Co-Optimization of CO2-EOR Strategies Considering the Spatio-Temporal Sequence Prediction of CO2 Flooding and Sequestration

Day 2 Tue, April 23, 2024(2024)

引用 0|浏览0
暂无评分
摘要
Abstract CO2 injection for field development strategies serves not only to enhance hydrocarbon recovery but also to facilitate subsurface CO2 sequestration. The optimization problem aimed at coordinating CO2 flooding and sequestration simultaneously is proposed to ensure the comprehensiveness of CO2-EOR strategies. The conventional optimization workflow falls short in comprehensively incorporating the multidimensional reservoir information that influences CO2 flooding. In this paper, a novel optimization framework that couples the AST-GraphTrans model (Attention-based Spatio-temporal Graph-Transformer Network) and multi-objective optimization algorithm MOPSO (Multi-objective Particle Swarm Optimization) is established to optimize the CO2-EOR strategies in integrated development of CO2 flooding and sequestration simultaneously. The framework consists of two outstanding components. The AST-GraphTrans model is utilized to forecast the CO2-EOR dynamics, which includes cumulative oil production, CO2 sequestration volume, and CO2 flooding front. And the MOPSO algorithm is employed for handling the co-optimization of CO2-EOR strategies, i.e., maximizing the oil production while maximizing the sequestration volume with the containment of gas channeling. The effectiveness of the proposed framework is validated on a field-scale reservoir model. The results demonstrate that it can achieve the co-optimization of CO2-EOR strategies by considering the spatio-temporal sequence prediction of CO2 flooding and sequestration.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要