Excess water production is a serious economic and environmental problem in most mature oil fields. Accurate and timely diagnosis of the water production mechanism is critical in the success of the applied treatment methodology. While many empirical techniques have been traditionally used in production data analysis, the significance of water-oil ratio (WOR) in proper identification of the type of the water production problem in oil wells is not yet fully investigated. Data mining techniques could facilitate extracting any hidden predictive information from oil and water production data to be used in water control studies.

This paper applies a meta learning classification technique called Logistic Model Trees (LMT) to diagnose water production mechanisms based on WOR data and static reservoir parameters. Synthetic reservoir models are built to simulate excess water production due to coning, channeling and gravity segregated flows. Various cases are then generated by varying some of the input parameters in each model. A number of key features from plots of WOR against oil recovery factor are heuristically extracted by segmenting these plots at certain points. LMT classifiers are then applied to integrate these features with reservoir parameters to build classification models for predicting the water production mechanism in different scenarios of pre and post water-production stages.

It is observed that a valid association between WOR data and the water production mechanism exists. Our results with high prediction accuracy rates of 88% for pre-production and more than 94% for post-production stage demonstrate efficiency of the proposed LMT classifiers and significance of WOR values in classifying excess water production problems.

You can access this article if you purchase or spend a download.