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

Abstract

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.

AEM in Norway: A Review of the Coverage, Applications and the State of Technology

“…Methods have been tested with promising results showing that real-time inversions of airborne TEM data using an ANN can provide at least equal quality inversions as standard 1-D deterministic methods. Here, an inversion could be completed in only 24 s using a standard laptop, compared with an inversion taking a few hours using standard inversion methods [71]. Such developments could significantly change typical survey conduction, as real-time data allows for real-time interpretation to a given survey.…”

Use of machine learning to estimate statistics of the posterior distribution in probabilistic inverse problems - an application to airborne EM data.

“…Others have used machine learning methods to directly solve the inverse problem by estimating a direct mapping from data to model parameters (Puzyrev & Swidinsky, 2019;Moghadas, 2020;Bai et al, 2020). These methods estimate a single model, as the deterministic methods, and typically without accounting for uncertainty on geophysical data, and uncertainty on the predicted model parameters.…”

1D Stochastic Inversion of Airborne Time-Domain Electromagnetic Data with Realistic Prior and Accounting for the Forward Modeling Error

“…Clearly, approaches based on 1D forward modeling are particularly convenient for their computational performances [40]. Recent strategies exploit the neural networks potential, allowing almost real-time inversions with no significant quality reductions [41]. In addition, in the attempt of retrieving, not merely the conductivity distribution, but, rather, immediately useful pieces of information about the targets and, at the same time, in the effort of supplying reliable assessment of the associated uncertainty, probabilistic petrophysical inversions are becoming more and more common [42].…”