Enhanced Well Placement Through Infill Well Optimization with 3D Confidence Index Map

Abstract The success of a field development plan is highly dependent on the choice of well locations. Choosing the optimum well locations is, however, non-trivial and requires a thorough understanding of hydrocarbon reservoir performance and properties [1]. Even after the locations are identified there is a need to further rank the wells in terms of confidence as part of the risk assessment. This paper presents a novel approach that integrates geological modeling, geostatistics, and machine learning techniques to generate a confidence index map, which could then be used for optimizing infill well placement with a much higher level of confidence. This, in turn, helps with better decision making and reduces the risk involved in drilling additional infill wells. The conventional approaches use averaging techniques to combine several reservoir attributes to identify the wells placement targets. These approaches could be further improved with the proposed workflow and capture the reservoir understanding which vary from one hydrocarbon reservoir to another. Leveraging on the various machine learning algorithms, the 3D Confidence Index Map (CIM) methodology addresses this challenge by systematically quantifying the uncertainty associated with key reservoir parameters and integrating them into a spatial map that highlights areas with the highest confidence for successful infill drilling. This paper presents a workflow using the Confidence Index Map (CIM) methodology to addresses the challenge in optimizing infill well placement with a much higher level of confidence. Furthermore, this approach also provides valuable insights by incorporating uncertainty into the analysis, helps to identify and mitigate risks associated with infill drilling from mature oil and gas fields.