Data-driven Performance Indicators for SAGD Process of Oil Sands Using Support Vector Regression Machine with Parameter Optimization Algorithm

Abstract

Abstract The rapid and accurate forecasting of performance in the Steam-Assisted Gravity Drainage (SAGD) process for oil sands is crucial for the reasonable design of the development plan. This study aims to address this need by presenting novel data-driven performance indicators based on support vector regression (SVR), a machine learning method that complements the traditional physics-driven approach. During the SAGD process, steam is injected into the reservoir to heat the bitumen, reducing its viscosity, and allowing it to flow towards a lower well where it can be collected. The performance of the SAGD process depends on various factors such as steam injection rate, reservoir heterogeneity, and operating conditions. Accurately forecasting the performance of the SAGD process can help optimize these parameters and improve the overall efficiency of oil sands recovery. The data-driven performance indicators proposed in this study utilize the SVR method to establish a relationship between input parameters and the desired performance outputs. In the constructing process, some parameter optimization algorithms, like grid search method, particle swarm optimization algorithm and genetic algorithm, are used to identify the optimal SVR model structure. The validation results show that the design meets the desired objectives. All in all, through proposed data-driven performance indicators, the performance of SAGD process in candidate oil sands projects could be rapidly and easily obtained.