Reservoir and production engineers value accurate, timely data on layer-level production and injection. In practice however, production is usually measured only at the well level due to difficulty, expense, and production disruption of running flowmeters, and layer-level injection allocation is currently measured using expensive tracers or other inaccurate and time consuming processes. Injection rates, production rates, and connectivity are dynamic and need to be estimated continuously, otherwise leading to out-of-date analysis and results.
Using state-of-the-art machine learning and data assimilation approaches with well-known physical models, Tachyus’ Subsurface Back Allocation continuously calculates layer-level production rates and dynamic injection allocations that match all measured historical injection and production data. The workflow runs very fast and can be powered by the cloud or local computing. Tachyus’ Subsurface Back Allocation is the equivalent of running tracers and flowmeters in every well during the whole history of the field.