Physics-guided deep learning-based inversion for airborne electromagnetic data
Open Access
- 8 July 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Geophysical Journal International
- Vol. 238 (3) , 1774-1789
Abstract
SUMMARY: The Earth's subsurface structure provides critical insights into sustainable resource management and geologic evolution. The airborne electromagnetic (AEM) method is an efficient data acquisition technique and can be used to image the underground resistivity structure with high spatial resolution. However, inversion of the increasingly huge volume of AEM data poses a heavy computational burden. In this study, we develop a hybrid deep learning-based approach by using the physics-guided neural network (PGNN) which incorporates the governing physical laws into the loss function to solve the AEM inverse problem. The PGNN integrates the strength of data-driven method for representation learning with electromagnetic laws and allows for the underlying physical constraints to be strictly satisfied. We validate the effectiveness of our approach using both synthetic and field datasets. Compared with the classic Gauss–Newton method, our PGNN inversion system shows strong robustness against multiple noise sources and reduces the risk of being trapped in local extrema. Moreover, the PGNN-inverted results are physically more consistent with the AEM observations compared to the purely data-driven approach. Application to the field AEM data from Northern Australia demonstrates that the PGNN-based inversion framework effectively estimates the subsurface electrical properties with considerable lateral continuity and significantly higher efficiency, completing the inversion of more than 2734000 AEM soundings taking only minutes on a common PC. Our proposed PGNN-based method shows great promise for large-scale underground resistivity imaging, and the well-identified subsurface resistivity structure can effectively improve our understanding of resource distributions and geological hazards.Keywords
Funding Information
- National Natural Science Foundation of China (U2239201, 42204074)
- China Postdoctoral Science Foundation (2022M720214)
This publication has 37 references indexed in Scilit:
- Three‐dimensional inversion of semi‐airborne transient electromagnetic data based on finite element methodNear Surface Geophysics, 2021
- Hydrogeophysical Characterization in a Volcanic Context From Local to Regional Scales Combining Airborne Electromagnetism and MagnetismGeophysical Research Letters, 2021
- The Helicopter Time-Domain Electromagnetic Technology Advances in ChinaSurveys in Geophysics, 2021
- Airborne Geophysical Imaging of Weak Zones on Iliamna Volcano, Alaska: Implications for Slope StabilityJournal of Geophysical Research: Solid Earth, 2021
- Probabilistic Categorical Groundwater Salinity Mapping From Airborne Electromagnetic Data Adjacent to California's Lost Hills and Belridge Oil FieldsWater Resources Research, 2020
- New methods of controlled-source electromagnetic detection in ChinaScience China Earth Sciences, 2020
- Electromagnetic methods for mineral exploration in China: A reviewOre Geology Reviews, 2020
- A combining regularization strategy for the inversion of airborne time-domain electromagnetic dataJournal of Applied Geophysics, 2018
- A Generic 1D Forward Modeling and Inversion Algorithm for TEM Sounding with an Arbitrary Horizontal LoopPure and Applied Geophysics, 2016
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989