Fast History Matching and Optimization Using a Novel Physics-Based Data-Driven Flow Network Model: An Application to a Steamflood Sector Model

Abstract

AbstractFull-fidelity models can be computationally expensive during history matching (HM) and optimization since these problems typically require hundreds of simulations. Previously, we have implemented a physics-based data-driven flow network model GPSNet that serves as a surrogate without the need to build the 3D full-fidelity model. In this paper, GPSNet is upgraded to GPSNet-2D to better suit the thermal process and it successfully enables a rapid HM and optimization for a steamflood sector model.The reservoir is discretized into a series of 2D connections (x-z planes) between well completions. These connections capture the main areal/vertical flow paths and the grid properties of each connection are interpreted with historical data. Steam segregation and heat loss are included to better represent the subsurface physics. When simulating GPSNet-2D through a commercial simulator, an equivalent 3D Cartesian model is designed where vertical slices correspond to the inter-well connection planes. Thereafter, an iterative HM is conducted using Ensemble Smoother with Multiple Data Assimilation (ES-MDA). The best-matched model is then used for steam injector control optimization.The GPSNet-2D model is first validated through a synthetic steamflood case. History matching result shows that the GPSNet-2D model not only aligns closely to field-scale volumetric data but also yields good well-level matches, including bottom hole pressure/temperature and phase rates. Then, it is successfully applied to steamflood HM and optimization for a 36-well sector of a heavy oil field in the San Joaquin Valley (SJV) in North American. Again, the calibrated GPSNet-2D model demonstrates its capability and reliability of generating accurate field-scale match results and reasonable matches for most of the wells. For well control optimization, we select the P50 model to boost net present value (NPV) under well constraints. The integration with a commercial simulator in GPSNet-2D provides flexibility to account for complex physics in the thermal recovery processes, such as steam segregation near injectors, fast steam breakthroughs at producers, and heat loss to the overburden/underburden formations. Unlike traditional simulation that relies on a detailed characterization of geological models, the GPSNet-2D model only requires well volumetric production/injection data and its approximate trajectory and can be generated and updated rapidly. In addition, GPSNet-2D also runs much faster (minutes) than a full-fidelity thermal model due to the much fewer gridblocks used in the model.To our knowledge, this is the first time a physics-based data-driven network model integrated with a commercial simulator is demonstrated via a field steamflood case. Unlike approaches developed with analytic/empirical solutions or research simulators, the use of a commercial simulator makes it possible to extend flow network modeling to simulate EOR processes more realistically. It serves as an ideal surrogate model for both fast & reliable decision-making in reservoir management.