Data-driven model for hydraulic fracturing design optimization. Part II: Inverse problem

Duplyakov, Viktor; Morozov, Aleksandr; Popkov, Dmitriy; Shel, Egor; Vainshtein, Albert; Burnaev, Evgeny; Осипцов, А. Н.; Paderin, Grigory

doi:10.1016/j.petrol.2021.109303

Cited by 19 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it comes to HF, the balancing act between incremental future revenue and execution costs poses a significant optimization challenge. There is limited research on incorporating cost implications (like net present value -NPV) into fracture parameter optimization (Duplyakov et al, 2022).…”

Section: Optimization Dilemmasmentioning

confidence: 99%

“…Most work employ ML to predict the production profile and cumulative production after a fracturing job (Temizel et Syed et al, 2022). Others adopt ML to determine the inverse problem of determining the optimal hydraulic fracturing parameters given a desired production output (Duplyakov et al, 2022;Sprunger et al, 2022). Such parameters include proppant and fluid volumes, fracture length, number of HF stages, and pump rates.…”

Section: Ml/ai For Hf Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Systematic Analysis of Novel Machine Learning Techniques for Hydraulic Fracturing Optimization

Alake,

Oyedeji

2024

Preprint

View full text Add to dashboard Cite

Over the past decade, the volume and quality of data in the oil and gas industry have exploded, breeding exciting opportunities to implement machine learning for better data- driven decisions. One critical example is hydraulic fracturing (HF), given our ever-growing reliance on HF to meet global hydrocarbon demand. This paper systematically explores the work of several researchers to apply ML techniques (including linear regression, neural networks, support vector machine, decision trees, and more) to HF-related operations, from production forecast to HF design. Furthermore, this study examines how optimization algorithms (including gradient-free, differential evolution, and surrogate-based optimizations) are incorporated with different ML techniques for selecting optimal HF parameters (like fracture number, proppant concentration, and more) during the planning process. The paper aims to provide a comprehensive overview without delving too deeply into technical intricacies to ensure accessibility for a broader audience. Additionally, it introduces innovative techniques currently being integrated into the industry and offers a clear understanding of the processes involved. Ultimately, the analysis concludes that machine learning is an accurate and cost-effective alternative for hydraulic fracturing optimization.

show abstract

Section: Optimization Dilemmasmentioning

confidence: 99%

Section: Ml/ai For Hf Overviewmentioning

confidence: 99%

Systematic Analysis of Novel Machine Learning Techniques for Hydraulic Fracturing Optimization

Alake,

Oyedeji

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The application of machine learning and artificial intelligence involves several stages: data collection, data preparation, choosing the machine learning model, training, and testing of the model and validation [138]. Different researchers have applied artificial intelligence methods to predict geological [139], petrophysical [140], and geomechanical properties [141] and production and enhanced oil recovery methods' efficiency for shale and tight reservoirs [142,143]. A systematic review of the application of artificial intelligence by Syed et al [144] has shown an exponential increase in the publication of artificial intelligence applications to shale and tight reservoirs.…”

Section: Data-driven Modeling Approachesmentioning

confidence: 99%

“…Their findings showed the ten most important feature optimizations of hydraulic fracturing. Furthermore, Duplyakov et al [143] utilized the data of Morozov et al [142] to identify the parameters for optimization of hydraulic fracturing by an inverse approach. The optimization methods used in this study showed that increasing the proppant mass and reducing the average proppant concentration were vital to maximize the well productivity.…”

Section: Data-driven Modeling Approachesmentioning

confidence: 99%

Tight and Shale Oil Exploration: A Review of the Global Experience and a Case of West Siberia

Dorhjie,

Mukhina,

Kasyanenko

et al. 2023

Energies

View full text Add to dashboard Cite

Shale and tight oil reservoirs, with horizontal wells and hydraulic fractures, typically have a recovery ratio of around 10%. The exploration of tight oil and shale in North America has proven economically viable, thanks to advancements, such as horizontal wells, hydraulic fracturing, and other enhanced oil recovery techniques. Taking inspiration from the global experience (the North American shale experience), the exploration and development of the West Siberian tight and shale reserves was more focused on the reported best practices of the exploration of North American shale. In this study, the advance in the specific areas of shale and tight oil exploration was considered, with more emphasis placed on the progress in the exploration of West Siberian shales. According to the review literature, thermal enhanced recovery methods capable of converting organic matter into hydrocarbons were studied more than other methods of enhanced oil recovery. Aligned with global trends, there has been a growing focus on research aiming to integrate data-driven approaches and pore-scale simulations to enhance recovery from tight and shale formations. Multiple pilot studies have showcased promising prospects for implementing multistage hydraulic fracturing. Nevertheless, there are limited pilot studies dedicated to enhanced oil recovery methods for West Siberian shale.

show abstract

“…Their results showed that a 73% increase in fluid volume and a 38% increase in proppant use could double postfracture production. Under boundary constraints, Duplyakov et al (2022) used the high-dimensional black box approximation function to optimize fracturing design parameters based on Ridge regression and CatBoost algorithm. They also used particle swarm optimization, sequential least squares programming, surrogate optimization model and differential evolution optimization method to solve the problem.…”

Section: Introductionmentioning

confidence: 99%

Optimizing construction parameters for fractured horizontal wells in shale oil

Liu

Li²,

Jia³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Shale oil is mainly extracted by fracturing. However, it is difficult to determine the optimum construction parameters to obtain maximum productivity. In this paper, a fuzzy comprehensive production evaluation model for fractured shale oil horizontal wells based on random forest algorithm and coordinated principal component analysis is proposed. The fracturing parameters of the target wells are optimized by combining this model with an orthogonal experimental design. The random forest algorithm was used to calculate the importance of data sample factors. The main controlling factors of the production of fractured horizontal wells in shale oil were obtained. To reduce the noise of the sample data, principal component analysis was used to reduce the dimensions of the main control factors. Furthermore, the random forest algorithm was used to determine the weight of the principal components after reducing the dimensionality. The membership function of the main control factors after reducing dimensionality was established by combining the fuzzy statistics and assignment methods. In addition, the membership matrix of the effect prediction of fractured horizontal wells in shale oil was determined. The fuzzy comprehensive evaluation method is used to score and evaluate the effect of fractured horizontal wells. Combined with the orthogonal experimental design method, the optimized parameter design of a fractured horizontal well considering the comprehensive action of multiple parameters is realized. After construction according to the optimized parameters, production following fracturing increases significantly. This verifies the rationality of the optimization method that is proposed in this paper.

show abstract

Data-driven model for hydraulic fracturing design optimization. Part II: Inverse problem

Cited by 19 publications

References 16 publications

Systematic Analysis of Novel Machine Learning Techniques for Hydraulic Fracturing Optimization

Systematic Analysis of Novel Machine Learning Techniques for Hydraulic Fracturing Optimization

Tight and Shale Oil Exploration: A Review of the Global Experience and a Case of West Siberia

Optimizing construction parameters for fractured horizontal wells in shale oil

Contact Info

Product

Resources

About