Pattern Recognition for Steam Flooding Field Applications Based on Hierarchical Clustering and Principal Component Analysis

Steam flooding is a complex process that has been considered as an effective enhanced oil recovery (EOR) technique in both heavy oil and light oil reservoirs. Many studies have been conducted on different sets of steam flooding projects using the conventional data analysis methods while the implementation of machine learning algorithms to find the hidden patterns are rarely found. In this study, a hierarchical clustering algorithm coupled with principal component analysis is used to analyze the steam flooding projects worldwide. The goal of this research is to group similar steam flooding projects into the same cluster so that valuable operational design experiences and production performance from the analog cases can be referenced for decision-making. Besides, hidden patterns embedded in steam flooding applications can be revealed based on data characteristics of each cluster for different reservoir/fluid conditions. In this research, all reservoir/fluid properties were first normalized to the same scale to ensure the same importance of properties. Principal component analysis is applied to project original data to a new feature space, which reduces the dimensions from 8D to 2D but still retain more than 90% of the variance. After the data pre-processing process, the hierarchical clustering algorithm is implemented with the optimized design of five clusters, Euclidean distance, and Ward’s linkage method based on the computation of 30 indices, linkage coefficients, and clustering structures. The results of the hierarchical clustering depict that each cluster detects a unique range of each property, and the analog cases present that fields under similar reservoir/fluid conditions could share similar operational design and production performance