The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period, even for Texas A&M users with NetID.
Prediction of Estimated Ultimate Recovery in the Eagle Ford
MetadataShow full item record
The study presents prediction of Estimated Ultimate Recovery (EUR) for multi-stage hydraulically fractured horizontal wells producing primarily oil in the Eagle Ford. The EUR prediction models’ comparison for the multi-stage hydraulically fractured horizontal wells in the Eagle Ford is made possible with the help of advances in neural networks. The monthly production and well data is collected for oil producing wells (1,134) drilled in 2010-11 in the Eagle Ford from Drilling Info Desktop. The models were trained using Multiple Linear Regression (MLR), Support Vector Machine (SVM) and Bayesian Regularized Neural Networks (BRNN). These models learn the relationship between well data and the EUR (estimated by decline curve analysis). Furthermore, these models were tested on the data not used in the training of the models. A model selection algorithm is formulated which produced a median absolute error of 22%. The models were trained and tested using Eagle Ford shale oil production data but the methodology and code should be applicable to other resource plays as well. This method could be useful for predicting the performance of various unconventional reservoirs for both oil and gas as a quick-look tool. As an advice for further work this tool can be used to prepare forecasts for unconventional gas reservoirs as well and combined with the oil forecasts to present a more holistic view.
Dholi, Mohit (2016). Prediction of Estimated Ultimate Recovery in the Eagle Ford. Master's thesis, Texas A & M University. Available electronically from