Three-Dimension Inversion of Magnetic Data Based on Multi-Constraint UNet++
Source abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geophysical and Geoelectrical Methods · Geological and Geophysical Studies · Geomagnetism and Paleomagnetism Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Geo−Exploration Science and Technology, Jilin University, 938 Ximinzhu Street, Changchun 130026, China
School of Information Science and Technology, Fudan University, Shanghai 200433, China
Kunming Shipborne Equipment Research and Test Center, Kunming 650051, China
Funding
Ningxia Key Research and Development Plan · National Natural Science Foundation of China · Scientific Research Project of the Education Department of Jilin Province · Fundamental Research Funds for the Central Universities
References (23)
Show source-provided references
1. The historical development of the magnetic method in exploration10.1190/1.2133784 ↗
2. 3-D inversion of magnetic data10.1190/1.1443968 ↗
3. 3-D Gravity Data Inversion Based on Enhanced Dual U-Net Framework
4. 3-D Gravity and Magnetic Joint Inversion Based on Deep Learning Combined with Measurement Data Constraint
5. Deep learning 3D sparse inversion of gravity data10.1029/2021JB022476 ↗
6. Deng, H., Hu, X., Cai, H., Liu, S., Peng, R., Liu, Y., and Han, B. (2022). 3D inversion of magnetic gradient tensor data based on convolutional neural networks. Minerals, 12.10.3390/min12050566 ↗
7. 3D geological structure inversion from Noddy-generated magnetic data using deep learning methods10.1016/j.cageo.2021.104701 ↗
8. 3-D Joint Inversion of Gravity and Magnetic Data Based on a Deep Learning Network With Automatic Recognition of Structural Similarity10.1109/TGRS.2023.3330988 ↗
9. Deep Learning Inversion for Multivariate Magnetic Data
10. Inversion of the Gravity Gradiometry Data by ResUet Network: An Application in Nordkapp Basin, Barents Sea
11. Milletari, F., Navab, N., and Ahmadi, S.-A. (2016, January 25–28). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.10.1109/3DV.2016.79 ↗
12. Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Jorge Cardoso, M. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Proceedings of the Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, 14 September 2017, Proceedings 3, Springer.10.1007/978-3-319-67558-9_28 ↗
13. Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Proceedings of the4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 20 September 2018, Proceedings 4; Springer.10.1007/978-3-030-00889-5_1 ↗
14. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation10.1109/TMI.2019.2959609 ↗
15. Blakely, R.J. (1996). Potential Theory in Gravity and Magnetic Applications, Cambridge University Press.10.1017/CBO9780511549816 ↗
16. U-net and its variants for medical image segmentation: A review of theory and applications10.1109/ACCESS.2021.3086020 ↗
17. WBC-Net: A white blood cell segmentation network based on UNet++ and ResNet10.1016/j.asoc.2020.107006 ↗
18. DifUnet++: A satellite images change detection network based on UNet++ and differential pyramid
19. Peng, D., Zhang, Y., and Guan, H. (2019). End-to-end change detection for high resolution satellite images using improved UNet++. Remote Sens., 11.10.3390/rs11111382 ↗
20. Cao, Y., and Gu, Q. (2020, January 7–12). Generalization error bounds of gradient descent for learning over-parameterized deep relu networks. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i04.5736 ↗
21. Active fault survey on the Tanlu fault zone in Laizhou Bay10.1007/s11589-006-0506-5 ↗
22. High resolution tomography of the Tanlu fault zone near Hefei with passive seismic and magnetotelluric linear array data10.29382/eqs-2020-0061 ↗
23. High-resolution 3-D crustal shear-wave velocity model reveals structural and seismicity segmentation of the central-southern Tanlu Fault zone, eastern China10.1016/j.tecto.2020.228372 ↗