Abstract
The oil is called as the industrial blood. For one oil well, its oil production is a wavelike process. It can be modeled as a time series data. During the whole life cycle for one well, it can have several similar stages. Meanwhile, the oil wells in the same oilfield may share similar production processes. However, these two similarities are hard to be accurately described by a mathematical formula. Therefore, in this paper, we use LSTM which is a kind of deep learning model to learn the oil production characteristics from the existed wells and predict the new oil well’s production behavior. With the real oil well production data from DaGang Oilfield in Hebei Province of China, two experiments are implemented. One experiment uses one well’s previous production data to predict its future, while the other experiment uses different oil wells from the same oilfield to predict another individual oil well’s production. The results show that the LSTM is able to get satisfactory prediction output.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhou, Y., Zhou, F.J., Feng, L.Y.: A new model for predicting oil and gas production. Pet. Geol. Oilfield Dev. Daqing 37(05), 76–80 (2018)
Pang, M.Y., Tang, H.: Von bertalanffy mathematical model for predicting oil field cumulative production. China Sci. Pap. 12(21), 2487–2491 (2017)
Ren, F.L., Ren, S.D., Li, J.J.: Prediction of oil production based on linear regression method and time series method. Henan Sci. 36(06), 817–822 (2018)
Liu, Y.K., Bi, Y.B., Sui, X.G., Wu, X.H.: The development index prediction when oilfield coming into declining stage. Gas Ind. 03, 100–102 (2007)
Yao, L.L., Xiong, Y., Luo, B., Ge, F.: The practical method on recoverable reserves when oilfield coming into declining stage. West China Explor. Eng. 10, 83–85 (2017)
Chen, Y.Q., Hu, J.G., Zhang, D.J.: The derivation and autoregression of logistic model. Xinjiang Pet. Geol. 02, 150–155 (1996)
Li, Z.C.: The dynamic prediction on oilfield based on water driving curve. Neijiang Sci. 39(06), 79–81 (2018)
Lu, J.Z.: The prediction method on oilfield’s yearly production and water cut. Pet. Geol. Oilfield Dev. Daqing 04, 62–65 (2007)
Energy-Oil and Gas Research; Studies from Petroleum University of Technology Further Understanding of Oil and Gas Research (Development of Robust Surrogate Model for Economic Performance Prediction of Oil Reservoir Production Under Waterflooding Process). Energy Weekly News (2019)
Leyla, M.: Neural networks for prediction of oil production. IFAC Pap. Line 51(30) (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yan, C., Qiu, Y., Zhu, Y. (2021). Predict Oil Production with LSTM Neural Network. In: Liu, Q., Liu, X., Li, L., Zhou, H., Zhao, HH. (eds) Proceedings of the 9th International Conference on Computer Engineering and Networks . Advances in Intelligent Systems and Computing, vol 1143. Springer, Singapore. https://doi.org/10.1007/978-981-15-3753-0_34
Download citation
DOI: https://doi.org/10.1007/978-981-15-3753-0_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3752-3
Online ISBN: 978-981-15-3753-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)