石油地球物理勘探2025，Vol.60Issue(6)：1386-1398,13.DOI:10.13810/j.cnki.issn.1000-7210.20240493
基于多层级图神经网络的井间连通性评估
Interwell connectivity evaluation based on multi-level graph neural network
摘要
Abstract
During waterflooding,evaluating interwell connectivity is essential for reservoir management,pro-duction strategy optimization,and improved hydrocarbon recovery.Existing methods,those are based on graph neural networks fail to characterize the temporal and spatial relationships within well networks through graph structures,limiting the accurate description of delayed dynamic responses.To bridge this gap,this study pro-poses a multi-level graph-structured temporal network model to capture dynamic relationships from time-series well network data,and enable precise interwell connectivity evaluation.Specifically,considering the injection-production response delay of a well network,a multi-level graph-structured temporal-spatial dependence repre-sentation method is proposed,which integrates production time-series responses with the spatial structure infor-mation of the well network is introduced.Subsequently,a multi-level temporal graph neural network model is established;Next,an attention mechanism based hierarchical information interaction and update method is de-veloped.These together enable the model to explore dynamic interactions between injection and production wells and achieve accurate inversion of interwell connectivity.Experimental results demonstrate that the pro-posed model exhibits superior accuracy over conventional temporal models,with a consistency of 93.8%with tracer test results.Moreover,it conforms to the gradual evolution of connectivity in accordance with physical principles,demonstrating the method's strong practical applicability in engineering.关键词
注水开发/井间连通性/时间序列/注意力机制/图神经网络Key words
waterflooding/interwell connectivity/time-series/attention mechanism/graph neural networks分类
天文与地球科学引用本文复制引用
WANG Xin,JIANG Yue,ZENG Xingjie..基于多层级图神经网络的井间连通性评估[J].石油地球物理勘探,2025,60(6):1386-1398,13.基金项目
本项研究受国家自然科学基金优秀青年基金"页岩气多尺度非线性渗流力学"(52222402)、国家自然青年基金"基于物理图神经网络的井间连通性智能识别理论与方法"(52404040)、南充市科技计划项目"储层自动识别及分类评价技术研究"(23XNSYSX0111)联合资助. （52222402）
