Seismic reservoir property estimation and uncertainty quantification with statistical learning techniques
Anshuman Pradhan
Seismic reservoir characterization has conventionally necessitated estimation of subsurface elastic properties. Inverse methods employed to such an end generally run into theoretical, numerical and computational complexities given the high dimensional nature of seismic data. The research question we pose: is such a step warranted when the end goal is reservoir characterization? We employ statistical learning techniques to learn the implicit relationship between seismic data and reservoir properties. Such learning is subsequently exploited for property estimation and uncertainty quantification without an explicit seismic inversion step. Applications include reservoir net-to-gross estimation, geo-modeling parameter estimation and reservoir facies estimation from seismic data.