Articles | Volume 15, issue 3
https://doi.org/10.5194/essd-15-1389-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-15-1389-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
DL-RMD: a geophysically constrained electromagnetic resistivity model database (RMD) for deep learning (DL) applications
Muhammad Rizwan Asif
CORRESPONDING AUTHOR
Hydro-Geophysics Group (HGG), Department of Geoscience, Aarhus
University, Aarhus C, 8000, Denmark
Department of Electrical and Computer Engineering, Aarhus University, Aarhus N, 8200, Denmark
Aarhus University Centre for Water Technology (WATEC), Aarhus University, Aarhus C, 8000, Denmark
Nikolaj Foged
Hydro-Geophysics Group (HGG), Department of Geoscience, Aarhus
University, Aarhus C, 8000, Denmark
Aarhus University Centre for Water Technology (WATEC), Aarhus University, Aarhus C, 8000, Denmark
Thue Bording
Hydro-Geophysics Group (HGG), Department of Geoscience, Aarhus
University, Aarhus C, 8000, Denmark
Aarhus GeoInstruments, Åbyhøj, 8230, Denmark
Jakob Juul Larsen
Department of Electrical and Computer Engineering, Aarhus University, Aarhus N, 8200, Denmark
Aarhus University Centre for Water Technology (WATEC), Aarhus University, Aarhus C, 8000, Denmark
Anders Vest Christiansen
Hydro-Geophysics Group (HGG), Department of Geoscience, Aarhus
University, Aarhus C, 8000, Denmark
Aarhus University Centre for Water Technology (WATEC), Aarhus University, Aarhus C, 8000, Denmark
Related authors
No articles found.
Nikhil B. Gaikwad, Lichao Liu, Matthew P. Griffiths, Denys Grombacher, and Jakob Juul Larsen
Geosci. Instrum. Method. Data Syst., 14, 139–151, https://doi.org/10.5194/gi-14-139-2025, https://doi.org/10.5194/gi-14-139-2025, 2025
Short summary
Short summary
This work presents simulations, modelling, and experimental verification of a novel steady-state surface nuclear magnetic resonance (NMR) transmitter used for the non-invasive exploration of groundwater. The paper focuses on three main aspects of high-current transmitter instrumentation: thermal management, current-drooping, and pulse stability. This work will interest readers involved in geoscientific instrument prototyping for groundwater exploration using portable geoscientific instruments.
Mathias Vang, Jakob Juul Larsen, Anders Vest Christiansen, and Denys Grombacher
EGUsphere, https://doi.org/10.5194/egusphere-2025-406, https://doi.org/10.5194/egusphere-2025-406, 2025
Short summary
Short summary
To manage groundwater effectively, it's important to understand subsurface water systems. Geophysical methods can characterize subsurface layers, but relying on just one method can be misleading. This study combines two methods – Transient electromagnetics and surface nuclear magnetic resonance – in a K-means clustering scheme to better resolve freshwater and saltwater zones. Two case studies showed how a combined approach improves characterization of these hydrogeological important layers.
Smith Kashiram Khare, Paul McLachlan, Pradip Kumar Maurya, and Jakob Juul Larsen
Geosci. Instrum. Method. Data Syst., 13, 27–41, https://doi.org/10.5194/gi-13-27-2024, https://doi.org/10.5194/gi-13-27-2024, 2024
Short summary
Short summary
Data recorded with transient electromagnetics are typically gated to improve the signal-to-noise ratio. Gating corresponds to low-pass filtering of data with the shape of the gate giving the frequency response. We show that standard gate shapes can lead to significant correlation between gates caused by distortion from VLF radios. A multi-objective cost function is used to select optimum gate shapes with less influence from radio noise. Performance is demonstrated using synthetic and field data.
Hafsa Mahmood, Ty P. A. Ferré, Raphael J. M. Schneider, Simon Stisen, Rasmus R. Frederiksen, and Anders V. Christiansen
EGUsphere, https://doi.org/10.5194/egusphere-2023-1872, https://doi.org/10.5194/egusphere-2023-1872, 2023
Preprint withdrawn
Short summary
Short summary
Temporal drain flow dynamics and understanding of their underlying controlling factors are important for water resource management in tile-drained agricultural areas. This study examine whether simpler, more efficient machine learning (ML) models can provide acceptable solutions compared to traditional physics based models. We predicted drain flow time series in multiple catchments subject to a range of climatic and landscape conditions.
Mathias Vang, Denys Grombacher, Matthew P. Griffiths, Lichao Liu, and Jakob Juul Larsen
Hydrol. Earth Syst. Sci., 27, 3115–3124, https://doi.org/10.5194/hess-27-3115-2023, https://doi.org/10.5194/hess-27-3115-2023, 2023
Short summary
Short summary
In this paper, we use a novel surface nuclear magnetic resonance (SNMR) method for rapid high-quality data acquisition. The SNMR results from more than 100 soundings in three different case studies were used to map groundwater. The soundings successfully track the water table through the three areas and are compared to boreholes and other geophysical measurements. The study highlights the use of SNMR in hydrological surveys and as a tool for regional mapping of the water table.
Hilary A. Dugan, Peter T. Doran, Denys Grombacher, Esben Auken, Thue Bording, Nikolaj Foged, Neil Foley, Jill Mikucki, Ross A. Virginia, and Slawek Tulaczyk
The Cryosphere, 16, 4977–4983, https://doi.org/10.5194/tc-16-4977-2022, https://doi.org/10.5194/tc-16-4977-2022, 2022
Short summary
Short summary
In the McMurdo Dry Valleys of Antarctica, a deep groundwater system has been hypothesized to connect Don Juan Pond and Lake Vanda, both surface waterbodies that contain very high concentrations of salt. This is unusual, since permafrost in polar landscapes is thought to prevent subsurface hydrologic connectivity. We show results from an airborne geophysical survey that reveals widespread unfrozen brine in Wright Valley and points to the potential for deep valley-wide brine conduits.
Pradip Kumar Maurya, Frederik Ersted Christensen, Masson Andy Kass, Jesper B. Pedersen, Rasmus R. Frederiksen, Nikolaj Foged, Anders Vest Christiansen, and Esben Auken
Hydrol. Earth Syst. Sci., 26, 2813–2827, https://doi.org/10.5194/hess-26-2813-2022, https://doi.org/10.5194/hess-26-2813-2022, 2022
Short summary
Short summary
In this paper, we present an application of the electromagnetic method to image the subsurface below rivers, lakes, or any surface water body. The scanning of the subsurface is carried out by sailing an electromagnetic sensor called FloaTEM. Imaging results show a 3D distribution of different sediment types below the freshwater lakes. In the case of saline water, the system is capable of identifying the probable location of groundwater discharge into seawater.
M. Andy Kass, Esben Auken, Jakob Juul Larsen, and Anders Vest Christiansen
Geosci. Instrum. Method. Data Syst., 10, 313–323, https://doi.org/10.5194/gi-10-313-2021, https://doi.org/10.5194/gi-10-313-2021, 2021
Short summary
Short summary
We have developed a towed magnetic gradiometer system for rapid acquisition of magnetic and magnetic gradient maps. This high-resolution system is flexible and has applications to utility detection, archaeology, unexploded ordnance, or any other applications where high-resolution maps of the magnetic field or gradient are required. Processing of the data has been simplified as much as possible to facilitate rapid results and interpretations.
Krista F. Myers, Peter T. Doran, Slawek M. Tulaczyk, Neil T. Foley, Thue S. Bording, Esben Auken, Hilary A. Dugan, Jill A. Mikucki, Nikolaj Foged, Denys Grombacher, and Ross A. Virginia
The Cryosphere, 15, 3577–3593, https://doi.org/10.5194/tc-15-3577-2021, https://doi.org/10.5194/tc-15-3577-2021, 2021
Short summary
Short summary
Lake Fryxell, Antarctica, has undergone hundreds of meters of change in recent geologic history. However, there is disagreement on when lake levels were higher and by how much. This study uses resistivity data to map the subsurface conditions (frozen versus unfrozen ground) to map ancient shorelines. Our models indicate that Lake Fryxell was up to 60 m higher just 1500 to 4000 years ago. This amount of lake level change shows how sensitive these systems are to small changes in temperature.
Alexis Neven, Pradip Kumar Maurya, Anders Vest Christiansen, and Philippe Renard
Earth Syst. Sci. Data, 13, 2743–2752, https://doi.org/10.5194/essd-13-2743-2021, https://doi.org/10.5194/essd-13-2743-2021, 2021
Short summary
Short summary
The shallow underground is constituted of sediments that present high spatial variability. This upper layer is the most extensively used for resource exploitation (groundwater, geothermal heat, construction materials, etc.). Understanding and modeling the spatial variability of these deposits is crucial. We present a high-resolution electrical resistivity dataset that covers the upper Aare Valley in Switzerland. These data can help develop methods to characterize these geological formations.
Rasmus Bødker Madsen, Hyojin Kim, Anders Juhl Kallesøe, Peter B. E. Sandersen, Troels Norvin Vilhelmsen, Thomas Mejer Hansen, Anders Vest Christiansen, Ingelise Møller, and Birgitte Hansen
Hydrol. Earth Syst. Sci., 25, 2759–2787, https://doi.org/10.5194/hess-25-2759-2021, https://doi.org/10.5194/hess-25-2759-2021, 2021
Short summary
Short summary
The protection of subsurface aquifers from contamination is an ongoing environmental challenge. Some areas of the underground have a natural capacity for reducing contaminants. In this research these areas are mapped in 3D along with information about, e.g., sand and clay, which indicates whether contaminated water from the surface will travel through these areas. This mapping technique will be fundamental for more reliable risk assessment in water quality protection.
Jakob Juul Larsen, Stine Søgaard Pedersen, Nikolaj Foged, and Esben Auken
Geosci. Instrum. Method. Data Syst., 10, 81–90, https://doi.org/10.5194/gi-10-81-2021, https://doi.org/10.5194/gi-10-81-2021, 2021
Short summary
Short summary
The transient electromagnetic method (TEM) is widely used for mapping subsurface resistivity structures, but data are inevitably contaminated by noise from various sources including radio signals in the very low frequency (VLF) 3–30 kHz band. We present an approach where VLF noise is effectively suppressed with a new post-processing scheme where boxcar gates are combined into semi-tapered gates. The result is a 20 % increase in the depth of investigation for the presented test survey.
Cited articles
Asif, M. R.: rizwanasif/DL-RMD: DL-RMD (DL-RMD), Zenodo [code], https://doi.org/10.5281/zenodo.7740243, 2023.
Asif, M. R., Qi, C., Wang, T., Fareed, M. S., and Khan, S.: License plate
detection for multi-national vehicles–a generalized approach, Multimed.
Tools Appl., 78, 35585–35606, 2019.
Asif, M. R., Bording, T. S., Barfod, A. S., Grombacher, D. J., Maurya, P.
K., Christiansen, A. V., Auken, E., and Larsen, J. J.: Effect of data
pre-processing on the performance of neural networks for 1-D transient
electromagnetic forward modelling, IEEE Access, 9, 34635–34646, 2021a.
Asif, M. R., Bording, T. S., Maurya, P. K., Zhang, B., Fiandaca, G.,
Grombacher, D. J., Christiansen, A. V., Auken, E., and Larsen, J. J.: A
Neural Network-Based Hybrid Framework for Least-Squares Inversion of
Transient Electromagnetic Data, IEEE T. Geosci. Remote, 60, 4503610, https://doi.org/10.1109/TGRS.2021.3076121, 2021b.
Asif, M. R., Foged, N., Bording, T., Larsen, J. J., and Christiansen, A. V.:
DL-RMD: A geophysically constrained electromagnetic resistivity model
database for deep learning applications, Zenodo [data set], https://doi.org/10.5281/zenodo.7260886, 2022a.
Asif, M. R., Foged, N., Maurya, P. K., Grombacher, D. J., Christiansen, A.
V., Auken, E., and Larsen, J. J.: Integrating neural networks in
least-squares inversion of airborne time-domain electromagnetic data,
Geophysics, 87, E177–E187, https://doi.org/10.1190/geo2021-0335.1, 2022b.
Auken, E., Christiansen, A. V., Kirkegaard, C., Fiandaca, G., Schamper, C.,
Behroozmand, A. A., Binley, A., Nielsen, E., Effersø, F., and
Christensen, N. B.: An overview of a highly versatile forward and stable
inverse algorithm for airborne, ground-based and borehole electromagnetic
and electric data, Explor. Geophys., 46, 223–235, https://doi.org/10.1071/EG13097, 2015 (data available at: https://hgg.au.dk/software/aarhusinv, last access: 16 March 2023).
Auken, E., Foged, N., Larsen, J. J., Lassen, K. V. T., Maurya, P. K., Dath,
S. M., and Eiskjær, T. T.: tTEM – A towed transient electromagnetic
system for detailed 3D imaging of the top 70 m of the subsurface,
Geophysics, 84, E13–E22, 2018.
Baan, M. V. D. and Jutten, C.: Neural networks in geophysical applications,
Geophysics, 65, 1032–1047, 2000.
Bai, P., Vignoli, G., Viezzoli, A., Nevalainen, J., and Vacca, G.: (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via
Artificial Neural Network, Remote Sensing, 12, 3440, https://doi.org/10.3390/rs12203440, 2020.
Balch, S., Boyko, W., and Paterson, N.: The AeroTEM airborne electromagnetic
system, The Leading Edge, 22, 562–566, 2003.
Bang, M., Oh, S., Noh, K., Seol, S. J., and Byun, J.: Imaging subsurface orebodies with airborne electromagnetic data using a recurrent neural network, Geophysics, 86, E407–E419, https://doi.org/10.1190/geo2020-0871.1, 2021.
Bergen, K. J., Johnson, P. A., Maarten, V., and Beroza, G. C.: Machine
learning for data-driven discovery in solid Earth geoscience, Science, 363,
eaau0323, https://doi.org/10.1126/science.aau0323, 2019.
Birken, R. A. and Poulton, M. M.: Neural Network Interpretation of High
Frequency Electromagnetic Ellipticity Data Part II: Analyzing 3D Responses,
Journal of Environmental Engineering Geophysics, 4, 149–165, 1999.
Birken, R. A., Poulton, M. M., and Lee, K. H.: Neural Network Interpretation
of High Frequency Electromagnetic Ellipticity Data Part I: Understanding the
Half-Space and Layered Earth Response, Journal of Environmental Engineering
Geophysics, 4, 93–103, 1999.
Bording, T. S., Asif, M. R., Barfod, A. S., Larsen, J. J., Zhang, B.,
Grombacher, D. J., Christiansen, A. V., Engebretsen, K. W., Pedersen, J. B.,
Maurya, P. K., and Auken, E.: Machine learning based fast forward modelling
of ground-based time-domain electromagnetic data, J. Appl.
Geophys., 187, 104290, https://doi.org/10.1016/j.jappgeo.2021.104290, 2021.
Christiansen, A. V. and Auken, E.: Layered 2-D inversion of profile data,
evaluated using stochastic models, ASEG Extended Abstracts, 1–8, https://doi.org/10.1071/ASEG2003_3DEMab005, 2003.
Christiansen, A. V. and Auken, E.: A global measure for depth of
investigation, Geophysics, 77, WB171–WB177, 2012.
Christiansen, A. V., Auken, E., and Sørensen, K.: The transient
electromagnetic method, in: Groundwater geophysics, edited by: Kirsch, R., Springer, ISBN 978-3-540-29383-5, https://doi.org/10.1007/3-540-29387-6_6, 2006.
Colombo, D., Li, W., Rovetta, D., Sandoval-Curiel, E., and Turkoglu, E.:
Physics-driven deep learning joint inversion, in: SEG Technical Program
Expanded Abstracts 2020, Society of Exploration Geophysicists, 1775–1779, https://doi.org/10.1190/segam2020-3424997.1, 2020a.
Colombo, D., Li, W., Sandoval-Curiel, E., and McNeice, G. W.:
Electromagnetic reservoir monitoring with machine-learning inversion and
fluid flow simulators, in: Fifth International Conference on Engineering
Geophysics (ICEG), Al Ain, UAE, 21–24 October 2019, 167–170, https://doi.org/10.1190/iceg2019-043.1, 2020b.
Colombo, D., Turkoglu, E., Li, W., and Rovetta, D.: Coupled physics-deep
learning inversion, Comput. Geosci., 157, 104917, https://doi.org/10.1016/j.cageo.2021.104917, 2021a.
Colombo, D., Turkoglu, E., Li, W., Sandoval-Curiel, E., and Rovetta, D.:
Physics-driven deep learning inversion with application to transient
electromagnetics, Geophysics, 86, E209–E224, https://doi.org/10.1190/geo2020-0760.1, 2021b.
Conway, D., Alexander, B., King, M., Heinson, G., and Kee, Y.: Inverting
magnetotelluric responses in a three-dimensional earth using fast forward
approximations based on artificial neural networks, Comput.
Geosci., 127, 44–52, 2019.
Dong, C., Loy, C. C., and Tang, X.: Accelerating the super-resolution
convolutional neural network, in: European conference on computer vision, Amsterdam, the Netherlands, 11–14 October 2016,
391–407, https://doi.org/10.1007/978-3-319-46475-6_25, 2016.
Dramsch, J. S.: 70 years of machine learning in geoscience in review,
Adv. Geophys., 61, 1–55, https://doi.org/10.1016/bs.agph.2020.08.002, 2020.
Feng, X.-T. and Seto, M.: Neural network dynamic modelling of rock
microfracturing sequences under triaxial compressive stress conditions,
Tectonophysics, 292, 293–309, 1998.
Guo, R., Li, M., Fang, G., Yang, F., Xu, S., and Abubakar, A.: Application
of supervised descent method to transient electromagnetic data inversion,
Geophysics, 84, E225–E237, 2019.
Hopfield, J. J.: Neural networks and physical systems with emergent
collective computational abilities, P. Natl. Acad.
Sci. USA, 79, 2554–2558, 1982.
Jørgensen, F., Sandersen, P. B., Auken, E., Lykke-Andersen, H., and
Sørensen, K.: Contributions to the geological mapping of Mors, Denmark – a
study based on a large-scale TEM survey, B. Geol. Soc.
Denmark, 52, 53–75, 2005.
Karshakov, E. V., Podmogov, Y. G., Kertsman, V. M., and Moilanen, J.:
Combined Frequency Domain and Time Domain Airborne Data for Environmental
and Engineering Challenges, J. Environ. Eng. Geoph.,
22, 1–11, https://doi.org/10.2113/JEEG22.1.1, 2017.
Khatibi, S. and Aghajanpour, A.: Machine Learning: A Useful Tool in
Geomechanical Studies, a Case Study from an Offshore Gas Field, Energies,
13, 3528, https://doi.org/10.3390/en13143528, 2020.
Kirsch, R.: Groundwater geophysics: a tool for hydrogeology, Springer, ISBN 978-3-540-29383-5, https://doi.org/10.1007/3-540-29387-6, 2006.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet classification with deep convolutional neural networks, Adv. Neur. Inf. Proc. Sys., 25, 1097–1105, https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf (last access: 16 March 2023), 2012.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: Imagenet classification
with deep convolutional neural networks, Communications of the ACM, 60,
84–90, 2017.
Kwan, K., Reford, S., Abdoul-Wahab, D. M., Pitcher, D. H., Bournas, N.,
Prikhodko, A., Plastow, G., and Legault, J. M.: Supervised neural network
targeting and classification analysis of airborne EM, magnetic and gamma-ray
spectrometry data for mineral exploration, ASEG Extended Abstracts, 2015,
1–5, https://doi.org/10.1071/ASEG2015ab306, 2015.
Leggatt, P. B., Klinkert, P. S., and Hage, T. B.: The Spectrem airborne
electromagnetic system – Further developments, Geophysics, 65, 1976–1982,
2000.
Li, J., Liu, Y., Yin, C., Ren, X., and Su, Y.: Fast imaging of time-domain
airborne EM data using deep learning technology, Geophysics, 85, E163–E170, https://doi.org/10.1190/geo2019-0015.1, 2020.
Lin, F., Chen, K., Wang, X., Cao, H., Chen, D., and Chen, F.: Denoising stacked autoencoders for transient electromagnetic signal denoising, Nonlin. Processes Geophys., 26, 13–23, https://doi.org/10.5194/npg-26-13-2019, 2019.
Liu, W., Lü, Q., Yang, L., Lin, P., and Wang, Z.: Application of
Sample-Compressed Neural Network and Adaptive-Clustering Algorithm for
Magnetotelluric Inverse Modeling, IEEE Geoscience Remote Sensing Letters,
18, 1540–1544, https://doi.org/10.1109/LGRS.2020.3005796, 2020.
Maurer, H., Holliger, K., and Boerner, D. E.: Stochastic regularization:
Smoothness or similarity?, Geophys. Res. Lett., 25, 2889–2892,
1998.
Moghadas, D.: One-dimensional deep learning inversion of electromagnetic
induction data using convolutional neural network, Geophys. J.
Int., 222, 247–259, 2020.
Moghadas, D., Behroozmand, A. A., and Christiansen, A. V.: Soil electrical
conductivity imaging using a neural network-based forward solver: Applied to
large-scale Bayesian electromagnetic inversion, J. Appl.
Geophys., 176, 104012, https://doi.org/10.1016/j.jappgeo.2020.104012, 2020.
Møller, I., Jacobsen, B. H., and Christensen, N. B.: Rapid inversion of
2-D geoelectrical data by multichannel deconvolution, Geophysics, 66,
800–808, 2001.
Noh, K., Yoon, D., and Byun, J.: Imaging subsurface resistivity structure
from airborne electromagnetic induction data using deep neural network,
Explor. Geophys., 51, 214–220, 2020.
Pang, X., Zhou, Y., Wang, P., Lin, W., and Chang, V.: An innovative neural
network approach for stock market prediction, J. Supercomput.,
76, 2098–2118, 2020.
Poulton, M. M., Sternberg, B. K., and Glass, C. E.: Location of subsurface
targets in geophysical data using neural networks, Geophysics, 57,
1534–1544, 1992.
Puzyrev, V.: Deep learning electromagnetic inversion with convolutional
neural networks, Geophys. J. Int., 218, 817–832, 2019.
Puzyrev, V. and Swidinsky, A.: Inversion of 1D frequency-and time-domain
electromagnetic data with convolutional neural networks, Comput.
Geosci., 149, 104681, https://doi.org/10.1016/j.cageo.2020.104681, 2021.
Qin, S., Wang, Y., Tai, H.-M., Wang, H., Liao, X., and Fu, Z.: TEM apparent
resistivity imaging for grounding grid detection using artificial neural
network, IET Generation, Transmission, Distribution, 13, 3932–3940, https://doi.org/10.1049/iet-gtd.2018.6450, 2019.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A.: You only look once:
Unified, real-time object detection, in: Proceedings of the IEEE conference on
computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, 779–788, https://doi.org/10.1109/CVPR.2016.91, 2016.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., and
Carvalhais, N.: Deep learning and process understanding for data-driven
Earth system science, Nature, 566, 195–204, 2019.
Ren, S., He, K., Girshick, R., and Sun, J.: Faster r-cnn: Towards real-time
object detection with region proposal networks, Adv. Neur.
In., 1, 91–99, 2015.
Röth, G. and Tarantola, A.: Neural networks and inversion of seismic
data, J. Geophys. Res.-Sol. Ea., 99, 6753–6768, 1994.
Smith, R., Fountain, D., and Allard, M.: The MEGATEM fixed-wing transient EM
system applied to mineral exploration: a discovery case history, First
Break, 21, https://doi.org/10.3997/1365-2397.21.7.25570, 2003.
Smith, R. S.: Airborne electromagnetic methods: Applications to minerals,
water and hydrocarbon exploration, Canadian Society of Explortation
Geophysics, 35, 7–10, https://csegrecorder.com/articles/view/airborne-electromagnetic-methods-app-to-minerals-water-hydrocarbon-expl (last access: 16 March 2023), 2010.
Sørensen, K. I. and Auken, E.: SkyTEM-A new high-resolution helicopter
transient electromagnetic system, Explor. Geophys., 35, 191–199, 2004.
Tacher, L., Pomian-Srzednicki, I., and Parriaux, A.: Geological
uncertainties associated with 3-D subsurface models, Comput. Geosci., 32, 212–221, 2006.
Viezzoli, A., Christiansen, A. V., Auken, E., and Sørensen, K.: Quasi-3D
modeling of airborne TEM data by spatially constrained inversion,
Geophysics, 73, F105–F113, 2008.
Vignoli, G., Fiandaca, G., Christiansen, A. V., Kirkegaard, C., and Auken,
E.: Sharp spatially constrained inversion with applications to transient
electromagnetic data, Geophys. Prospect., 63, 243–255, 2015.
Wang, W., Zhang, M., Chen, G., Jagadish, H., Ooi, B. C., and Tan, K.-L.:
Database meets deep learning: Challenges and opportunities, ACM SIGMOD
Record, 45, 17–22, 2016.
Wu, S., Huang, Q., and Zhao, L.: Convolutional neural network inversion of
airborne transient electromagnetic data, Geophys. Prospect., 69,
1761–1772, 2021a.
Wu, S., Huang, Q., and Zhao, L.: De-noising of transient electromagnetic
data based on the long short-term memory-autoencoder, Geophys. J.
Int., 224, 669–681, 2021b.
Xue, G., Li, H., He, Y., Xue, J., and Wu, X.: Development of the Inversion
Method for Transient Electromagnetic Data, IEEE Access, 8, 146172–146181, https://doi.org/10.1109/ACCESS.2020.3013626,
2020.
Zhang, R., Liu, Y., and Sun, H.: Physics-guided convolutional neural network
(PhyCNN) for data-driven seismic response modeling, Eng. Struct.,
215, 110704, https://doi.org/10.1016/j.engstruct.2020.110704, 2020.
Zhang, Y. and Paulson, K.: Regularized hopfield neural networks and its
application to one-dimensional inverse problem of magnetotelluric
observations, Inverse Probl. Eng., 5, 33–53, 1997.
Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Bengio, C. L. Y., and
Courville, A.: Towards end-to-end speech recognition with deep convolutional
neural networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1701.02720, 10 January 2017.
Zhang, Z., Qi, C., and Asif, M. R.: Investigation on Projection Space Pairs
in Neighbor Embedding Algorithms, 2018 14th IEEE International Conference on Signal Processing (ICSP), Beijing, China, 12–16 August 2018, 125–128, https://doi.org/10.1109/ICSP.2018.8652441, 2018.
Zhdanov, M. S.: Inverse theory and applications in geophysics, 2nd edn., Elsevier, ISBN 978-0-444-62674-5,
https://doi.org/10.1016/C2012-0-03334-0,
2015.
Zhu, K.-G., Ma, M.-Y., Che, H.-W., Yang, E.-W., Ji, Y.-J., Yu, S.-B., and
Lin, J.: PC-based artificial neural network inversion for airborne
time-domain electromagnetic data, J. Appl. Geophys., 9, 1–8, https://doi.org/10.1007/s11770-012-0307-7,
2012.
Short summary
To apply a deep learning (DL) algorithm to electromagnetic (EM) methods, subsurface resistivity models and/or the corresponding EM responses are often required. To date, there are no standardized EM datasets, which hinders the progress and evolution of DL methods due to data inconsistency. Therefore, we present a large-scale physics-driven model database of geologically plausible and EM-resolvable subsurface models to incorporate consistency and reliability into DL applications for EM methods.
To apply a deep learning (DL) algorithm to electromagnetic (EM) methods, subsurface resistivity...
Altmetrics
Final-revised paper
Preprint