🤖 AI Summary
This study addresses the challenge of simultaneously achieving uncertainty quantification and physical constraint enforcement in magnetotelluric inversion. To this end, we propose a Neural Physics Inference (NPI) framework that pioneers the coupling of an Ensemble Conditional Gaussian Process (EnsCGP) with constrained residual learning, incorporating a physics-constrained objective function to establish a modular, uncertainty-aware inversion paradigm. Crucially, this mechanism ensures the propagation of ensemble uncertainty information throughout the entire estimation process. Evaluations on both synthetic datasets and field measurements from the Gabbs Valley geothermal area demonstrate that the proposed method significantly reduces inversion errors while maintaining robust uncertainty assessment capabilities.
📝 Abstract
We present the Neuro-Physical Inverter (NPI), a modular, uncertainty-aware framework for geophysical inversion that couples ensemble-based conditioning with constrained residual learning, demonstrated in the 1D magnetotelluric (MT) setting as a controlled testbed. The framework operates in two stages. An Ensemble-Conditional Gaussian Process (EnsCGP) conditions a prior ensemble of resistivity models on the observed response, producing a physically admissible reference ensemble. A residual-learning neural network then predicts targeted corrections to this reference, trained on synthetic data and fine-tuned per station for field application through a physics-coupled objective. Because an ensemble is conditioned, refined, and propagated through both stages, every estimate carries an associated ensemble spread. Synthetic experiments show that NPI systematically reduces ensemble-mean error without destabilizing the ensemble. Applied to broadband MT data from the Gabbs Valley geothermal region (Nevada, USA), NPI reduces the across-station mean misfit over the mid-period band while retaining comparable ensemble spread. The propagated ensemble yields a factor of uncertainty that serves as an operational measure of constraint within the assumed model class. Both stages are dimension-agnostic in formulation, and the design principles established here are intended to scale to higher-dimensional parameterizations.