ABSTRACT
Seismic inversion uses observed data, such as well-logging and seismic data, to infer rock parameters. However, it still suffers from nonunique solutions. The nonuniqueness increases when extrapolating away from the well location. To mitigate this effect, we incorporate geologic information into a deep-learning (DL) framework in the form of generated probabilistic labels. We transform geologic information into reservoir heterogeneity (RH) weights and geologic pattern constraint (GPC) weights to generate probabilistic labels. The RH weights are used to capture the variability in accuracy during the spatial extrapolation of well data. The RH weights are used to balance the constraint weights between well and seismic data in the DL model. The GPC weights are used to characterize the changes in geologic patterns from well locations to nonwell locations. Based on variations in local prestack seismic waveforms, the DL model learns extrapolation patterns of well data with similar geologic patterns. By combining the rock parameters derived from well logs with these two types of weights, we can generate a series of probability labels. Two types of geologic information and well-logging data are deeply integrated into a supervised 2D residual block UNet framework. In this way, we develop a novel DL-based prestack multitrace seismic inversion method. We validate our method on a 3D synthetic model and a 3D field data set. The results indicate that our method exhibits great potential for characterizing the spatial variation in subsurface rocks and outperforms traditional DL methods.