A Data-Driven Approach to Predict the Breakdown Pressure of the Tight and Unconventional Formation

2021 ◽  
Author(s):  
Zeeshan Tariq ◽  
Murtada Saleh Aljawad ◽  
Mobeen Murtaza ◽  
Mohamed Mahmoud ◽  
Dhafer Al-Shehri ◽  
...  
Keyword(s):  
Neural Network ◽  
Hydraulic Fracturing ◽  
Rock Properties ◽  
Breakdown Pressure ◽  
Rock Samples ◽  
In Situ Stresses ◽  
Fracturing Fluids ◽  
The Neural Network ◽  
Different Types

Abstract Unconventional reservoirs are characterized by their extremely low permeabilities surrounded by huge in-situ stresses. Hydraulic fracturing is a most commonly used stimulation technique to produce from such reservoirs. Due to high in situ stresses, breakdown pressure of the rock can be too difficult to achieve despite of reaching maximum pumping capacity. In this study, a new model is proposed to predict the breakdown pressures of the rock. An extensive experimental study was carried out on different cylindrical specimens and the hydraulic fracturing stimulation was performed with different fracturing fluids. Stimulation was carried out to record the rock breakdown pressure. Different types of fracturing fluids such as slick water, linear gel, cross-linked gels, guar gum, and heavy oil were tested. The experiments were carried out on different types of rock samples such as shales, sandstone, and tight carbonates. An extensive rock mechanical study was conducted to measure the elastic and failure parameters of the rock samples tested. An artificial neural network was used to correlate the breakdown pressure of the rock as a function of fracturing fluids, experimental conditions, and rock properties. Fracturing fluid properties included injection rate and fluid viscosity. Rock properties included were tensile strength, unconfined compressive strength, Young's Modulus, Poisson's ratio, porosity, permeability, and bulk density. In the process of data training, we analyzed and optimized the parameters of the neural network, including activation function, number of hidden layers, number of neurons in each layer, training times, data set division, and obtained the optimal model suitable for prediction of breakdown pressure. With the optimal setting of the neural network, we were successfully able to predict the breakdown pressure of the unconventional formation with an accuracy of 95%. The proposed method can greatly reduce the prediction cost of rock breakdown pressure before the fracturing operation of new wells and provides an optional method for the evaluation of tight oil reservoirs.

Predicting Hydraulic Fracturing in a Carbonate Gas Reservoir in Abu Dhabi Using 1D Mechanical Earth Model: Uncertainty and Constraints

2015 ◽  
Author(s):  
Manhal Sirat ◽  
Mujahed Ahmed ◽  
Xing Zhang
Keyword(s):  
Hydraulic Fracturing ◽  
Hydraulic Fracture ◽  
Natural Fracture ◽  
Abu Dhabi ◽  
Hydraulic Fractures ◽  
Gas Reservoir ◽  
In Situ Stresses ◽  
Tight Carbonate ◽  
Different Depths

Abstract In-situ stress state plays an important role in controlling fracture growth and containment in hydraulic fracturing managements. It is evident that the mechanical properties, existing stress regime and the natural fracture network of its reservoir rocks and the surrounding formations mainly control the geometry, size and containments of produced hydraulic fractures. Furthermore, the three principal in situ stresses' axes swap directions and magnitudes at different depths giving rise to identifying different mechanical bedrocks with corresponding stress regimes at different depths. Hence predicting the hydro-fractures can be theoretically achieved once all the above data are available. This is particularly difficult in unconventional and tight carbonate reservoirs, where heterogeneity and highly stress variation, in terms of magnitude and orientation, are expected. To optimize the field development plan (FDP) of a tight carbonate gas reservoir in Abu Dhabi, 1D Mechanical Earth Models (MEMs), involving generating the three principal in-situ stresses' profiles and mechanical property characterization with depth, have been constructed for four vertical wells. The results reveal the swap of stress magnitudes at different mechanical layers, which controls the dimension and orientation of the produced hydro-fractures. Predicted containment of the Hydro-fractures within the specific zones is likely with inevitable high uncertainty when the stress contrast between Sv, SHmax with Shmin respectively as well as Young's modulus and Poisson's Ratio variations cannot be estimated accurately. The uncertainty associated with this analysis is mainly related to the lacking of the calibration of the stress profiles of the 1D MEMs with minifrac and/or XLOT data, and both mechanical and elastic properties with rock mechanic testing results. This study investigates the uncertainty in predicting hydraulic fracture containment due to lacking such calibration, which highlights that a complete suite of data, including calibration of 1D MEMs, is crucial in hydraulic fracture treatment.

A Novel Method and its Application to Define Maximum Horizontal Stress and Stress Path

2021 ◽  
Author(s):  
Jianguo Zhang ◽  
Karthik Mahadev ◽  
Stephen Edwards ◽  
Alan Rodgerson
Keyword(s):  
Fracture Initiation ◽  
Stress Path ◽  
Horizontal Stress ◽  
Geomechanical Model ◽  
Breakdown Pressure ◽  
In Situ Stresses ◽  
Fracture Closure ◽  
Minimum Horizontal Stress ◽  
Maximum Horizontal Stress

Abstract Maximum horizontal stress (SH) and stress path (change of SH and minimum horizontal stress with depletion) are the two most difficult parameters to define for an oilfield geomechanical model. Understanding these in-situ stresses is critical to the success of operations and development, especially when production is underway, and the reservoir depletion begins. This paper introduces a method to define them through the analysis of actual minifrac data. Field examples of applications on minifrac failure analysis and operational pressure prediction are also presented. It is commonly accepted that one of the best methods to determine the minimum horizontal stress (Sh) is the use of pressure fall-off analysis of a minifrac test. Unlike Sh, the magnitude of SH cannot be measured directly. Instead it is back calculated by using fracture initiation pressure (FIP) and Sh derived from minifrac data. After non-depleted Sh and SH are defined, their apparent Poisson's Ratios (APR) are calculated using the Eaton equation. These APRs define Sh and SH in virgin sand to encapsulate all other factors that influence in-situ stresses such as tectonic, thermal, osmotic and poro-elastic effects. These values can then be used to estimate stress path through interpretation of additional minifrac data derived from a depleted sand. A geomechanical model is developed based on APRs and stress paths to predict minifrac operation pressures. Three cases are included to show that the margin of error for FIP and fracture closure pressure (FCP) is less than 2%, fracture breakdown pressure (FBP) less than 4%. Two field cases in deep-water wells in the Gulf of Mexico show that the reduction of SH with depletion is lower than that for Sh.

scholarly journals High-Resolution Sea Surface Temperature and Salinity in the Global Ocean from Raw Satellite Data

2019 ◽  
Vol 11 (19) ◽  
pp. 2191 ◽  
Author(s):  
Encarni Medina-Lopez ◽  
Leonardo Ureña-Fuentes
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Satellite Data ◽  
Google Earth ◽  
Sea Surface ◽  
Global Ocean ◽  
The Neural Network ◽  
Wide Range ◽  
Sentinel 2

The aim of this work is to obtain high-resolution values of sea surface salinity (SSS) and temperature (SST) in the global ocean by using raw satellite data (i.e., without any band data pre-processing or atmospheric correction). Sentinel-2 Level 1-C Top of Atmosphere (TOA) reflectance data is used to obtain accurate SSS and SST information. A deep neural network is built to link the band information with in situ data from different buoys, vessels, drifters, and other platforms around the world. The neural network used in this paper includes shortcuts, providing an improved performance compared with the equivalent feed-forward architecture. The in situ information used as input for the network has been obtained from the Copernicus Marine In situ Service. Sentinel-2 platform-centred band data has been processed using Google Earth Engine in areas of 100 m × 100 m. Accurate salinity values are estimated for the first time independently of temperature. Salinity results rely only on direct satellite observations, although it presented a clear dependency on temperature ranges. Results show the neural network has good interpolation and extrapolation capabilities. Test results present correlation coefficients of 82 % and 84 % for salinity and temperature, respectively. The most common error for both SST and SSS is 0.4 ∘ C and 0 . 4 PSU. The sensitivity analysis shows that outliers are present in areas where the number of observations is very low. The network is finally applied over a complete Sentinel-2 tile, presenting sensible patterns for river-sea interaction, as well as seasonal variations. The methodology presented here is relevant for detailed coastal and oceanographic applications, reducing the time for data pre-processing, and it is applicable to a wide range of satellites, as the information is directly obtained from TOA data.

scholarly journals The Behavior of VLF/LF Variations Associated with Geomagnetic Activity, Earthquakes, and the Quiet Condition Using a Neural Network Approach

Entropy ◽  
2018 ◽  
Vol 20 (9) ◽  
pp. 691 ◽  
Author(s):  
Irina Popova ◽  
Alexandr Rozhnoi ◽  
Maria Solovieva ◽  
Danila Chebrov ◽  
Masashi Hayakawa
Keyword(s):  
Neural Network ◽  
Radio Wave ◽  
Seismic Activity ◽  
Low Frequency ◽  
Magnetic Storms ◽  
Network Approach ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Different Types ◽  
Parameters Of Seismicity

The neural network approach is proposed for studying very-low- and low-frequency (VLF and LF) subionospheric radio wave variations in the time vicinities of magnetic storms and earthquakes, with the purpose of recognizing anomalies of different types. We also examined the days with quiet geomagnetic conditions in the absence of seismic activity, in order to distinguish between the disturbed signals and the quiet ones. To this end, we trained the neural network (NN) on the examples of the representative database. The database included both the VLF/LF data that was measured during four-year monitoring at the station in Petropavlovsk-Kamchatsky, and the parameters of seismicity in the Kuril-Kamchatka and Japan regions. It was shown that the neural network can distinguish between the disturbed and undisturbed signals. Furthermore, the prognostic behavior of the VLF/LF variations indicative of magnetic and seismic activity has a different appearance in the time vicinity of the earthquakes and magnetic storms.

Rock properties and in-situ stress state of the Egilabria Prospect, Lawn Hill Platform, Queensland

2019 ◽  
Vol 59 (1) ◽  
pp. 383 ◽  
Author(s):  
Adam H. E. Bailey ◽  
Liuqi Wang ◽  
Lisa Hall ◽  
Paul Henson
Keyword(s):  
In Situ Stress ◽  
Rock Properties ◽  
Resource Potential ◽  
North West ◽  
Reservoir Volume ◽  
Geological Surveys ◽  
In Situ Stresses ◽  
Petroleum Resource ◽  
Gas Potential

The Energy component of Geoscience Australia’s Exploring for the Future (EFTF) program is aimed at improving our understanding of the petroleum resource potential of northern Australia, in partnership with the state and territory geological surveys. The sediments of the Mesoproterozoic South Nicholson Basin and the underlying Paleoproterozoic Isa Superbasin in the Northern Territory and Queensland are amongst the primary targets of the EFTF Energy program, as they are known to contain organic-rich sedimentary units with the potential to host unconventional gas plays, although their subsurface extent under the cover of the Georgina Basin is presently unknown. In order to economically produce from unconventional reservoirs, the petrophysical rock properties and in-situ stresses must be conducive to the creation of secondary permeability networks that connect a wellbore to as large a reservoir volume as possible. This study utilises data from the recently drilled Armour Energy wells Egilabria 2, Egilabria 2-DW1, and Egilabria 4 to constrain rock properties and in-situ stresses for the Isa Superbasin sequence where intersected on the Lawn Hill Platform of north-west Queensland. These results have implications for petroleum prospectivity in an area with proven gas potential, which are discussed here in the context of the rock properties and in-situ stresses desired for a viable shale gas play. In addition, these results are relevant to potential future exploration across the broader Isa Superbasin sequence.

High-resolution sea surface salinity and temperature in coastal areas from Sentinel-2 and Copernicus Marine in situ data

2020 ◽  
Author(s):  
Encarni Medina-Lopez
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Sea Surface ◽  
Sea Surface Salinity ◽  
Global Ocean ◽  
Surface Salinity ◽  
In Situ Data ◽  
The Neural Network ◽  
Sentinel 2

<p>The aim of this work is to obtain high-resolution values of sea surface salinity (SSS) and temperature (SST) in the global ocean by using raw satellite data (i.e., without any band data pre-processing or atmospheric correction). Sentinel-2 Level 1-C Top of Atmosphere (TOA) reflectance data is used to obtain accurate SSS and SST information. A deep neural network is built to link the band information with in situ data from different buoys, vessels, drifters, and other platforms around the world. The neural network used in this paper includes shortcuts, providing an improved performance compared with the equivalent feed-forward architecture. The in situ information used as input for the network has been obtained from the Copernicus Marine In situ Service. Sentinel-2 platform-centred band data has been processed using Google Earth Engine in areas of 100 m x 100 m. Accurate salinity values are estimated for the first time independently of temperature. Salinity results rely only on direct satellite observations, although it presented a clear dependency on temperature ranges. Results show the neural network has good interpolation and extrapolation capabilities. Test results present correlation coefficients of 82% and 84% for salinity and temperature, respectively. The most common error for both SST and SSS is 0.4 C and 0.4 PSU. The sensitivity analysis shows that outliers are present in areas where the number of observations is very low. The network is finally applied over a complete Sentinel-2 tile, presenting sensible patterns for river-sea interaction, as well as seasonal variations. The methodology presented here is relevant for detailed coastal and oceanographic applications, reducing the time for data pre-processing, and it is applicable to a wide range of satellites, as the information is directly obtained from TOA data.</p>

Determination of In-Situ Stresses From Hydraulically Fractured Spherical Cavities

1983 ◽  
Vol 105 (2) ◽  
pp. 125-127 ◽  
Author(s):  
W. E. Warren
Keyword(s):  
Hydraulic Fracturing ◽  
Principal Stress ◽  
Spherical Cavity ◽  
Hydraulic Fractures ◽  
Stress Measurements ◽  
In Situ Stresses ◽  
Spherical Cavities ◽  
Stress Directions

Several problems in analysis can arise in estimating in-situ stresses from standard hydraulic fracturing operations if the borehole is not aligned with one of the principal stress directions. In these nonaligned situations, the possibility of fracturing a spherical cavity for estimating the in-situ stresses is investigated. The theory utilizes all the advantages of direct stress measurements associated with hydraulic fracturing and eliminates the geometrical problems associated with the analysis of hydraulic fractures in cylindrical boreholes.

scholarly journals A Precision Agricultural Application: Manggis Fruit Classification Using Hybrid Deep Learning

2021 ◽  
Vol 35 (5) ◽  
pp. 375-381
Author(s):  
Putra Sumari ◽  
Wan Muhammad Azimuddin Wan Ahmad ◽  
Faris Hadi ◽  
Muhammad Mazlan ◽  
Nur Anis Liyana ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Stochastic Gradient Descent ◽  
Traditional Methods ◽  
High Performing ◽  
The Neural Network ◽  
Different Types ◽  
Filter Size ◽  
Fully Connected ◽  
Convolution Filters

Fruits come in different variants and subspecies. While some subspecies of fruits can be easily differentiated, others may require an expertness to differentiate them. Although farmers rely on the traditional methods to identify and classify fruit types, the methods are prone to so many challenges. Training a machine to identify and classify fruit types in place of traditional methods can ensure precision fruit classification. By taking advantage of the state-of-the-art image recognition techniques, we approach fruits classification from another perspective by proposing a high performing hybrid deep learning which could ensure precision mangosteen fruit classification. This involves a proposed optimized Convolutional Neural Network (CNN) model compared to other optimized models such as Xception, VGG16, and ResNet50 using Adam, RMSprop, Adagrad, and Stochastic Gradient Descent (SGD) optimizers on specified dense layers and filters numbers. The proposed CNN model has three types of layers that make up its model, they are: 1) the convolutional layers, 2) the pooling layers, and 3) the fully connected (FC) layers. The first convolution layer uses convolution filters with a filter size of 3x3 used for initializing the neural network with some weights prior to updating to a better value for each iteration. The CNN architecture is formed from stacking these layers. Our self-acquired dataset which is composed of four different types of Malaysian mangosteen fruit, namely Manggis Hutan, Manggis Mesta, Manggis Putih and Manggis Ungu was employed for the training and testing of the proposed CNN model. The proposed CNN model achieved 94.99% classification accuracy higher than the optimized Xception model which achieved 90.62% accuracy in the second position.

Sign in / Sign up

Export Citation Format

Share Document