Studying the direction of hydraulic fracture in carbonate reservoirs: Using machine learning to determine reservoir pressure

Martyushev, Dmitriy A.; Ponomareva, Inna N.; Филиппов, Е. В.

doi:10.1016/j.ptlrs.2022.06.003

Cited by 7 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers have recently been able to forecast the value of PP and fracture pressure using artificial intelligence algorithms in order to better predict the PP and FP in subsurface reservoirs. This is certainly relevant if the model is independent of the normal velocity trend and depends on the porosity (Rabbani and Babaei, 2019;Galkin et al, 2021;Ponomareva et al, 2021;Zakharov, 2021;Martyushev et al, 2022;Ponomareva et al, 2022). In 2000, Sadiq and Nashawi (2000) used artificial intelligence methods to predict formation failure pressure, which is the last point of formation PP.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of GMDH model to predict pore pressure

et al. 2023

View full text Add to dashboard Cite

Pore pressure (PP) is one of the essential and very critical parameters in the oil and gas industry, especially in reservoir engineering, exploitation, and production. Forecasting this valuable parameter can prevent huge costs incurred by the oil and gas industry. This research aims to develop a algorithm to better predict PP in subsurface -formations. Based on this, information from three wells (F1, F2, and F3) representing one of the Middle East oil fields was used in this research. The input variables used in this research include; laterolog (LLS), photoelectric index (PEF), compressional wave velocity (Vp), porosity (NPHI), gamma ray (spectral) (SGR), density (RHOB), gamma ray (corrected) (CGR), shear wave velocity (Vs), caliper (CALI), resistivity (ILD), and sonic transit time (DT). Based on the results presented in the heat map (Spearman’s correlation), it can be concluded that the pairs of parameters RHOB-PEF, CGR-SGR, RHOB-CALL, DT-PEF, PP-RHOB, Vs-RHOB, ILD-LLS, DT-CGR, and DT-NPHI are connected. In this research the GS-GMDH methods is used for modeling which is based on the Group method of data handling (GMDH). The results of this research show that this algorithm has an average error of RMSE = 1.88 Psi and R2 = 0.9997, indicating its high-performance accuracy. The difference between this method and the conventional GMDH method is that it can use three or more variables instead of two, which can improve prediction accuracy. Furthermore, by using the input of each neuron layer, the proposed model can communicate with other adjacent and non-adjacent layers to solve complex problems in the simplest possible way.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Application of GMDH model to predict pore pressure

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Over the years, these technologies have evolved and have been utilized in various capacities within the oil and gas sector, including completion design optimization [7,8], production monitoring [9], reservoir depletion tracking [10], fracture monitoring [11], well interference studies [12], integrity monitoring during fracking [13], flow assurance during the completion stage [14], cleanup studies [15], the monitoring of subsequent stimulation fluids [16], and pipeline leak detection [17]. In addition to traditional numerical and lab studies on simulating hydraulic fractures [18], by studying how fractures spread [19] and how wellbores may be cleaned [20], we may understand how this technology can greatly enhance decision-making and the optimization of these processes. In 2012, Johanessen et al [21], employed various techniques concerning Distributed Acoustic Sensing (DAS) measurements to analyze the flow along the wellbore.…”

Section: Introductionmentioning

confidence: 99%

Application of Fiber Optics for Completion Design Optimization: A Methodological Approach and Key Findings

Fathi,

Belyadi,

Adenan

et al. 2024

Fuels

View full text Add to dashboard Cite

This study investigates the application of fiber optic technology to optimize completion design in a hydraulic fracture stimulation for Marcellus Shale Reservoir. With a focus on improving cluster efficiencies and overcoming interstage communication challenges, the research utilizes real-time data from distributed acoustic (DAS), temperature (DTS), and strain (DSS) measurements. The methodology comprises a comprehensive analysis of completion and stimulation reports, fiber optics, microseismic data, and well logs. Conducted at the MSEEL well pads, MIP, and Boggess, and equipped with permanent and deployable fiber optic cables, this study emphasizes that engineered/geomechanical completion design leads to sustained cluster efficiency and stage production performance. Inefficient cluster efficiencies are primarily linked to fracture communication. Recommendations include employing a geomechanical completion design, avoiding non-uniform high natural fracture zones during hydraulic fracture stimulations, implementing short stage length, and using more 100 mesh sand. These insights, derived from correlations between fracture counts, distributed strain sensing (DSS), cluster efficiency, production logging, and production data, offer significant implications for optimizing completion design in unconventional reservoirs. The effective application of fiber optic technology, providing real-time DAS, DTS, and slow strain data, proves instrumental in addressing interstage communication challenges, contributing to improved reservoir performances and cost-effective operations in hydraulic fracture stimulations.

show abstract

“…This provides a new idea for optimizing the stimulation process of carbonate reservoirs in the Middle East. The hydraulic fracturing process of carbonate reservoirs is affected by many factors, which makes the fracture propagation mechanism complex [21,22], and it is difficult to control fracture propagation. Liu et al [23] modeled the distribution of natural fractures and cavities in carbonate reservoirs using the element partition method to study the interaction law of hydraulic fractures and cavities under different injection conditions.…”

Section: Introductionmentioning

confidence: 99%

Study on Optimization of Stimulation Technology of Heterogeneous Porous Carbonate Reservoir

Zhao,

Xu,

Wang

et al. 2024

Processes

View full text Add to dashboard Cite

Mishrif (M) reservoir of Faihaa (F) oilfield in Iraq is a heterogeneous porous carbonate reservoir. The reservoir properties of each reservoir unit differ greatly, and the distribution of porosity and permeability is non-uniform. Some reservoir units have the problem that the expected production cannot be achieved or the production decline rate is too fast after matrix acidification. This work optimized and compared the process of acid fracturing and hydraulic fracturing techniques. The Mishrif B (MB) and Mishrif C (MC) layers are selected as the target units for fracturing and the perforation intervals are optimized. The acid fracturing process adopted the acid fracturing technology of guar gum pad fluid and gelled acid multi-stage injection. According to the wellhead pressure limit and fracture propagation geometry, the pumping rate is optimized. The recommended maximum pumping rate of acid fracturing is 5.0 m3/min, and the optimized acid volume is 256.4 m3. The pressure changes during hydraulic fracturing and acid fracturing are different. It is recommended that the maximum hydraulic fracturing pump rate is 4.5 m3/min for MB and MC layers, and the amount of proppant in MB and MC layers is 37.5 m3 and 43.7 m3, respectively. The production prediction of two optimized processes is carried out. The results showed that the effect of acid fracturing in MB and MC layers is better than hydraulic fracturing, and it is recommended to adopt acid fracturing technology to stimulate MB and MC layers. Acid fracturing operation is carried out in the X-13 well, and better application results are achieved. The results of this study provide optimized reference ideas for reservoir stimulation in heterogeneous porous reservoirs.

show abstract

Studying the direction of hydraulic fracture in carbonate reservoirs: Using machine learning to determine reservoir pressure

Cited by 7 publications

References 33 publications

Application of GMDH model to predict pore pressure

Application of GMDH model to predict pore pressure

Application of Fiber Optics for Completion Design Optimization: A Methodological Approach and Key Findings

Study on Optimization of Stimulation Technology of Heterogeneous Porous Carbonate Reservoir

Contact Info

Product

Resources

About