting, we added the Dice coefficient to the loss function. Finally, we proposed a multi-constraint deep learning 3D inversion method based on UNet++. Compared with the traditional single-constraint deep learning method, the multi-constraint deep learning method has better data-fitting and model-fitting effects. Then, we designed corresponding test models and evaluation metrics to test the effectiveness and feasibility of the method, and applied it to the actual aeromagnetic data of a test area in Suqian City, Jiangsu Province.
Share and Cite
MDPI and ACS Style
Jiao, J.; Zeng, X.; Liu, H.; Yu, P.; Lin, T.; Zhou, S.
Three-Dimension Inversion of Magnetic Data Based on Multi-Constraint UNet++. Appl. Sci. 2024, 14, 5730.
https://doi.org/10.3390/app14135730
AMA Style
Jiao J, Zeng X, Liu H, Yu P, Lin T, Zhou S.
Three-Dimension Inversion of Magnetic Data Based on Multi-Constraint UNet++. Applied Sciences. 2024; 14(13):5730.
https://doi.org/10.3390/app14135730
Chicago/Turabian Style
Jiao, Jian, Xiangcheng Zeng, Hui Liu, Ping Yu, Tao Lin, and Shuai Zhou.
2024. "Three-Dimension Inversion of Magnetic Data Based on Multi-Constraint UNet++" Applied Sciences 14, no. 13: 5730.
https://doi.org/10.3390/app14135730
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.