Error-aware surrogate modeling for accelerated three-dimensional probabilistic inversion of controlled-source electromagnetic data

We present a workflow for three-dimensional probabilistic inversion of controlled-source electromagnetic data that effectively balances accuracy and computational efficiency. The approach mitigates the high computational cost of forward modeling by employing a surrogate model derived from a mesh coarsening strategy. To account for the modeling errors inherent to this approximation, we implement a deep-learning–based parametric correction, enabling the joint inversion of correction and subsurface physical parameters. We use a synthetic marine experiment to verify that the proposed method recovers the true subsurface parameters. The inclusion of an error correction significantly improves predictive accuracy and reduces computation time compared to conventional forward modeling. Application to a real world marine data acquisition further illustrates the capability of the method to estimate the geometry and location of an oil reservoir. Our results highlight the potential of deep-learning–assisted surrogate modeling as a practical tool for accelerating the probabilistic inversion.