Geomodelling of multi-scenario non-stationary reservoirs with enhanced GANSim

GANSim is a generative adversarial networks (GANs)-based direct conditional geomodelling framework. To extend GANSim to multi-scenario, non-stationary reservoir geomodelling, and to address its tendency to overlook single-grid well conditioning data that can cause local facies disconnections around wells, an enhanced GANSim framework is proposed. The effectiveness of the enhanced GANSim is validated using a 3D multi-scenario, non-stationary turbidite fan reservoir as an example. For reservoirs that may involve multiple geological scenarios, two GANSim geomodelling workflows are proposed: (1) training a comprehensive GANSim model that covers all possible geological scenarios; and (2) first performing geological scenario falsification and then training GANSim models only for the unfalsified scenarios. On this basis, a local discriminator architecture is designed to improve facies continuity around wells. The modelling results show that both workflows can generate non-stationary facies models that conform to expected geological patterns and honor conditioning data, and the facies discontinuity issue around wells is effectively resolved. Compared with multipoint geostatistical methods(SNESIM), GANSim exhibits superior capability in reproducing reservoir geological patterns and modelling efficiency. Although GANSim requires a longer training time, once training is completed, it can be applied to geomodelling reservoirs of arbitrary scale with similar geological structures, achieving modelling speeds approximately 1 000 times faster than SNESIM.