Title | Joint 3D inversion of gravity and magnetic data using deep learning neural networks |
Author | |
Corresponding Author | Wei, Nanyu |
DOI | |
Publication Years | 2022-08-15
|
Conference Name | 2nd International Meeting for Applied Geoscience and Energy, IMAGE 2022
|
ISSN | 1052-3812
|
EISSN | 1949-4645
|
Source Title | |
Volume | 2022-August
|
Pages | 1457-1461
|
Conference Date | August 28, 2022 - September 1, 2022
|
Conference Place | Houston, TX, United states
|
Publisher | |
Abstract | Three-dimensional (3D) joint inversion of geophysical data is often non-unique, non-linear on a large scale, and is complicated for most conventional model-driven approaches that use additional regularization terms in the objective function. In recent years, with the development of computing devices and artificial intelligence, processing large-scale data using data-driven methods is no longer difficult, and great progress has been made in the inversion of single geophysical dataset using the deep learning. In this work, we explore the feasibility of using deep learning methods for 3D joint inversion. In particular, we propose two methods based on modified U-Net architectures: (1) early fusion that constructs a single network and requires different types of data to be preprocessed to share the same size; (2) late fusion that employs multiple branches of network designed for different types of data, but feature-fused together before the final loss is calculated. Our synthetic examples focus on the joint 3D inversion of gravity and magnetic inversion for mineral exploration; the model is parameterized by an ore body represented by an ellipsoid with an arbitrary size, position and orientation in the 3D space. We have found that the performance of the early fusion mostly relies on the data preprocessing, but the early fusion has obvious advantages in its simplicity and efficiency; the late fusion is a more stable choice and highly flexible in cases where data are in different sizes. Our results have proven the feasibility and the basic workflow of 3D joint inversion using the deep learning methods. © 2022 Society of Exploration Geophysicists and the American Association of Petroleum Geologists. |
SUSTech Authorship | First
; Corresponding
|
Language | English
|
Indexed By | |
Funding Project | This work was supported by National Key R&D Program of China under grant no. 2018YFC0603305 and the BGP, CNPC Scientific Research Program.
|
EI Accession Number | 20230413445790
|
EI Keywords | Data handling
; Deep neural networks
; Geophysical prospecting
; Geophysics
; Large dataset
; Mineral exploration
; Ore deposits
; Ores
|
ESI Classification Code | Ergonomics and Human Factors Engineering:461.4
; Geophysics:481.3
; Geophysical Prospecting:481.4
; Exploration and Prospecting Methods:501.1
; Data Processing and Image Processing:723.2
; Gravitation, Relativity and String Theory:931.5
|
Data Source | EV Compendex
|
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/519712 |
Department | Department of Earth and Space Sciences |
Affiliation | 1.Department of Earth and Space Sciences, Southern University of Science and Technology, China 2.BGP Inc., CNPC |
First Author Affilication | Department of Earth and Space Sciences |
Corresponding Author Affilication | Department of Earth and Space Sciences |
First Author's First Affilication | Department of Earth and Space Sciences |
Recommended Citation GB/T 7714 |
Wei, Nanyu,Yang, Dikun,Wang, Zhigang,et al. Joint 3D inversion of gravity and magnetic data using deep learning neural networks[C]:Society of Exploration Geophysicists,2022:1457-1461.
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment