2022
DOI: 10.2118/206126-pa
|View full text |Cite
|
Sign up to set email alerts
|

Simulating Oil and Water Production in Reservoirs with Generative Deep Learning

Abstract: Summary This study investigated the ability to produce accurate multiphase flow profiles simulating the response of producing reservoirs, using generative deep learning (GDL) methods. Historical production data from numerical simulators were used to train a variational autoencoder (VAE) algorithm that was then used to predict the output of new wells in unseen locations. This work describes a procedure in which data analysis techniques can be applied to existing historical producti… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(2 citation statements)
references
References 16 publications
0
2
0
Order By: Relevance
“…Furthermore, Wang et al [48] outlined an integrated method that combines predictions of fluid flow with direct flow simulation, significantly reducing computation time without compromising accuracy. Alakeely and Horne [2] examined the effectiveness of generative deep learning methods in predicting multiphase flow profiles of new wells in unseen locations using historical production data and a variational autoencoder algorithm. Dong et al [51] introduced a deep reinforcement learning based approach for automatic curve matching for well test interpretation, utilizing the double deep Q-network.…”
Section: Overviewmentioning
confidence: 99%
“…Furthermore, Wang et al [48] outlined an integrated method that combines predictions of fluid flow with direct flow simulation, significantly reducing computation time without compromising accuracy. Alakeely and Horne [2] examined the effectiveness of generative deep learning methods in predicting multiphase flow profiles of new wells in unseen locations using historical production data and a variational autoencoder algorithm. Dong et al [51] introduced a deep reinforcement learning based approach for automatic curve matching for well test interpretation, utilizing the double deep Q-network.…”
Section: Overviewmentioning
confidence: 99%
“…Apart from these, a variant of the gradient boosting machine, e.g., extreme gradient boosting machine (XGBoost), was implemented for fast analysis of well placements in a heterogeneous reservoir [4]. The articles [5,6] also discussed the use of some more advanced ML methods in simulating the behavior of reservoirs and production trends, which is an important criterion to be manifested by a proxy model. The potential implementation of ML methods in proxy modeling was also further highlighted in the domain of secondary recovery.…”
Section: Introductionmentioning
confidence: 99%