skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Instantaneous Inversion of Airborne Electromagnetic Data Based on Deep Learning

Geophysical research letters, 2022-05, Vol.49 (10), p.n/a [Peer Reviewed Journal]

2022. American Geophysical Union. All Rights Reserved. ;ISSN: 0094-8276 ;EISSN: 1944-8007 ;DOI: 10.1029/2021GL097165

Full text available

Citations Cited by
  • Title:
    Instantaneous Inversion of Airborne Electromagnetic Data Based on Deep Learning
  • Author: Wu, Sihong ; Huang, Qinghua ; Zhao, Li
  • Subjects: Adaptability ; airborne electromagnetics ; Algorithms ; Data acquisition ; Deep learning ; Domains ; Electrical properties ; electrical property ; Electrical resistivity ; Geological surveys ; Hazard mitigation ; Inversion ; Lake basins ; Lakes ; Machine learning ; Machine translation ; Measuring instruments ; Mitigation ; Mountains ; Reconstruction ; resistivity imaging ; Resource exploration ; Soundings ; subsurface structure ; Surveying ; Time measurement ; Urban development ; Urbanization
  • Is Part Of: Geophysical research letters, 2022-05, Vol.49 (10), p.n/a
  • Description: The airborne electromagnetic (AEM) method is becoming an effective means for subsurface electrical property reconstruction with the merits of terrain adaptability and acquisition efficiency. However, instantaneous inversion of time‐domain AEM data is still a challenge, owing to the huge amount of data. Inspired by Google's neural machine translation system, we develop a fast inversion operator guided by deep learning to translate time‐domain AEM measurements directly into subsurface resistivity structures. Trained by synthetic data, our system shows impressive adaptability to field observations and strong robustness against noise disturbance. Applied to the AEM data set acquired by the U.S. Geological Survey in Leach Lake Basin, CA, USA, our system successfully delivers results in seconds for a common PC from more than 740,000 AEM soundings. The inverted structures clearly delineate the geometries of the lake, surrounding mountains and faults. The inversion operator can support instantaneous subsurface resistivity reconstruction for AEM observations. Plain Language Summary The airborne electromagnetic (AEM) method helps establish our understanding of subsurface structure (depth of hundreds of meters) in terms of electrical properties. However, large survey area and high sampling density lead to enormous volumes of data, thus slowing down the inversion process. We develop a fast inversion operator based on deep learning to map electromagnetic responses directly onto resistivity models. We demonstrate the system's performance on both synthetic and field data. Our system yields more robust results than conventional inversion algorithms, and in a quasi real‐time manner, which will greatly improve the efficiency of AEM data inversion. The instant subsurface imaging can be greatly beneficial for resource exploration and management, urban development, hazard mitigation, and other applications. Key Points We use synthetic data to train a deep learning‐based long short‐term memory network for airborne electromagnetic data inversion Application to field data yields accurate, instantaneous results, depicting subsurface geometries of lake, mountains, and faults The instant subsurface imaging system supports applications including resource exploration, urban development, hazard mitigation, etc
  • Publisher: Washington: John Wiley & Sons, Inc
  • Language: English
  • Identifier: ISSN: 0094-8276
    EISSN: 1944-8007
    DOI: 10.1029/2021GL097165
  • Source: Wiley Blackwell AGU Digital Library
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait