(Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network

The possibility to have results very quickly after, or even during, the collection of electromagnetic data would be important, not only for quality check purposes, but also for adjusting the location of the proposed flight lines during an airborne time-domain acquisition. This kind of readiness could have a large impact in terms of optimization of the Value of Information of the measurements to be acquired. In addition, the importance of having fast tools for retrieving resistivity models from airborne time-domain data is demonstrated by the fact that Conductivity-Depth Imaging methodologies are still the standard in mineral exploration. In fact, they are extremely computationally efficient, and, at the same time, they preserve a very high lateral resolution. For these reasons, they are often preferred to inversion strategies even if the latter approaches are generally more accurate in terms of proper reconstruction of the depth of the targets and of reliable retrieval of true resistivity values of the subsurface. In this research, we discuss a novel approach, based on neural network techniques, capable of retrieving resistivity models with a quality comparable with the inversion strategy, but in a fraction of the time. We demonstrate the advantages of the proposed novel approach on synthetic and field datasets.

[1]  R. Herrington,et al.  The Sakatti Cu-Ni-PGE Sulfide Deposit in Northern Finland , 2015 .

[2]  G. Street,et al.  Regional TEMPEST survey in north-east Namibia , 2015 .

[3]  The Impact on Geological and Hydrogeological Mapping Results of Moving from Ground to Airborne TEM , 2014 .

[4]  Henrique Lorenzo,et al.  GPR Signal Characterization for Automated Landmine and UXO Detection Based on Machine Learning Techniques , 2014, Remote. Sens..

[5]  M. Zhdanov,et al.  Spectral Induced Polarization Survey with Distributed Array System for Mineral Exploration: Case Study in Saudi Arabia , 2020, Minerals.

[6]  Zhen Zhu,et al.  Optimized Approximation Algorithm in Neural Networks Without Overfitting , 2008, IEEE Transactions on Neural Networks.

[7]  Deva Prasad Ghosh,et al.  Optimizing Acquisition Geometry in Shallow Gas Cloud Using Particle Swarm Optimization Approach , 2017, Int. J. Comput. Intell. Syst..

[8]  T. Cudahy Mineral Mapping for Exploration: An Australian Journey of Evolving Spectral Sensing Technologies and Industry Collaboration , 2016 .

[9]  Andrea Viezzoli,et al.  Spatially constrained inversion for quasi 3D modelling of airborne electromagnetic data – an application for environmental assessment in the Lower Murray Region of South Australia , 2009 .

[10]  K. Kwan,et al.  AeroTEM characteristics and field results , 2001 .

[11]  Michel Allard,et al.  The MEGATEM fixed-wing transient EM system applied to mineral exploration: a discovery case history , 2003 .

[12]  Jungho Im,et al.  A Novel Framework of Detecting Convective Initiation Combining Automated Sampling, Machine Learning, and Repeated Model Tuning from Geostationary Satellite Data , 2019, Remote. Sens..

[13]  A. Christiansen,et al.  Artificial neural networks for removal of couplings in airborne transient electromagnetic data , 2016 .

[14]  M. Kubát An Introduction to Machine Learning , 2017, Springer International Publishing.

[15]  Esben Auken,et al.  SkyTEM–a New High-resolution Helicopter Transient Electromagnetic System , 2004 .

[16]  Jakob Juul Larsen,et al.  Extraction and use of noise models from transient electromagnetic data , 2018 .

[17]  G. Martelet,et al.  Processing methodology for regional AEM surveys and local implications , 2020, Exploration Geophysics.

[18]  James Macnae,et al.  Fast AEM data processing and inversion , 1998 .

[19]  M. Zhdanov,et al.  Large-Scale 3D Modeling and Inversion of Multiphysics Airborne Geophysical Data: A Case Study from the Arabian Shield, Saudi Arabia , 2018, Minerals.

[20]  Esben Auken,et al.  Sharp spatially constrained inversion with applications to transient electromagnetic data , 2015 .

[21]  Rong Liu,et al.  An Efficient Footprint-Guided Compact Finite Element Algorithm for 3-D Airborne Electromagnetic Modeling , 2019, IEEE Geoscience and Remote Sensing Letters.

[22]  Greg Hodges,et al.  MULTIPULSE – high resolution and high power in one TDEM system , 2015 .

[23]  P. B. Leggatt,et al.  The Spectrem airborne electromagnetic system—Further developments , 2000 .

[24]  Richard S. Smith,et al.  The moments of the impulse response: A new paradigm for the interpretation of transient electromagnetic data , 2002 .

[25]  Tapan Mukerji,et al.  Value of information of seismic amplitude and CSEM resistivity , 2008 .

[26]  Bernhard Siemon,et al.  Airborne Electromagnetic and Radiometric Peat Thickness Mapping of a Bog in Northwest Germany (Ahlen-Falkenberger Moor) , 2020, Remote. Sens..

[27]  David G. Stork,et al.  Pattern Classification , 1973 .

[28]  Jiwei Liu,et al.  Seismic Waveform Classification and First-Break Picking Using Convolution Neural Networks , 2018, IEEE Geoscience and Remote Sensing Letters.

[29]  Anders Vest Christiansen,et al.  A method for cognitive 3D geological voxel modelling of AEM data , 2013, Bulletin of Engineering Geology and the Environment.

[30]  Patrick P. K. Chan,et al.  Adversarial Feature Selection Against Evasion Attacks , 2016, IEEE Transactions on Cybernetics.

[31]  Michael S. Zhdanov,et al.  3D inversion of airborne electromagnetic data , 2012 .

[32]  Esben Auken,et al.  Layered and laterally constrained 2D inversion of resistivity data , 2004 .

[33]  E. Auken,et al.  Combining ground-based and airborne EM through Artificial Neural Networks for modelling glacial till under saline groundwater conditions , 2012 .

[34]  Catalin Iulian Pruncu,et al.  Machine Learning Modelling and Feature Engineering in Seismology Experiment , 2020, Sensors.

[35]  G. Vignoli,et al.  New regional stratigraphic insights from a 3D geological model of the Nasia sub-basin, Ghana, developed for hydrogeological purposes and based on reprocessed B-field data originally collected for mineral exploration , 2019, Solid Earth.

[36]  Andrew Curtis,et al.  Optimal design of focused experiments and surveys , 1999 .

[37]  Andrew Binley,et al.  An overview of a highly versatile forward and stable inverse algorithm for airborne, ground-based and borehole electromagnetic and electric data , 2015 .

[38]  Fabio Roli,et al.  Adversarial Biometric Recognition : A review on biometric system security from the adversarial machine-learning perspective , 2015, IEEE Signal Processing Magazine.

[39]  K. Witherly The quest for the Holy Grail in mining geophysics: A review of the development and application of airborne EM systems over the last 50 years , 2000 .

[40]  Mirko van der Baan,et al.  Neural networks in geophysical applications , 2000 .

[41]  Andrea Viezzoli,et al.  Examples of Improved Inversion of Different Airborne Electromagnetic Datasets Via Sharp Regularization , 2017 .

[42]  D. C. Fraser Resistivity mapping with an airborne multicoil electromagnetic system , 1978 .

[43]  E. V. Karshakov,et al.  Combined Frequency Domain and Time Domain Airborne Data for Environmental and Engineering Challenges , 2017 .

[44]  P. Wolfgram,et al.  Conductivity-depth transform of GEOTEM data , 1995 .

[45]  Rita Deiana,et al.  Focused inversion of vertical radar profile (VRP) traveltime data , 2012 .

[46]  J. Legault,et al.  VTEM airborne EM, aeromagnetic and gamma-ray spectrometric data over the Cerro Quema high sulphidation epithermal gold deposits, Panama , 2015 .

[47]  F. Jørgensen,et al.  3D geological modelling of a complex buried-valley network delineated from borehole and AEM data , 2015 .

[48]  A. P. Annan,et al.  An application of airborne GEOTEM* in Australian conditions , 1991 .

[49]  Mauricio D. Sacchi,et al.  Optimization for sparse acquisition , 2015 .

[50]  Tomasz Rymarczyk,et al.  A Non-Destructive System Based on Electrical Tomography and Machine Learning to Analyze the Moisture of Buildings , 2018, Sensors.

[51]  Helicopter EM (ZTEM–VTEM) survey results over the Nuqrah copper–lead–zinc–gold SEDEX massive sulphide deposit in the Western Arabian Shield, Kingdom of Saudi Arabia , 2015 .

[52]  R. Gloaguen,et al.  Development of Sustainable Test Sites for Mineral Exploration and Knowledge Spillover for Industry , 2020, Sustainability.

[53]  David M. Fountain Airborne electromagnetic systems - 50 years of development , 1998 .

[54]  A. Christiansen,et al.  A review of helicopter‐borne electromagnetic methods for groundwater exploration , 2009 .

[55]  J. Legault,et al.  VTEM airborne EM, aeromagnetic and gamma-ray spectrometric data over the Cerro Quema high sulphidation epithermal gold deposits, Panama , 2015 .

[56]  J. Macnae Improving the accuracy of shallow depth determinations in AEM sounding , 2003 .

[57]  Haoping Huang,et al.  Conductivity-depth imaging of helicopter-borne TEM data based on a pseudolayer half-space model , 2008 .

[58]  Shigeo Abe DrEng Pattern Classification , 2001, Springer London.

[59]  G. Vignoli,et al.  New regional stratigraphic insights from a 3D geological model of the Nasia sub-basin, Ghana, developed for hydrogeological purposes and based on reprocessed B-field data originally collected for mineral exploration , 2020, 2011.03608.

[60]  James Macnae,et al.  Airborne electromagnetic modelling options and their consequences in target definition , 2015 .