A multidimensional AI-trained correction to the 1D approximate model for Airborne TDEM sensing

Abstract

The computational resources required to solve the full 3D inversion of time-domain electromagnetic data are immense. To overcome the time-consuming 3D simulations, we construct a surrogate model, more precisely, a data-driven statistical model to replace the 3D simulations. It is trained on 3D data and predicts the approximate output much faster. We construct a surrogate model that predicts the discrepancy between a 1D subsurface model and a deviation of the 1D assumption. The latter response is fastly computable with a semi-analytical 1D forward model. We exemplify the approach on a two-layered case. The results are encouraging even with few training samples. Given the computational cost related to the 3D simulations, there are limitations in the number of training samples that can be generated. In addition, certain applications require a wide range of parameters to be sampled, such as the electrical conductivity parameters in a saltwater intrusion case. The challenge of this work is achieving the best possible accuracy with only a few thousand samples. We propose to view the performance in terms of learning gain, representing the gain from the surrogate model whilst still acknowledging a residual discrepancy. Our works open new avenues for effectively simulating 3D TDEM data.

References in corpus (5)

• Properties of principal component methods for functional and longitudinal data analysis
• A framework for simulation and inversion in electromagnetics
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Flexible quasi-2D inversion of time-domain AEM data, using a wavelet-based complexity measure
• Novel Airborne EM Image Appraisal Tool for Imperfect Forward Modelling

Cited by in corpus (1)

• Joining simplified physics models with coarse grids to speed-up intractable 3D time-domain simulations