Data-driven model-based rate decline prediction in unconventional eagle ford shale oil wells

The main objective of this paper is to develop a novel data-driven-based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and tau) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data get available, there is definitely extra room for further data analysis and improved results.

Automated summary

The paper aimed to develop a new data-driven model to predict decline curves and EUR for new wells based on nearby wells data. It found decline curves are a simpler alternative to complex reservoir simulators and successfully linked predictor variables to decline curve parameters. The study's novelty lies in the algorithm and dataset used for rate decline prediction in Eagle Ford data set, with room for further data analysis and improvement as more data become available.