Discrete Well Affinity Data-Driven Proxy Model for Production Forecast

Summary A physics-based data-driven model is proposed for forecasting of subsurface energy production. The fully relies on production data and does not require any in-depth knowledge reservoir geology or governing physics. In the approach, we use Delft Advanced Reservoir Terra Simulator (DARTS) as a workhorse simulation. DARTS uses an operator-based linearization technique that exploits abstract interpretation physics benefiting computational performance. trained to fit increasing fidelity forecast reflecting significant changes in dynamics over its history. examined validated both synthetic real field data. We demonstrate developed approach capable providing accurate reliable daily basis, even if exact geological information available.