Uncertainty Quantification of Machine Learning-Based Repeatability Enhancement for Time-lapse Seismic Data

The increasing exploitation of the subsurface has increased the demand for advanced time-lapse seismic monitoring technologies, which are critical for effective underground monitoring. Although machine learning-based data processing techniques have significantly improved data repeatability, research on quantifying the uncertainty in the predictions generated by these models remains insufficient. This study proposed a machine learning model for the quantitative evaluation of uncertainties in time-lapse seismic data. The aleatoric and epistemic uncertainties were independently quantified, providing a more detailed and objective assessment of prediction reliability and enabling the formulation of guidelines for additional data processing procedures to further enhance repeatability of the time-lapse seismic data. The model was trained and validated using synthetic data generated based on the Sleipner monitoring dataset and field data from Pohang, Korea. In synthetic experiments, low uncertainty values were obtained when time-lapse seismic differences were associated with actual subsurface changes, whereas elevated uncertainty was observed when the seismic differences were unrelated to true subsurface variations, confirming that the quantified uncertainties provide meaningful criteria for time-lapse seismic interpretation. In field data applications, regions exhibiting time-lapse differences consistently showed high uncertainty, indicating that the observed differences might not be attributed to temporal subsurface changes. Furthermore, a Geological Change Indicator (GCI) was introduced, defined as the relationship between the quantified uncertainties and data differences, which was used to successfully identify the presence or absence of subsurface changes.