Collaborative Filtering in Development Well Recommendation for Well Argumentation

In this paper, an attribute clustering based collaborative filtering algorithm is applied for development well recommendation towards exploratory wells argumentation. The algorithm utilizes similarity characteristics of exploratory and development well related attributes, especially porosity, permeability and oil saturation, to filter redundant data by feature selection. Experiment use practical well data of the oil company for clustering. By integration of a scaled rating scheme on properties and the collaborative filtering philosophy to provide the recommend cluster. Such cluster contains the candidate development wells for recommendation. Finally, by calculating the similarity between exploratory and development wells, the scheme is able to provide the geologist the selected development wells for the decided exploratory in well argumentation.