Dynamic Reservoir Modeling of the Utah FORGE Enhanced Geothermal Project Using Fast Marching Method

Abstract The Utah FORGE project is the largest Enhanced Geothermal System (EGS) demonstration site for geothermal energy production in low permeability formation with limited subsurface water availability. The FORGE project encompasses hydraulic stimulation followed by fluid circulation test. High-resolution EGS simulations are computationally intensive because they involve non-isothermal flow within hard rocks containing hydraulic and natural fractures. This study involves the development and history-matching of a reservoir model at the Utah FORGE site based on a discrete fracture network model and dynamic data from circulation tests for assessment of long-term performance and sustainability of the geothermal project. We propose a novel Fast-Marching-Method (FMM) based accelerated dynamic reservoir modeling approach enabling orders of magnitude faster simulation and demonstrate its power and efficacy through application at the Utah FORGE site. The reservoir dynamic model for the Utah FORGE site is developed based on a Discrete Fracture Network (DFN) model constructed using well logs and microseismic data. A month-long circulation test results are used as observational data for history matching and model updating. To mitigate the high computational cost from repeated simulations during history matching, we utilize the Fast Marching Method (FMM)-based simulation that transforms 3D fine-scale simulations into equivalent multi-resolution simulations using Diffusive Time of Flight (DTOF) as spatial coordinate. The DTOF represents the propagation time of the ‘pressure front’ and is computed in seconds by solving the Eikonal equation with FMM. Using the DTOF contours, the 3D fine-scale model is converted into a coarse multi-resolution model while preserving the 3D fine-scale near-wellbore region to maintain the hydraulic fracture fidelity and leading to the orders of magnitude acceleration in simulation time. The FMM-based multi-resolution simulation is applied to the Utah FORGE model and compared with 3D fine-scale simulation using a commercial simulator. The proposed approach is shown to speed up the simulation by more than an order of magnitude (10 to 20 times) with minimal loss of accuracy. Using the fast simulation model, a multi-objective genetic algorithm is applied to calibrate the reservoir model using bottomhole pressure and fluid temperature obtained during the circulation test. The calibrated reservoir model is used to predict long-term geothermal performance for 10 years at the Utah FORGE site, providing estimates of production rates, fluid temperatures and thermal power output.