Using machine learning to interpret 3D airborne electromagnetic inversions

Abstract

Although 3D airborne electromagnetic inversions have improved greatly in recent years, the presence of smooth boundaries has often been a strong criticism. This smoothness can easily be remedied by applying different types of regularization and constraints to the model, but another approach is to learn what underlying structures or boundaries these smooth transitions represent. To perform this advanced inversion interpretation, we trained a machine learning algorithm known as VNet to identify the relationship between a true synthetic model and the resulting smooth 3D inversion model. By training on one section of the model and predicting on another, the algorithm was able to learn the general relationships required to intelligently sharpen the inversion model in the prediction area. The resulting images approximate the true synthetic model to a much closer degree compared to the original inversion model. The VNet was trained in two ways, one to predict a conductivity value for each pixel, and another to predict a classification unit for each pixel presuming the conductivity for each class is known. Each method performed similarly well with some minor differences, which gives the user some options depending on the scenario and how much a priori information is known. Overall this automatic interpretation technique worked well over a synthetic model, and future simulations will be run in order to make the method more robust and applicable for field scenarios.