Browsing by Author "Selveindran, Anand"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
Item An Integrated Petroleum Reservoir Management (MDT) of a Mature Oilfield(2017) Selveindran, Anand; Simone, Alessandra; Chen, J.; Joslin, B.; Narayan, R.; Rendon, C.; Sharma, P.Item An Investigation into the Relative Effectiveness of CO2 and Hydrocarbon Gas as an EOR Injectant for a Marginal Onshore USA Sandstone Reservoir(2017-08) Selveindran, Anand; Kostarelos, Konstantinos; Palayangoda, Sujeewa; Hatzignatiou, Dimitrios G.CO2 injection is a widely employed and highly successful method for Enhanced Oil Recovery (EOR) onshore USA. Despite the benefits, there are significant challenges to CO2 injection, including corrosion and adverse rock–mineral interactions. Furthermore, CO2 supply is not always easily available, and gas transportation costs may be prohibitive especially for marginal assets. The shale boom has flooded the market with natural gas, with an accompanying drop in gas prices. The relative abundance of hydrocarbon gas warrants investigation into the viability of using this gas as a CO2 substitute. Coreflooding and slimtube experiments were carried out to compare the effectiveness of supercritical hydrocarbon gas and CO2 injection for enhanced oil recovery. These experiments were used to calibrate a numerical simulation model. Different blends of hydrocarbon gasses were assessed as EOR injectants resulting in the proposal of a gas mixture with displacement efficiencies comparable to CO2.Item Machine Learning Assisted Reservoir Management for Injection Projects(2021-12) Selveindran, Anand; Thakur, Ganesh C.; Farouq Ali, S. M.; Aminzadeh, Fred; Lee, Kyung Jae; Wesley, AvinashReservoir management is critical for optimal hydrocarbon reservoir performance. A key component of reservoir management is decision making utilizing numerical reservoir models. One downside of these models is the large computational footprint for development and deployment. Recent developments in machine learning provide technologies that can augment reservoir management workflows. In this work, machine learning algorithms are used to optimize selection of injector well location, perform fluid production prediction and optimize well controls. Selection of optimized water and gas injection well locations is a key challenge in secondary and tertiary recovery projects. Traditional approaches using numerical simulation require a high number of simulation runs with optimization algorithms. This is further complicated if there is geological uncertainty (e.g., multiple geological models are required to capture the uncertainty range). An alternative approach is proposed, using machine learning algorithms trained on a geological ensemble. Well level aggregations are proposed to efficiently reduce the number of injector well location evaluations. Proxies were trained with several target variables including oil recovery and CO2 storage. These proxies provide rapid evaluations of injector locations within seconds at accuracies between 0.94 - 0.98 (R2 score comparing machine learning proxy predictions and numerical simulation results). Blind tests with different geological realizations yielded results comparable to numerical simulation. Posterior sampling was used to determine optimal injector locations across a large geomodel ensemble. To predict time varying production without numerical simulation, deep learning models including a Convolutional Neural Network (CNN) were trained with well level data. These algorithms successfully predicted production from water and miscible flooded patterns. Models trained on several wells could predict production from a neighbor well within the same pattern area. Finally, a Graph Neural Network (GNN) proxy was used within a Closed Loop Reservoir Management (CLRM) workflow to optimize oil production of a waterflood. Kriging was used to initialize the adjacency matrix, resulting in improved network performance. The GNN proxy was able to perform monthly optimization over a period of one year within eight minutes, compared to 6 hours using traditional simulation.