Production forecast and optimization for parent-child well pattern in unconventional reservoirs

Wu, Hai Yan; Chen, Zan; Chen, Shengnan; Hui, Gang; Kong, Bing

doi:10.1016/j.petrol.2021.108899

Cited by 22 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xue et al [24] established a mechanism model through numerical simulation, which generated a large amount of data and predicted the future production of shale gas based on multiobjective random forest regression. Wang et al [25] predicted the first annual productivity of subwells based on RF, GBDT, Linear Regression and neural network, among which RF and GBDT had significantly better prediction effect than the latter. Alwated et al [26] mainly studied the machine learning technology, including random forest, gradient boosting regression and decision tree to predict the migration of fluid in porous media.…”

Section: Gbdtmentioning

confidence: 99%

A Data-Driven Oil Production Prediction Method Based on the Gradient Boosting Decision Tree Regression

Ma¹,

Zhao²,

Zhao³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Accurate prediction of monthly oil and gas production is essential for oil enterprises to make reasonable production plans, avoid blind investment and realize sustainable development. Traditional oil well production trend prediction methods are based on years of oil field production experience and expertise, and the application conditions are very demanding. With the rapid development of artificial intelligence technology, big data analysis methods are gradually applied in various sub-fields of the oil and gas reservoir development. Based on the data-driven artificial intelligence algorithm Gradient Boosting Decision Tree (GBDT), this paper predicts the initial single-layer production by considering geological data, fluid PVT data and well data. The results show that the GBDT algorithm prediction model has great accuracy, significantly improving efficiency and strong universal applicability. The GBDT method trained in this paper can predict production, which is helpful for well site optimization, perforation layer optimization and engineering parameter optimization and has guiding significance for oilfield development.

show abstract

Section: Gbdtmentioning

confidence: 99%

A Data-Driven Oil Production Prediction Method Based on the Gradient Boosting Decision Tree Regression

Ma¹,

Zhao²,

Zhao³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…Garcia Ferrer et al [27] suggested a workflow using numerical simulation to optimize child wells in a depleted environment. Wang et al [28] used a data-driven approach in the Montney to maximize the productivity of child wells. Kang et al [29] implemented a workflow for automated history matching and optimization for hydraulic fracturing design; in their study, they used a different optimization algorithm (COBYLA) and kriging as their proxy models.…”

Section: Bakkenmentioning

confidence: 99%

Offset Well Design Optimization Using a Surrogate Model and Metaheuristic Algorithms: A Bakken Case Study

Merzoug

Rasouli

2023

Eng

View full text Add to dashboard Cite

Fracture-driven interaction FDI (colloquially called “Frac-hit”) is the interference of fractures between two or more wells. This interference can have a significant impact on well production, depending on the unconventional play of interest (which can be positive or negative). In this work, the surrogate model was used along with metaheuristic optimization algorithms to optimize the completion design for a case study in the Bakken. A numerical model was built in a physics-based simulator that combines hydraulic fracturing, geomechanics, and reservoir numerical modeling as a continuous simulation. The stress was estimated using the anisotropic extended Eaton method. The fractures were calibrated using Microseismic Depletion Delineation (MDD) and microseismic events. The reservoir model was calibrated to 10 years of production data and bottom hole pressure by adjusting relative permeability curves. The stress changes due to depletion were calibrated using recorded pressure data from MDD and FDI. Once the model was calibrated, sensitivity analysis was run on the injected volumes, the number of clusters, the spacing between clusters, and the spacing between wells using Sobol and Latin Hypercube sampling. The results were used to build a surrogate model using an artificial neural network. The coefficient of correlation was in the order of 0.96 for both training and testing. The surrogate model was used to construct a net present value model for the whole system, which was then optimized using the Grey Wolf algorithm and the Particle Swarm Optimization algorithm, and the optimum design was reported. The optimum design is a combination of wider well spacing (1320 ft), tighter cluster spacing (22 ft), high injection volume (1950 STB/cluster), and a low cluster number per stage (seven clusters). This study suggests an optimum design for a horizontal well in the Bakken drilled next to a well that has been producing for ten years. The design can be deployed in new wells that are drilled next to depleted wells to optimize the system’s oil production.

show abstract

“…Machinelearning algorithms find extensive applications across diverse domains and phases within the petroleum industry including reservoir geology and engineering, as well as oil and gas exploration, development, and production. 3 Combining with machine learning will be the research core and hotspot for the construction and development of artificial intelligence in the oil and gas field. 4 Cluster analysis algorithms are primarily used to classify and identify lithologies based on strong correlations with geological features.…”

Section: Introductionmentioning

confidence: 99%

Lithofacies identification of shale formation based on mineral content regression using LightGBM algorithm: A case study in the Luzhou block, South Sichuan Basin, China

Liu,

Zhu,

Zhai

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

Lithofacies form the basis for evaluating shale gas fields and play an important role in gas reservoir enrichment. The accurate identification of shale lithofacies is key for exploration and development. Based on well‐logged data, the accuracy of mineral content prediction using machine‐learning regression models is not ideal. Therefore, feature derivation was introduced to enhance the correlation between minerals and lithofacies and improve the data expression ability. Four machine‐learning models for mineral regression were established based on feature‐derived data sets: LightGBM, XGBoost, artificial neural network, and support vector machine. By calculating the evaluation metrics of each model, we found that LightGBM had the best prediction performance. To compare and confirm the accuracy of the model in identifying lithofacies, this study established a new method, MT‐LightGBM, which combines the LightGBM mineral content regression model with mineral ternary diagrams to identify lithofacies. By using the MT‐LightGBM model and LightGBM classification models to identify the target lithofacies, it was found that the accuracy of lithofacies identification of MT‐LightGBM reached 94%. This accuracy is high and is of great significance for understanding and evaluating underground shale reservoirs.

show abstract

Production forecast and optimization for parent-child well pattern in unconventional reservoirs

Cited by 22 publications

References 26 publications

A Data-Driven Oil Production Prediction Method Based on the Gradient Boosting Decision Tree Regression

A Data-Driven Oil Production Prediction Method Based on the Gradient Boosting Decision Tree Regression

Offset Well Design Optimization Using a Surrogate Model and Metaheuristic Algorithms: A Bakken Case Study

Lithofacies identification of shale formation based on mineral content regression using LightGBM algorithm: A case study in the Luzhou block, South Sichuan Basin, China

Contact Info

Product

Resources

About