Keynote 5: Informing neural networks with fluid flow consistent property correlations: A 4D seismic inversion application

In this work we tackle the challenge of estimating reservoir property variations during a period of production, directly from 4D seismic data. We employ a deep neural network to invert 4D seismic amplitude maps to the simultaneous changes in pressure, water and gas saturations. The method is applied to a real field data case, where, as is common in such applications, the data measured at the wells is insufficient for training neural networks, thus, the network is trained on synthetic data. Training on synthetic data offers much freedom in designing a training dataset, therefore, it is important to understand the impact of the distribution of data in training datasets on the inversion results. We perform a study testing four different approaches to populating a training dataset, showing the impact of including physics-based constraints on the reservoir property distribution. Using the results of a reservoir simulation model to populate our training datasets we demonstrate the benefits of constraining training samples to fluid flow consistent combinations in the dynamic reservoir property domain, uncovering the potential of deep neural networks for 4D seismic inversion, in a situation where no appropriate measured data is present.