Stable downward continuation of the gravity potential field implemented using deep learning

被引:1
作者
Li, Honglei [1 ,2 ]
Chen, Shi [1 ,2 ]
Li, Yongbo [1 ,2 ]
Zhang, Bei [1 ,2 ]
Zhao, Ming [1 ,2 ]
Han, Jiancheng [1 ,2 ]
机构
[1] China Earthquake Adm, Inst Geophys, Beijing, Peoples R China
[2] Beijing Baijiatuan Earth Sci Natl Observat & Res S, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
gravity downward continuation; convolutional neural network; deep learning; upscaling low-resolution images; DC-Net model; ITERATION METHOD;
D O I
10.3389/feart.2022.1065252
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Downward continuation (DC) of the gravity potential field is an important approach used to understand and interpret the density structure and boundary of anomalous bodies. It is widely used to delineate and highlight local and shallow anomalous sources. However, it is well known that direct DC transformation in the frequency domain is unstable and easily affected by high-frequency noise. Recent deep learning applications have led to the development of image recognition and resolution enhancement using the convolutional neural network technique. A similar deep learning architecture is also suitable for training a model for the DC problem. In this study, to solve the problems in existing DC methods, we constructed a dedicated model called DC-Net for the DC problem. We fully trained the DC-Net model on 38,400 pairs of gravity anomaly data at different altitudes using a convolutional neural network. We conducted several experiments and implemented a real-world example. The results demonstrate the following. First, several validation data subset and test data prediction results indicate that the DC-Net model was sufficiently trained. Moreover, it performed better than the traditional strategy in refining the upscaling of low-resolution images. Second, we performed tests on test datasets with changing levels of noise and demonstrated that the DC-Net model is noise-resistant and robust. Finally, we used the proposed model in a real-world example, which demonstrates that the DC-Net model is suitable for solving the DC problem and delineating the detailed gravity anomaly feature near the field source. For real data processing, noise in the gravity anomaly should be reduced in advance. Additionally, we recommend noise quantification of the gravity anomaly before network training.
引用
收藏
页数:13
相关论文
共 39 条
[1]  
Adewumi T., 2018, EGYPT J PETROL, V27, P759, DOI [10.1016/j.ejpe.2017.11.002, DOI 10.1016/J.EJPE.2017.11.002]
[2]   Review of deep learning: concepts, CNN architectures, challenges, applications, future directions [J].
Alzubaidi, Laith ;
Zhang, Jinglan ;
Humaidi, Amjad J. ;
Al-Dujaili, Ayad ;
Duan, Ye ;
Al-Shamma, Omran ;
Santamaria, J. ;
Fadhel, Mohammed A. ;
Al-Amidie, Muthana ;
Farhan, Laith .
JOURNAL OF BIG DATA, 2021, 8 (01)
[3]   Machine learning for data-driven discovery in solid Earth geoscience [J].
Bergen, Karianne J. ;
Johnson, Paul A. ;
de Hoop, Maarten V. ;
Beroza, Gregory C. .
SCIENCE, 2019, 363 (6433) :1299-+
[4]  
Blakely RJ., 1996, Potential Theory in Gravity and Magnetic Applications, P441
[5]   Spectral Metric for Dataset Complexity Assessment [J].
Branchaud-Charron, Frederic ;
Achkar, Andrew ;
Jodoin, Pierre-Marc .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :3210-3219
[6]   An enhancing precision method for downward continuation of gravity anomalies [J].
Chen, Mengtao ;
Yang, Wencai .
JOURNAL OF APPLIED GEOPHYSICS, 2022, 204
[7]   The stable downward continuation of potential field data [J].
Cooper, Gordon .
EXPLORATION GEOPHYSICS, 2004, 35 (04) :260-265
[8]  
CORDELL L.E., 1985, Soc. Expl. Geophys, P181, DOI [10.1190/1.0931830346.ch16, DOI 10.1190/1.0931830346.CH16]
[9]  
Elieff S, 2018, INTERPLAY SAMPLING A
[10]  
Geng ZC, 2020, GEOPHYSICS, V85, pWA87, DOI [10.1190/GEO2019-0252.1, 10.1190/geo2019-0252.1]