3D gravity anomaly forward and inversion algorithm based on improved LinkNet

YuJie ZHANG, HouPu LI, MengXin QIU

Prog Geophy ›› 2024, Vol. 39 ›› Issue (6) : 2219-2231.

PDF(9301 KB)
Home Journals Progress in Geophysics
Progress in Geophysics

Abbreviation (ISO4): Prog Geophy      Editor in chief:

About  /  Aim & scope  /  Editorial board  /  Indexed  /  Contact  / 
PDF(9301 KB)
Prog Geophy ›› 2024, Vol. 39 ›› Issue (6) : 2219-2231. DOI: 10.6038/pg2024HH0411

3D gravity anomaly forward and inversion algorithm based on improved LinkNet

Author information +
History +

Abstract

gravity exploration is one of the most widely used geophysical methods in geophysics exploration by measuring gravity anomalies caused by density anomalies and interpreting the underground density anomalies qualitatively and quantitatively. Because 3D inversion of physical properties can describe the study object of geological structure more precisely, it has become a conventional method for quantitative interpretation of gravity anomaly data. Based on LinkNet, the forward and inverse methods of 3D gravity anomaly are studied in this paper. The forward network is constructed on the basis of Residual network to realize the mapping from underground density anomaly to gravity anomaly data. The loss function uses MSE loss, which constrains the real gravity anomaly data and the prediction value of the gravity anomaly output of the forward network. The encoder module of the inversion network is changed to the form of dense connection, and the mapping of gravity anomaly data to underground density anomaly body is studied. The loss function uses Dice loss to constrain the similarity between the real density anomaly and the density anomaly predicted by the inversion network. The data loss and the model loss are constrained by the forward network and the inverse network to reduce the non-uniqueness of the solution. By comparing with the method of training only inversion network, it is found that the average relative error of training both forward and inversion network is lower on the conventional data set, which verifies the effectiveness of the method, the effect of the network is further verified on the random model and five conventional models. Finally, the effect of the network on real field data is tested.

Key words

Gravity forward modeling / Gravity inversion / LinkNet / Residual network / Deep learning

Cite this article

Download Citations
YuJie ZHANG , HouPu LI , MengXin QIU. 3D gravity anomaly forward and inversion algorithm based on improved LinkNet[J]. Progress in Geophysics. 2024, 39(6): 2219-2231 https://doi.org/10.6038/pg2024HH0411

References

Adler J , Öktem O . Solving ill-posed inverse problems using iterative deep neural networks. Inverse Problems. 2017, 33(12 124007
Aggarwal H K , Mani M P , Jacob M . MoDL: model-based deep learning architecture for inverse problems. IEEE Transactions on Medical Imaging. 2019, 38(2): 394 405
Chen L H , Sun J G , Wu Y G , et al. Review of quasi-linear approximation in geophysical inversion. Progress in Geophysics. 2002, 17(3): 464-472
Huang R , Liu S , Qi R , et al. Deep learning 3D sparse inversion of gravity data. Journal of Geophysical Research: Solid Earth. 2021, 126(11): e2021JB022476
Li H P , Qi R , Hu J X , et al. 3D gravity anomaly inversion based on LinkNet. Applied Geophysics. 2023, 20(1): 36-50
Li Y G , Oldenburg D W . 3-D inversion of gravity data. Geophysics. 1998, 63(1): 109-119
Li Z L , Yao C L , Zheng Y M . 3D inversion of gravity data using Lp-norm sparse optimization. Chinese Journal of Geophysics. 2019, 62(10): 3699-3709
Liang Q , Chen C , Li Y G . 3-D inversion of gravity data in spherical coordinates with application to the GRAIL data. Journal of Geophysical Research: Planets. 2014, 119(6): 1359-1373
Liu J X , Sun H L , Chen B , et al. Review of the gravity and magnetic methods in the exploration of metal deposits. Progress in Geophysics. 2016, 31(2): 713-722
Liu S , Hu X Y , Liu T Y . A stochastic inversion method for potential field data: ant colony optimization. Pure and Applied Geophysics. 2014, 171(7): 1531-1555
M , Zhang Y , Liu S . Fast forward approximation and multitask inversion of gravity anomaly based on UNet3+. Geophysical Journal International. 2023, 234(2): 972-984
Noh K , Yoon D , Byun J . Imaging subsurface resistivity structure from airborne electromagnetic induction data using deep neural network. Exploration Geophysics. 2020, 51(2): 214-220
Pallero J L G , Fernández-Martínez J L , Bonvalot S , et al. Gravity inversion and uncertainty assessment of basement relief via particle swarm optimization. Journal of Applied Geophysics. 2015, 116 180-191
Phillips N , Chen J P , Oldenburg D , et al. Cost effectiveness of geophysical inversions in mineral exploration: applications at San Nicolas. The Leading Edge. 2001, 20(12): 1351-1360
Puzyrev V . Deep learning electromagnetic inversion with convolutional neural networks. Geophysical Journal International. 2019, 218(2): 817-832
Qin P B , Huang D N , Yuan Y , et al. Integrated gravity and gravity gradient 3D inversion using the non-linear conjugate gradient. Journal of Applied Geophysics. 2016, 126 52-73
Rezaie M . 3D non-smooth inversion of gravity data by zero order minimum entropy stabilizing functional. Physics of the Earth and Planetary Interiors. 2019, 294 106275
Shelhamer E , Long J , Darrell T . Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017, 39(4): 640-651
Wang L L , Meng D L , Wu B Y . Seismic inversion via closed-loop fully convolutional residual network and transfer learning. Geophysics. 2021, 86(5): R671-R683
Wang Y C , Liu L T , Xu H Z . The identification of gravity anomaly body based on the convolutional neural network. Geophysical and Geochemical Exploration. 2020, 44(2): 394-400
Wang Y Q , Ge Q , Lu W K , et al. Well-logging constrained seismic inversion based on closed-loop convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing. 2020, 58(8): 5564-5574
Zhang L Z , Zhang G B , Liu Y , et al. Deep learning for 3-D inversion of gravity data. IEEE Transactions on Geoscience and Remote Sensing. 2022, 60 5905918
Zhang Z H , Liao X L , Cao Y Y , et al. Joint gravity and gravity gradient inversion based on deep learning. Chinese Journal of Geophysics. 2021a, 64(4): 1435-1452
Zhang Z H , Lu R Q , Liao X L , et al. Inversion of magnetic anomaly and magnetic gradient anomaly based on fully convolution network. Progress in Geophysics. 2021b, 36(1): 325-337
陈丽虹 , 建国 , 燕冈 , et al. 地球物理反演的拟线性近似方法综述. 地球物理学进展. 2002, 17(3): 464-472
泽林 , 长利 , 元满 . 基于Lp范数稀疏优化算法的重力三维反演. 地球物理学报. 2019, 62(10): 3699-3709
建新 , 欢乐 , , et al. 重磁方法在国内外金属矿中的研究进展. 地球物理学进展. 2016, 31(2): 713-722
逸宸 , 林涛 , 厚泽 . 基于卷积神经网络识别重力异常体. 物探与化探. 2020, 44(2): 394-400
志厚 , 晓龙 , 云勇 , et al. 基于深度学习的重力异常与重力梯度异常联合反演. 地球物理学报. 2021a, 64(4): 1435-1452
志厚 , 润琪 , 晓龙 , et al. 基于全卷积神经网络的磁异常及磁梯度异常反演. 地球物理学进展. 2021b, 36(1): 325-337

感谢审稿专家提出的修改意见和编辑部的大力支持!

RIGHTS & PERMISSIONS

Copyright ©2024 Progress in Geophysics. All rights reserved.
PDF(9301 KB)

Accesses

Citation

Detail

Sections
Recommended

/