Efficient proxy for Time-Lapse Seismic ForwardModeling using U-Net Encoder-Decoder Approach

Abstract

The time-lapse seismic (4D seismic) forward modeling provides crucial data for calibrating reservoir models through the reservoir data assimilation method. Unfortunately, conventional 4D seismic forward modeling methodology is time-expensive and entails significant computational resource consumption. To address these drawbacks, in this work, our goal is to develop a proxy model for the 4D seismic forward modeling using a class of machine learning algorithm named U-Net encoder-decoder. We applied the developed proxy model to a benchmark carbonate reservoir using an ensemble of reservoir simulation models from UNISIM IV (a synthetic benchmark based on real data of a Brazilian pre-salt field). Moreover, we aim to introduce seminal strategies for interpreting the proposed proxy model operation, its outputs, and possible correlations between input and output variables. To achieve this, we trained and tested two versions of U-net-based models and applied methods for explainable AI, such as Grad-CAM and Forward Feature Selection. The experiments showed good results when applied to the test dataset. The R-squared values were in the range of 0.7 to 0.9, showing the efficiency of the proxy model to replace the 4D seismic forward modeling. Additionally, the qualitative analysis helped us identify which input properties and regions of the reservoir are more relevant for the model's inference. These results are a valuable preliminary step toward a robust, explainable machine learning-based proxy forward modeling.