Gaussian Processes enabled model calibration in the context of deep geological disposal

TL;DR

This paper introduces a Gaussian Process-based surrogate modeling approach to efficiently calibrate and analyze the mechanical behavior of emplacement drifts in deep geological repositories, significantly reducing computational costs.

Contribution

It presents a novel application of Gaussian Processes for surrogate modeling in the context of geological disposal, enabling faster calibration and sensitivity analysis.

Findings

Few key parameters suffice for accurate in-situ condition modeling.

The surrogate model reduces computational time for simulations.

Enhanced interpretation of monitoring data for safety assessment.

Abstract

Deep geological repositories are critical for the long-term storage of hazardous materials, where understanding the mechanical behavior of emplacement drifts is essential for safety assurance. This study presents a surrogate modeling approach for the mechanical response of emplacement drifts in rock salt formations, utilizing Gaussian Processes (GPs). The surrogate model serves as an efficient substitute for high-fidelity mechanical simulations in many-query scenarios, including time-dependent sensitivity analyses and calibration tasks. By significantly reducing computational demands, this approach facilitates faster design iterations and enhances the interpretation of monitoring data. The findings indicate that only a few key parameters are sufficient to accurately reflect in-situ conditions in complex rock salt models. Identifying these parameters is crucial for ensuring the reliability and safety of deep geological disposal systems.