Data-driven proxy model for waterflood performance prediction and optimization using Echo State Network with Teacher Forcing in mature fields

Deng, Lichi; Pan, Yuewei

doi:10.1016/j.petrol.2020.107981

Cited by 17 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…21 These ESN architecture features make them a particularly good fit for the kind of heterogeneous data fusion required here. In recent times, ESNs have been used for a wide range of applications, such as traffic management, 22 soil temperature modelling, 23 power grid voltage insulator damage classification, 24 waterflood performance prediction 25 and wind speed forecasting. 26 The general ESN architecture has three principal features.…”

Section: Echo State Networkmentioning

confidence: 99%

Heterogeneous data fusion for the improved non-destructive detection of steel-reinforcement defects using echo state networks

Wootton

Day

Haycock

2022

Structural Health Monitoring

View full text Add to dashboard Cite

The degradation of roads is an expensive problem: in the United Kingdom alone, £27 billion was spent on road repairs between 2013 and 2019. One potential cost-saver is the early, non-destructive detection of faults. There are many available techniques, each with its own benefits and drawbacks. This paper builds upon the successful processing of magnetic flux leakage (MFL) data by echo state networks (ESNs) for damage diagnostics, by augmenting ESNs with the depth of concrete cover as part of a data fusion approach. This fusion-based ESN outperformed a number of non-fusion ESN comparators and a previously used analytical technique. Additionally, the fusion ESN had an optimal threshold value whose standard deviation was three times smaller than that of the nearest alternative technique, potentially prompting a move towards automated defect detection in ‘real-world’ applications.

show abstract

Section: Echo State Networkmentioning

confidence: 99%

Heterogeneous data fusion for the improved non-destructive detection of steel-reinforcement defects using echo state networks

Wootton

Day

Haycock

2022

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Machine-learning algorithms are used to design and develop such applications to extract complex relationships between system and performance characteristics. In addition to their applications for unconventional reservoirs − and secondary recovery, − successful EOR forecasting and screening models have also been developed. Evaluations of different EOR methods, chemical flooding methods, − cyclic pressure pulsing, , and thermal methods − including SAGD , were made using data-driven models.…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning Approach for Forecasting Steam-Assisted Gravity-Drainage Performance in the Presence of Noncondensable Gases

Canbolat¹,

Artun

2022

ACS Omega

View full text Add to dashboard Cite

Steam-assisted gravity drainage (SAGD) is an effective enhanced oil recovery method for heavy oil reservoirs. The addition of certain amounts of noncondensable gases (NCG) may reduce the steam consumption, yet this requires new design-related decisions to be made. In this study, we aimed to develop a machine-learning-based forecasting model that can help in the design of SAGD applications with NCG. Experiments with or without carbon dioxide (CO 2 ) or n -butane ( n -C 4 H 10 ) mixed with steam were performed in a scaled physical model to explore SAGD mechanisms. The model was filled with crushed limestone that was premixed with heavy oil of 12.4° API gravity. Throughout the experiments, temperature, pressure, and production were continuously monitored. The experimental results were used to train neural-network models that can predict oil recovery (%) and cumulative steam–oil ratio (CSOR). The input parameters included injected gas composition, prior saturation with CO 2 or n -C 4 H 10 , separation between wells, and pore volume injected. Among different neural-network architectures tested, a 3-hidden-layer structure with 40, 30, and 20 neurons was chosen as the forecasting model. The model was able to predict oil recovery and CSOR with R 2 values of 0.98 and 0.95, respectively. Variable importance analysis indicated that pore volume injected, distance between wells, and prior CO 2 saturation are the most critical parameters that would affect the performance, in agreement with the experiments.

show abstract

“… 20 Deng and Pan (2021) designed and implemented the echo state network (ESN)-based data-driven proxy model to complete predicting tasks for waterflooding fields. 21 …”

Section: Introductionmentioning

confidence: 99%

“…20 Deng and Pan (2021) designed and implemented the echo state network (ESN)-based data-driven proxy model to complete predicting tasks for waterflooding fields. 21 Aforementioned works reveal that the data-driven proxy model could provide a powerful tool for solving performance forecasting problem and most of them involve time series changes. Several methods, including ANN, support vector machine, random forest regression, and their variants, can be used to construct a data-driven proxy model.…”

Section: Introductionmentioning

confidence: 99%

“…Zhong et al (2020) proposed a deep convolutional generative neural network (CDC-GAN)-based data-driven proxy model to predict the field oil production of reservoir developed by the waterflooding technology . Deng and Pan (2021) designed and implemented the echo state network (ESN)-based data-driven proxy model to complete predicting tasks for waterflooding fields …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Proxy Model for Forecasting of Cumulative Oil Production during the Steam-Assisted Gravity Drainage Process

Liu

et al. 2021

ACS Omega

View full text Add to dashboard Cite

The purpose of this study is to develop a data-driven proxy model for forecasting of cumulative oil (Cum-oil) production during the steam-assisted gravity drainage process. During the model building process, an artificial neural network (ANN) is used to offer a complementary and computationally efficient tool for the physics-driven model, and the von Bertalanffy performance indicator is used to bridge the physics-driven model with the ANN. After that, the accuracy of the model is validated by blind-testing cases. Average absolute percentage error of related parameters of the performance indicator in the testing data set is 0.77%, and the error of Cum-oil production after 20 years is 0.52%. The results illustrate that the integration of performance indicator and ANN makes it possible to solve time series problems in an efficient way. Besides, the data-driven proxy model could be applied to fast parametric studies, quick uncertainty analysis with the Monte Carlo method, and average daily oil production prediction. The findings of this study could help for better understanding of combination of physics-driven model and data-driven model and illustrate the potential for application of the data-driven proxy model to help reservoir engineers, making better use of this significant thermal recovery technology for oil sands or heavy oil reservoirs.

show abstract

Data-driven proxy model for waterflood performance prediction and optimization using Echo State Network with Teacher Forcing in mature fields

Cited by 17 publications

References 24 publications

Heterogeneous data fusion for the improved non-destructive detection of steel-reinforcement defects using echo state networks

Heterogeneous data fusion for the improved non-destructive detection of steel-reinforcement defects using echo state networks

Machine-Learning Approach for Forecasting Steam-Assisted Gravity-Drainage Performance in the Presence of Noncondensable Gases

Data-Driven Proxy Model for Forecasting of Cumulative Oil Production during the Steam-Assisted Gravity Drainage Process

Contact Info

Product

Resources

About