Machine learning-based prediction of the shale barrier size and spatial location using key features of SAGD production curves

Kim, Min; Shin, Hyundon

doi:10.1016/j.petrol.2020.107205

“…The number of DTs in the forest ( N _ E st ) serves as one of the tuning hyperparameters in the optimum RF model, while the maximum depth of DTs ( Max_D ) and number of features are used to search for the best split ( Max_F ) (Kim & Shin, 2020).…”

Section: Proposed Methods and Materials Usedmentioning

confidence: 99%

Reconstructing Daily Discharge in a Megadelta Using Machine Learning Techniques

Thanh

¹

,

Binh

²

,

Kantoush

³

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

River discharge is a crucial indicator to understand terrestrial water cycles and supplies necessary information about water resource management (Adnan et al., 2020). Direct measurement of river discharge, such as employing the acoustic Doppler current profiler, is complicated, costly, time-consuming, and labor-intensive because it requires a number of current sensors and repeated surveys performed by boats and is thus unsafe under unfavorable flow and weather conditions (Gisen & Savenije, 2015;Matte et al., 2018). Other noncontact methods, including large-scale particle image velocimetry (LSPIV) (Akbarpour et al., 2020) and remote sensing (Kebede et al., 2020), have recently begun to be used for discharge measurements. Nevertheless, the use of these methods in contiguous monitoring of river discharge is not feasible; for example, LSPIV cannot measure discharge in large rivers because of limited camera coverage, while satellite images are not always available due to cloud cover, particularly during rainy seasons. As a result, at hydrological stations situated on rivers worldwide, flow discharge is not directly measured; rather, it is indirectly estimated either from the widely used stage-discharge rating curve (RC) method or from cubature, rating-fall, tide-correction, and coaxial graphical-correction methods (Matte et al., 2018), in which the stage (water level) is recorded at specific intervals (e.g., daily, hourly, or sub-daily) depending on the goal of the measurements. Due to technical, financial, maintenance and political instability issues, long-term flow discharge datasets may have gaps, resulting in the loss of information or the misinterpretation of historical flow regime changes and hydrological processes (Tencaliec et al., 2015). Therefore, it is important to reconstruct missing discharge values to reliably provide helpful information for water resource management at the basin scale.Several methods, including statistical methods, numerical models, and machine learning (ML) algorithms, have been employed to predict river flows. Recently, ML techniques, such as support vector regression (SVR) (Adnan et al., 2020;Luo et al., 2019), random forest (RF), Gaussian process regression (GPR) (Sun et al., 2014), M5

show abstract

“…Kim and Shin (2018) generated a proxy model, based on simulation results, to predict oil production with different shale barrier sizes . Kim and Shin (2020) developed a trained machine learning model to forecast a distribution of shale according to oil production . Ma and Leung (2020) used a machine learning model to predict oil production and temperature profiles …”

Section: Steam-assisted Gravity Drainage (Sagd)mentioning

confidence: 99%

“…168 Kim and Shin (2020) developed a trained machine learning model to forecast a distribution of shale according to oil production. 169 Ma and Leung (2020) used a machine learning model to predict oil production and temperature profiles. 170 SAGD simulation also plays an important role in optimizing operations to achieve maximum performance.…”

Section: ■ Css Follow-up Processes and Simulationmentioning

confidence: 99%

A Critical Review of Reservoir Simulation Applications in Key Thermal Recovery Processes: Lessons, Opportunities, and Challenges

Yang

¹

,

Nie

²

,

Wu

³

et al. 2021

View full text Add to dashboard Cite

After a cyclic steam stimulation (CSS) process achieved accidental success in recovering heavy oil resources in the 1960s, thermal recovery processes started to unlock the door of in situ recovery of heavy oil and bitumen resources. After five decades of development, many thermal recovery processes have been developed, among which CSS and steam-assisted gravity drainage (SAGD) are two main commercialized processes. With the support of laboratory and field data, reservoir simulation can help engineers and researchers to understand recovery mechanisms, optimize operations, and forecast performance of either existing or emerging processes. In this paper, we present a critical review of applications of reservoir simulation on CSS, CSS follow-ups (steamflooding, liquid addition to steam for enhancing recovery (LASER), and in situ combustion), SAGD, solvent-assisted SAGD, and SAGD noncondensable gas (NCG) coinjection processes. This review and the analyses of these processes provide not only their clarifications from thermal simulation lessons but also an extensive summary of challenges still faced by industry. Moreover, they shed light on future research directions and opportunities for thermal recovery processes.

show abstract

“…In addition, it is an efficient method for screening the less influential parameters from the input parameters on the output parameters and simplifying the setting for further simulations. The significant parameters were selected from the results of multivariate analysis of variance (MANOVA) [5,[28][29][30]. Table 5 lists the p values from MANOVA.…”

Section: Selection Of Significant Parametersmentioning

confidence: 99%

“…The p value is an indicator to decide the relative significance between parameters. The criterion for selecting the significant parameters was a significance level of 0.05 [5,[28][29][30]; the significant parameters are highlighted in bold in Table 5. The significant parameters were used in the simulation experiments designed by Latin hypercube sampling to develop regression models for predicting the decline parameters.…”

Section: Selection Of Significant Parametersmentioning

confidence: 99%

Development of Production-Forecasting Model Based on the Characteristics of Production Decline Analysis Using the Reservoir and Hydraulic Fracture Parameters in Montney Shale Gas Reservoir, Canada

Shin

¹

,

Nguyen-Le

²

,

Kim

³

et al. 2021

Geofluids

Self Cite

2

0

View full text Add to dashboard Cite

This study developed a production-forecasting model to replace the numerical simulation and the decline curve analysis using reservoir and hydraulic fracture data in Montney shale gas reservoir, Canada. A shale-gas production curve can be generated if some of the decline parameters such as a peak rate, a decline rate, and a decline exponent are properly estimated based on reservoir and hydraulic fracturing parameters. The production-forecasting model was developed to estimate five decline parameters of a modified hyperbolic decline by using significant reservoir and hydraulic fracture parameters which are derived through the simulation experiments designed by design of experiments and statistical analysis: (1) initial peak rate ( P hyp ), (2) hyperbolic decline rate ( D hyp ), (3) hyperbolic decline exponent ( b hyp ), (4) transition time ( T transition ), and (5) exponential decline rate ( D exp ). Total eight reservoir and hydraulic fracture parameters were selected as significant parameters on five decline parameters from the results of multivariate analysis of variance among 11 reservoir and hydraulic fracture parameters. The models based on the significant parameters had high predicted R 2 values on the cumulative production. The validation results on the 1-, 5-, 10-, and 30-year cumulative production data obtained by the simulation showed a good agreement: R 2 > 0.89 . The developed production-forecasting model can be also applied for the history matching. The mean absolute percentage error on history matching was 5.28% and 6.23% for the forecasting model and numerical simulator, respectively. Therefore, the results from this study can be applied to substitute numerical simulations for the shale reservoirs which have similar properties with the Montney shale gas reservoir.

show abstract

Machine learning-based prediction of the shale barrier size and spatial location using key features of SAGD production curves

Cited by 20 publications

References 35 publications

Reconstructing Daily Discharge in a Megadelta Using Machine Learning Techniques

Reconstructing Daily Discharge in a Megadelta Using Machine Learning Techniques

A Critical Review of Reservoir Simulation Applications in Key Thermal Recovery Processes: Lessons, Opportunities, and Challenges

Development of Production-Forecasting Model Based on the Characteristics of Production Decline Analysis Using the Reservoir and Hydraulic Fracture Parameters in Montney Shale Gas Reservoir, Canada

Contact Info

Product

Resources

About