Fast imaging for the 3D density structures by machine learning approach
Residual Bouguer gravity anomaly inversion can be used to imaging for local density structures or to interpret near-surface anomalous mass distribution. The reasonable prior information is the crucial recipe for obtaining a realistic geological inversion result, especially for the ill-posed geophysi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2022.1028399/full |
| _version_ | 1828070322274828288 |
|---|---|
| author | Yongbo Li Yongbo Li Shi Chen Shi Chen Shi Chen Bei Zhang Bei Zhang Honglei Li Honglei Li |
| author_facet | Yongbo Li Yongbo Li Shi Chen Shi Chen Shi Chen Bei Zhang Bei Zhang Honglei Li Honglei Li |
| author_sort | Yongbo Li |
| collection | DOAJ |
| description | Residual Bouguer gravity anomaly inversion can be used to imaging for local density structures or to interpret near-surface anomalous mass distribution. The reasonable prior information is the crucial recipe for obtaining a realistic geological inversion result, especially for the ill-posed geophysical inversion problem. The conventional strategies introduce the prior constraints or joint multidisciplinary information in object function as regularization, and then use some optimization algorithm to minimize the object function. This process is called model-driven approach and is usually time-consuming. In recent years, the rapid development of machine learning technology has provided new solutions for solving geophysical inversion problems. Machine learning methods can reduce the dependence on prior information in the inversion process through setting special training datasets, and the time consumption of an inversion process executed by the trained model can be shortened by several orders of magnitude, which is conducive to fast inversion for the same type of application scenarios. In this study, we were inspired by the U-net model and develops the GV-Net (Gravity voxels inversion network) model using the convolutional neural network for the inversion of residual gravity anomalies. We first discussed the effects of different loss functions on the convergence speed of model training and prediction accuracy. Then, we analyzed the robustness of our model by changing noise levels of the datasets. At last, we employed this model in a real scenario. The results have demonstrated that the GV-Net model has the ability to deal with specific inverse problems by predefined training datasets. |
| first_indexed | 2024-04-11T00:35:55Z |
| format | Article |
| id | doaj.art-6e8766a2edf245c2acb83abf709a69c9 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-04-11T00:35:55Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-6e8766a2edf245c2acb83abf709a69c92023-01-06T19:04:30ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-01-011010.3389/feart.2022.10283991028399Fast imaging for the 3D density structures by machine learning approachYongbo Li0Yongbo Li1Shi Chen2Shi Chen3Shi Chen4Bei Zhang5Bei Zhang6Honglei Li7Honglei Li8Institute of Geophysics, China Earthquake Administration, Beijing, ChinaBeijing Baijiatuan Earth Science National Observation and Research Station, Beijing, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing, ChinaBeijing Baijiatuan Earth Science National Observation and Research Station, Beijing, ChinaNational Engineering Research Center of Offshore Oil and Gas Exploration, Beijing, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing, ChinaBeijing Baijiatuan Earth Science National Observation and Research Station, Beijing, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing, ChinaBeijing Baijiatuan Earth Science National Observation and Research Station, Beijing, ChinaResidual Bouguer gravity anomaly inversion can be used to imaging for local density structures or to interpret near-surface anomalous mass distribution. The reasonable prior information is the crucial recipe for obtaining a realistic geological inversion result, especially for the ill-posed geophysical inversion problem. The conventional strategies introduce the prior constraints or joint multidisciplinary information in object function as regularization, and then use some optimization algorithm to minimize the object function. This process is called model-driven approach and is usually time-consuming. In recent years, the rapid development of machine learning technology has provided new solutions for solving geophysical inversion problems. Machine learning methods can reduce the dependence on prior information in the inversion process through setting special training datasets, and the time consumption of an inversion process executed by the trained model can be shortened by several orders of magnitude, which is conducive to fast inversion for the same type of application scenarios. In this study, we were inspired by the U-net model and develops the GV-Net (Gravity voxels inversion network) model using the convolutional neural network for the inversion of residual gravity anomalies. We first discussed the effects of different loss functions on the convergence speed of model training and prediction accuracy. Then, we analyzed the robustness of our model by changing noise levels of the datasets. At last, we employed this model in a real scenario. The results have demonstrated that the GV-Net model has the ability to deal with specific inverse problems by predefined training datasets.https://www.frontiersin.org/articles/10.3389/feart.2022.1028399/fullgravity inversionconvolutional neural networkmachine learningore body identificationfast inversionbouguer gravity anomaly |
| spellingShingle | Yongbo Li Yongbo Li Shi Chen Shi Chen Shi Chen Bei Zhang Bei Zhang Honglei Li Honglei Li Fast imaging for the 3D density structures by machine learning approach Frontiers in Earth Science gravity inversion convolutional neural network machine learning ore body identification fast inversion bouguer gravity anomaly |
| title | Fast imaging for the 3D density structures by machine learning approach |
| title_full | Fast imaging for the 3D density structures by machine learning approach |
| title_fullStr | Fast imaging for the 3D density structures by machine learning approach |
| title_full_unstemmed | Fast imaging for the 3D density structures by machine learning approach |
| title_short | Fast imaging for the 3D density structures by machine learning approach |
| title_sort | fast imaging for the 3d density structures by machine learning approach |
| topic | gravity inversion convolutional neural network machine learning ore body identification fast inversion bouguer gravity anomaly |
| url | https://www.frontiersin.org/articles/10.3389/feart.2022.1028399/full |
| work_keys_str_mv | AT yongboli fastimagingforthe3ddensitystructuresbymachinelearningapproach AT yongboli fastimagingforthe3ddensitystructuresbymachinelearningapproach AT shichen fastimagingforthe3ddensitystructuresbymachinelearningapproach AT shichen fastimagingforthe3ddensitystructuresbymachinelearningapproach AT shichen fastimagingforthe3ddensitystructuresbymachinelearningapproach AT beizhang fastimagingforthe3ddensitystructuresbymachinelearningapproach AT beizhang fastimagingforthe3ddensitystructuresbymachinelearningapproach AT hongleili fastimagingforthe3ddensitystructuresbymachinelearningapproach AT hongleili fastimagingforthe3ddensitystructuresbymachinelearningapproach |