(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 coul...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/20/3440 |
| _version_ | 1797550432351944704 |
|---|---|
| author | Peng Bai Giulio Vignoli Andrea Viezzoli Jouni Nevalainen Giuseppina Vacca |
| author_facet | Peng Bai Giulio Vignoli Andrea Viezzoli Jouni Nevalainen Giuseppina Vacca |
| author_sort | Peng Bai |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T15:29:12Z |
| format | Article |
| id | doaj.art-0838238e75a64534982381857b8f60a0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:29:12Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0838238e75a64534982381857b8f60a02023-11-20T17:46:17ZengMDPI AGRemote Sensing2072-42922020-10-011220344010.3390/rs12203440(Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural NetworkPeng Bai0Giulio Vignoli1Andrea Viezzoli2Jouni Nevalainen3Giuseppina Vacca4Department of Civil and Environmental Engineering and Architecture, University of Cagliari, 09123 Cagliari, ItalyDepartment of Civil and Environmental Engineering and Architecture, University of Cagliari, 09123 Cagliari, ItalyAarhus Geophysics ApS, 8000 Aarhus, DenmarkOulu Mining School, University of Oulu, 90014 Oulu, FinlandDepartment of Civil and Environmental Engineering and Architecture, University of Cagliari, 09123 Cagliari, ItalyThe 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.https://www.mdpi.com/2072-4292/12/20/3440Neural networkinversionelectromagneticsairborne |
| spellingShingle | Peng Bai Giulio Vignoli Andrea Viezzoli Jouni Nevalainen Giuseppina Vacca (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network Remote Sensing Neural network inversion electromagnetics airborne |
| title | (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network |
| title_full | (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network |
| title_fullStr | (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network |
| title_full_unstemmed | (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network |
| title_short | (Quasi-)Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network |
| title_sort | quasi real time inversion of airborne time domain electromagnetic data via artificial neural network |
| topic | Neural network inversion electromagnetics airborne |
| url | https://www.mdpi.com/2072-4292/12/20/3440 |
| work_keys_str_mv | AT pengbai quasirealtimeinversionofairbornetimedomainelectromagneticdataviaartificialneuralnetwork AT giuliovignoli quasirealtimeinversionofairbornetimedomainelectromagneticdataviaartificialneuralnetwork AT andreaviezzoli quasirealtimeinversionofairbornetimedomainelectromagneticdataviaartificialneuralnetwork AT jouninevalainen quasirealtimeinversionofairbornetimedomainelectromagneticdataviaartificialneuralnetwork AT giuseppinavacca quasirealtimeinversionofairbornetimedomainelectromagneticdataviaartificialneuralnetwork |