Physically Guided Deep Unsupervised Inversion for 1D Magnetotelluric Models

TL;DR

This paper introduces a physics-guided deep unsupervised inversion method for 1D magnetotelluric models that directly utilizes observed data and a differentiable forward operator, improving accuracy over traditional and supervised deep learning methods.

Contribution

The work presents a novel physics-guided unsupervised deep learning approach for MT inversion that eliminates the need for large labeled datasets and enhances model accuracy.

Findings

Resistivity models are more accurate than traditional methods.

Method works effectively with field and synthetic data.

Improves inversion efficiency and accuracy.

Abstract

The global demand for unconventional energy sources such as geothermal energy and white hydrogen requires new exploration techniques for precise subsurface structure characterization and potential reservoir identification. The Magnetotelluric (MT) method is crucial for these tasks, providing critical information on the distribution of subsurface electrical resistivity at depths ranging from hundreds to thousands of meters. However, traditional iterative algorithm-based inversion methods require the adjustment of multiple parameters, demanding time-consuming and exhaustive tuning processes to achieve proper cost function minimization. Recent advances have incorporated deep learning algorithms for MT inversion, primarily based on supervised learning, and large labeled datasets are needed for training. This work utilizes TensorFlow operations to create a differentiable forward MT operator, leveraging its automatic differentiation capability. Moreover, instead of solving for the subsurface model directly, as classical algorithms perform, this paper presents a new deep unsupervised inversion algorithm guided by physics to estimate 1D MT models. Instead of using datasets with the observed data and their respective model as labels during training, our method employs a differentiable modeling operator that physically guides the cost function minimization, making the proposed method solely dependent on observed data. Therefore, the optimization algorithm updates the network weights to minimize the data misfit. We test the proposed method with field and synthetic data at different acquisition frequencies, demonstrating that the resistivity models obtained are more accurate than those calculated using other techniques.