Time-Dependent Neural Network Based Proxy Modeling of SAGD Process

Abstract

The present study proposes a novel single-layer Neural Network proxy to efficiently predict the production performance of oil reservoirs from a limited number of reservoir simulations. The proposed model is shown to provide powerful means for learning reservoir's dynamics from input-output relationships that is defined by multiple combinations of inputs and controls. A SAGD case with 3 well pairs is used to illustrate the approach. The workflow is organized as follows:1. Different numbers (from 30 to 200) of direct numerical simulations are conducted for the time horizon of ten years for the given reservoir. These simulations correspond to different combinations of the operational parameters sampled according to the Latin Hypercube Experimental Design (LHD). 2. The time series of the simulated entire field production performance (particularly: Cumulative Oil Production, cumulative SOR, Oil Recovery Factor, and Oil Production Rate) are used to build the corresponding Radial Basis Function (RBF) Network proxy model which represents production performance as objective functions of the operational parameters and time. The nodal Radial Functions of the Network are defined to exactly match the simulator's training outputs. The big advantage of this model is a combination of low computational complexity with high prediction accuracy. 3. The proxy model is then used to predict the production data for the given reservoir for any time period (within 10 training years) and any combination of the operational parameters. 4. The predicted data are compared with the actual simulation results for the same time period and the same combinations of the operational parameters to evaluate the prediction quality. It is shown that the proposed RBF proxy model can be used as a light version of simulator to estimate the production results for any combination of operational parameters and time horizon with much less computational efforts. The proposed approach is shown to provide a very efficient forecasting mechanism for the reservoir considered. The difference between the predicted and actual data could be as low as a few percent for the majority of the operational parameters depending on the number of simulations used to train the RBF model. In general, the accuracy of the proxy model increases with the number of training simulations.

Integration of machine learning and data analysis for the SAGD production performance with infill wells

“…Similar to the organization of a human brain, ANNs are formed by numerous neurons or nodes connected with associated weights and biases, containing an input layer, an output layer, and several hidden layers between the input layer and the output layer, as shown in Figure 7. The ANN algorithm was commonly utilized in a SAGD process in previous studies, such as predicting the cumulative oil production time series, [34] predicting recovery factors, [25] predicting cumulative steam-oil ratios, [24] and predicting net present values. [26]…”

“…Those studies paid much attention to the impact of reservoir heterogeneity, [12][13][14][15][16][17][18] optimization, [19][20][21][22][23] production performance prediction, [24][25][26][27][28] and clustering, [29][30][31] which have significantly improved the ability to predict a SAGD process. However, studies of a data-driven model applied to infill wells in a SAGD process are still rare.…”

Predicting the Dynamic Parameters of Multiphase Flow in CFD (Dam-Break Simulation) Using Artificial Intelligence-(Cascading Deployment)

“…• The transport equation with the following form is used to calculate the relative volume fraction in each cell: ∂γ ∂t + ∇•(γU) = 0 (10) By adding the artificial compression term into this equation, necessary compression of the surface is calculated:…”

Investigation of Properties Alternation during Super-Critical CO2 Injection in Shale

“…The boom of Bakken formation in North America is limited by the effective recovery method even with the recent advancement of hydraulic fracturing and horizontal drilling technology utilization [1]. Since then, the CO 2 flooding method has been proposed as the potential way to increase the recovery factor for the unconventional shale reservoir in the Bakken formation, especially combined with the advanced water-alternating-gas (CO 2 -WAG) and CO 2 huff and puff technologies [2][3][4][5][6][7]. Meanwhile, the injection of the supercritical CO 2 into the shale and coal bed methane reservoir would assist the emission reduction of greenhouse gases [8][9][10].…”