TY - GEN

T1 - Development of water flood model for oil production enhancement

AU - Tsvaki, Jetina J.

AU - Tailakov, Dmitry O.

AU - Pavlovskiy, Evgeniy N.

N1 - Publisher Copyright: © 2020 IEEE.

PY - 2020/11/14

Y1 - 2020/11/14

N2 - Main goal of any industry is to increase productivity which in oil and gas field is to increase reservoir oil asset by producing oil in an effective and economically efficient manner. The objective of the study is to develop a water flood model for oil production enhancement using artificial neural networks and provide a model that maximizes oil production for a given water injection that in turn will extend mature fields life and decrease operational costs. Using the data comprising of daily water injection rates, oil production rates, water production, and gas production from the year 2004 to 2016 for 577 injection wells, 1344 production wells, and 36 events which had occurred during the course. Comparative analysis on the deep neural models such as Multi-Layer Perception, Convolutional Neural Networks, Long Short-Term Memory, and Gated Recurrent Neural Networks are used, and Gated Recurrent Neural Networks outperformed them. To minimize the loss and improve the performance of the water flood model tabular data mix-up was adopted on all the models above. The results showed that the data mixed up Gated Recurrent Neural Network outperformed all the other models. To maximize the oil production Nelder-Mead optimization method was adopted to find appropriate water injection rates. A simple two-layered multi-layer perceptron was used in modeling the nonlinear relationship between water injection and oil production to avoid function complexity.

AB - Main goal of any industry is to increase productivity which in oil and gas field is to increase reservoir oil asset by producing oil in an effective and economically efficient manner. The objective of the study is to develop a water flood model for oil production enhancement using artificial neural networks and provide a model that maximizes oil production for a given water injection that in turn will extend mature fields life and decrease operational costs. Using the data comprising of daily water injection rates, oil production rates, water production, and gas production from the year 2004 to 2016 for 577 injection wells, 1344 production wells, and 36 events which had occurred during the course. Comparative analysis on the deep neural models such as Multi-Layer Perception, Convolutional Neural Networks, Long Short-Term Memory, and Gated Recurrent Neural Networks are used, and Gated Recurrent Neural Networks outperformed them. To minimize the loss and improve the performance of the water flood model tabular data mix-up was adopted on all the models above. The results showed that the data mixed up Gated Recurrent Neural Network outperformed all the other models. To maximize the oil production Nelder-Mead optimization method was adopted to find appropriate water injection rates. A simple two-layered multi-layer perceptron was used in modeling the nonlinear relationship between water injection and oil production to avoid function complexity.

KW - machine learning

KW - mature oilfields

KW - neural networks

KW - oil extraction

KW - water injection

UR - http://www.scopus.com/inward/record.url?scp=85099574457&partnerID=8YFLogxK

U2 - 10.1109/S.A.I.ence50533.2020.9303200

DO - 10.1109/S.A.I.ence50533.2020.9303200

M3 - Conference contribution

AN - SCOPUS:85099574457

T3 - Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

SP - 46

EP - 49

BT - Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

Y2 - 14 November 2020 through 15 November 2020

ER -