Perpustakaan Digital ITB

Hydraulic fracturing has been established as one of production enhancement methods in the petroleum industry. This method is proven to increase productivity and reserves in low permeability reservoirs, while in medium permeability it accelerates production without affecting well reserves. However, the production result from hydraulic fractured wells looks scattered and no direct correlation with the individual well parameters. It gets more challenging due to the decreasing trend in production result of hydraulic fracturing job and the needs to increase the success ratio. Meanwhile, there are hundreds of data that can be analyzed to show the relationship between reservoir properties and fracturing treatment with the production result. Hydraulic fracturing in several fields at South Sumatra area has been implemented since 2002. It may adequate for the evaluation to find the relationship between reservoir properties and hydraulic fracturing treatment with the production result. Empirical correlation and machine learning (ML) approach are proposed to evaluate and solve this problem. The concept of Darcy's equation is utilized as basis for the empirical correlation on the actual data. The ML method is then applied to provide better predictions both for production rate and water cut. This method has also been developed to solve data limitations so that the prediction method can be used for all wells. Comparison between empirical correlation and machile learning is then evaluated to have better prediction on the result of hydraulic fracturing job. Empirical correlation can give an R2 of 0.67, while ML can give a better R2 that is close to 0.80. ML offers input that can be obtained from primary parameter thus easier to be applied to predict the well performance. Thus, it can be used as well candidate selection tool.