Sensitivity analysis using physics-based machine learning: an example from surrogate modelling for magnetotellurics

Geophysical Journal International, vol. 242

Abstract

SUMMARY Geophysical simulations for complex subsurface structures and material distributions require the evaluation of partial differential equations by means of numerical methods. However, the mentioned high complexity often yields computationally very costly simulations, especially for electromagnetic (EM) and seismic methods. When used in the context of parameter estimation or inversion studies, this aspect severely limits the number of simulations that are affordable. However, especially for structured model analysis methods, such as global sensitivity analyses or inversions, often thousands to millions of forward simulation runs are required. To address this challenge, we propose utilizing a physics-based machine learning method, namely the non-intrusive reduced basis method, aiming at constructing low-dimensional surrogate models to significantly reduce the computational cost associated with the numerical forward model while preserving the physical principles.We demonstrate the effectiveness and benefits of the surrogate models using broad-band Magnetotelluric (MT) responses of a 2-D model that mimics a conceptual volcano-hosted geothermal system. Next to being a first such application, we also show how ML reduced basis method can be adapted to consistently treat complex-valued variables—an aspect that has been overlooked in previous studies. Additionally, reducing computation time by several orders of magnitude through the surrogate enables us to perform a global sensitivity analysis for MT applications. Despite additional insights, such an analysis has been normally deemed infeasible given the high computational burden. The methods developed here are presented in a generalized form, making this approach feasible for other electromagnetic techniques with a low-dimensional parameter space.

Authors 3

1. Denise Degen Aachen Computational Geoscience

   RWTH Aachen University · GFZ Helmholtz Centre for Geosciences · Technische Universität Darmstadt

   Affiliation as printed

   Computational Geoscience, Geothermics and Reservoir Geophysics (CG3), RWTH Aachen University , Mathieustraße 30, D-52074 Aachen ,

   Computational Geoscience, Geothermics and Reservoir Geophysics (CG3) , RWTH Aachen University, Mathieustraße 30, 52074 Aachen ,

   presently at: Institute of Applied Geosciences , TU Darmstadt, 64287 Darmstadt ,

   presently at: Section 4.5 Subsurface Process Modelling, GFZ Helmholtz Centre for Geosciences , 14473 Potsdam ,

2. Alexander V. Grayver

   University of Cologne

   Affiliation as printed

   Institute of Geophysics and Meteorology, University of Cologne , Albertus-Magnus-Platz, D-50923 Cologne ,

   Institute of Geophysics and Meteorology, University of Cologne , Albertus-Magnus-Platz, 50923 Cologne ,

3. Florian Wellmann corresponding Aachen Computational Geoscience

   RWTH Aachen University · Fraunhofer Research Institution for Energy Infrastructures and Geotechnologies IEG

   Affiliation as printed

   Computational Geoscience, Geothermics and Reservoir Geophysics (CG3), RWTH Aachen University , Mathieustraße 30, D-52074 Aachen ,

   Fraunhofer Research Institution for Energy Infrastructures and Geothermal Systems (IEG) , Am Hochschulcampus 1, D-44801 Bochum ,

   Computational Geoscience, Geothermics and Reservoir Geophysics (CG3) , RWTH Aachen University, Mathieustraße 30, 52074 Aachen ,

   Fraunhofer Research Institution for Energy Infrastructures and Geothermal Systems (IEG) , Am Hochschulcampus 1, 44801 Bochum ,