INTELLIGENT TIME SUCCESSIVE PRODUCTION MODELING

Production data analysis have been used extensively to predict performance of wells and field recovery but mostly on a single well basis. This paper presents a new approach to production data analysis using Artificial Intelligence (AI) techniques where production data history is used to build a field‑wide performance prediction model. In this work AI techniques and data driven modeling are utilized to predict future production of both synthetic and real field cases. Production history is paired with geological information from the field to build datasets containing the spatio‑temporal dependencies amongst different wells. These dependencies are addressed by information from Closest Offset Wells (COWs) including the geological characteristics (Spatial) and the dynamic production data (Temporal) of all COWs. Using the created dataset, a series of single layer neural networks is trained by back propagation algorithm. These networks are then fused together to form the ''Intelligent Time‑Successive Production Modeling '' (ITSPM). This technique only uses the well log information and the production history of existing wells to predict performance for new wells and initial hydrocarbon in place by a ''volumetric‑geostatistical'' method. A synthetic oil reservoir is modeled using a commercial simulator. Production and well‑log data are extracted into an all‑inclusive dataset. Next, several neural networks are trained and verified to predict different stages of the production. ITSPM method is utilized to estimate the production profile for nine newest wells in the reservoir and is also applied to the data from a real giant oil field in the Middle East including more than 200 wells with forty years of production history. ITSPM's production predictions of the four newest wells in this reservoir are compared to reality. When a reservoir simulation model is not a feasible option, ITSPM is an ideal alternative for real‑time predictive purposes.