Mechanistic Modeling of Distributed Strain Sensing DSS and Distributed Acoustic Sensing DAS to Assist Machine Learning Schemes Interpreting Unconventional Reservoir Datasets

2021 ◽  
Author(s):  
Kildare George Ramos Gurjao ◽  
Eduardo Gildin ◽  
Richard Gibson ◽  
Mark Everett
Keyword(s):  
Machine Learning ◽  
Hydraulic Fracturing ◽  
Field Data ◽  
Synthetic Data ◽  
Forward Modeling ◽  
Production Optimization ◽  
Acoustic Sensing ◽  
Fracture Opening ◽  
The Impact ◽  
Distributed Strain

Abstract The use of fiber optics in reservoir surveillance is bringing valuable insights to fracture geometry and fracture-hit identification, stage communication and perforation cluster fluid distribution in many hydraulic fracturing processes. However, given the complexity associated with field data, its interpretation is a major challenge faced by engineers and geoscientists. In this work, we propose to generate Distributed Strain/Acoustic Sensing (DSS/DAS) synthetic data of a cross-well fiber deployment that incorporate the physics governing hydraulic fracturing treatments. Our forward modeling is accurate enough to be reliably used in tandem with data-driven (machine learning) interpretation methods. The forward modeling is based on analytical and numerical solutions. The analytical solution is developed integrating two models: 2D fracture (e.g. Khristianovic-Geertsma-de Klerk known as KGD) and induced stress (e.g. Sneddon, 1946). DSS is estimated using the plane strain approach that combines calculated stresses and rock properties (e.g. Young's modulus and Poisson ratio). On the other hand, the numerical solution is implemented using the Displacement Discontinuity Method (DDM), a type of Boundary Element Method (BEM), with net pressure and/or shear stress as boundary condition. In this case, fiber gauge length concept is incorporated deriving displacement (i.e. DDM output) in space to obtain DSS values. In both methods DAS is estimated by the differentiation of DSS in time. The analytical technique considers a single fracture opening and is used in a sensitivity analysis to evaluate the impact that rock/fluid parameters can promote on strain time histories. Moreover, advanced cases including multiple fractures failing in tensile or shear mode are simulated applying the numerical technique. Results indicate that our models are able to capture typical characteristics present in field data: heart-shaped pattern from a fracture approaching the fiber, stress shadow and fracture hits. In particular, the numerical methodology captures relevant phenomenon associated with hydraulic and natural fractures interaction, and provides a solid foundation for generating accurate and rich synthetic data that can be used to support a physics-based machine learning interpretation framework. The developed forward modeling, when embedded in a classification or regression artificial intelligence framework, will be an important tool adding substantial insights related to field fracture systems that ultimately can lead to production optimization. Also, the development of specific packages (commercial or otherwise) that explicitly model both DSS and DAS, incorporating the impact of fracture opening and slippage on strain and strain rate, is still in its infancy. This paper is novel in this regard and opens up new avenues of research and applications of synthetic DAS/DSS in hydraulic fracturing processes.

Advanced Multi-Disciplinary Simulation Workflow for Well Placement, Hydraulic Fracturing and Production Optimization Applied to the Diyab Unconventional Play in Onshore UAE

2021 ◽  
Author(s):  
Hamid Pourpak ◽  
Samuel Taubert ◽  
Marios Theodorakopoulos ◽  
Arnaud Lefebvre-Prudencio ◽  
Chay Pointer ◽  
...  
Keyword(s):  
Hydraulic Fracturing ◽  
United Arab Emirates ◽  
Reservoir Characterization ◽  
Horizontal Wells ◽  
Production Optimization ◽  
Production Performance ◽  
Well Placement ◽  
Fully Integrated ◽  
Sector Model ◽  
The Impact

Abstract The Diyab play is an emerging unconventional play in the Middle East. Up to date, reservoir characterization assessments have proved adequate productivity of the play in the United Arab Emirates (UAE). In this paper, an advanced simulation and modeling workflow is presented, which was applied on selected wells located on an appraisal area, by integrating geological, geomechanical, and hydraulic fracturing data. Results will be used to optimize future well landing points, well spacing and completion designs, allowing to enhance the Stimulated Rock Volume (SRV) and its consequent production. A 3D static model was built, by propagating across the appraisal area, all subsurface static properties from core-calibrated petrophysical and geomechanical logs which originate from vertical pilot wells. In addition, a Discrete Fracture Network (DFN) derived from numerous image logs was imported in the model. Afterwards, completion data from one multi-stage hydraulically fracked horizontal well was integrated into the sector model. Simulations of hydraulic fracturing were performed and the sector model was calibrated to the real hydraulic fracturing data. Different scenarios for the fracture height were tested considering uncertainties related to the fracture barriers. This has allowed for a better understanding of the fracture propagation and SRV creation in the reservoir at the main target. In the last step, production resulting from the SRV was simulated and calibrated to the field data. In the end, the calibrated parameters were applied to the newly drilled nearby horizontal wells in the same area, while they were hydraulically fractured with different completion designs and the simulated SRVs of the new wells were then compared with the one calculated on the previous well. Applying a fully-integrated geology, geomechanics, completion and production workflow has helped us to understand the impact of geology, natural fractures, rock mechanical properties and stress regimes in the SRV geometry for the unconventional Diyab play. This work also highlights the importance of data acquisition, reservoir characterization and of SRV simulation calibration processes. This fully integrated workflow will allow for an optimized completion strategy, well landing and spacing for the future horizontal wells. A fully multi-disciplinary simulation workflow was applied to the Diyab unconventional play in onshore UAE. This workflow illustrated the most important parameters impacting the SRV creation and production in the Diyab formation for he studied area. Multiple simulation scenarios and calibration runs showed how sensitive the SRV can be to different parameters and how well placement and fracture jobs can be possibly improved to enhance the SRV creation and ultimately the production performance.

Data-Driven Optimization of Intermittent Gas Production in Mature Fields Assisted by Deep Learning and a Population-Based Global Optimizer

2021 ◽  
Author(s):  
Javier Fatou Gómez ◽  
Pejman Shoeibi Omrani ◽  
Stefan Philip Christian Belfroid
Keyword(s):  
Deep Learning ◽  
Field Data ◽  
Synthetic Data ◽  
Population Based ◽  
Gas Production ◽  
Production Optimization ◽  
Global Optimizer ◽  
Single Well ◽  
Production Increase ◽  
Operational Criteria

Abstract In gas wells, decreased/unstable production can occur due to difficult-to-predict dynamic effects resulted from late-life phenomena, such as liquid loading and flooding. To minimize the negative impact of these effects, maximize production and extend the wells’ lifetime, wells are often operated in an intermittent production regime. The goal of this work is to find the optimum production and shut-in cycles to maximize intermittent gas production as a decision support to operators. A framework suitable for single and multiple wells was developed by coupling a Deep Learning forward model trained on historical data with a population-based global optimizer, Particle Swarm Optimization (PSO). The forward model predicts the production rates and wellhead pressure during production and shut-in conditions, respectively. The PSO algorithm optimizes the operational criteria given operational and environmental objectives, such as maximizing production, minimizing start-up/shut-in actions, penalizing emissions under several constraints such as planned maintenances and meeting a contract production value. The accuracy of the Deep Learning models was tested on synthetic and field data. On synthetic data, mature wells were tested under different reservoir conditions such as initial water saturation, permeability and flow regimes. The relative errors in the predicted total cumulative production ranged between 0.5 and 4.6% for synthetic data and 0.9% for field data. The mean errors for pressure prediction were of 2-3 bar. The optimization framework was benchmarked for production optimization and contract value matching for a single-well (on field data) and a cluster of wells (synthetic data). Single-well production optimization of a North Sea well achieved a 3% production increase, including planned maintenances. Production optimization for six wells resulted in a 21% production increase for a horizon of 30 days, while contract value matching yielded 29/30 values within 3% of the target. The most optimum, repeatable and computationally efficient results were obtained using critical pressure/gas flowrates as operational criteria. This could enable real-time gas production optimization and operational decision-making in a wide range of well conditions and operational requirements.

Localizing microseismic events on field data using a U-Net based convolutional neural network trained on synthetic data

Geophysics ◽  
2021 ◽  
pp. 1-47
Author(s):  
N. A. Vinard ◽  
G. G. Drijkoningen ◽  
D. J. Verschuur
Keyword(s):  
Hydraulic Fracturing ◽  
Field Data ◽  
Synthetic Data ◽  
Region Of Interest ◽  
Velocity Model ◽  
Mitigation Measures ◽  
Large Field ◽  
Data Sets ◽  
Data Set ◽  
Full Waveforms

Hydraulic fracturing plays an important role when it comes to the extraction of resources in unconventional reservoirs. The microseismic activity arising during hydraulic fracturing operations needs to be monitored to both improve productivity and to make decisions about mitigation measures. Recently, deep learning methods have been investigated to localize earthquakes given field-data waveforms as input. For optimal results, these methods require large field data sets that cover the entire region of interest. In practice, such data sets are often scarce. To overcome this shortcoming, we propose initially to use a (large) synthetic data set with full waveforms to train a U-Net that reconstructs the source location as a 3D Gaussian distribution. As field data set for our study we use data recorded during hydraulic fracturing operations in Texas. Synthetic waveforms were modelled using a velocity model from the site that was also used for a conventional diffraction-stacking (DS) approach. To increase the U-Nets’ ability to localize seismic events, we augmented the synthetic data with different techniques, including the addition of field noise. We select the best performing U-Net using 22 events that have previously been identified to be confidently localized by DS and apply that U-Net to all 1245 events. We compare our predicted locations to DS and the DS locations refined by a relative location (DSRL) method. The U-Net based locations are better constrained in depth compared to DS and the mean hypocenter difference with respect to DSRL locations is 163 meters. This shows potential for the use of synthetic data to complement or replace field data for training. Furthermore, after training, the method returns the source locations in near real-time given the full waveforms, alleviating the need to pick arrival times.

scholarly journals Privacy Preserving Classification of EEG Data Using Machine Learning and Homomorphic Encryption

2021 ◽  
Vol 11 (16) ◽  
pp. 7360
Author(s):  
Andreea Bianca Popescu ◽  
Ioana Antonia Taca ◽  
Cosmin Ioan Nita ◽  
Anamaria Vizitiu ◽  
Robert Demeter ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Synthetic Data ◽  
Privacy Preserving ◽  
Supervised Machine Learning ◽  
Computational Time ◽  
Small Integer ◽  
Encrypted Data ◽  
The Impact

Data privacy is a major concern when accessing and processing sensitive medical data. A promising approach among privacy-preserving techniques is homomorphic encryption (HE), which allows for computations to be performed on encrypted data. Currently, HE still faces practical limitations related to high computational complexity, noise accumulation, and sole applicability the at bit or small integer values level. We propose herein an encoding method that enables typical HE schemes to operate on real-valued numbers of arbitrary precision and size. The approach is evaluated on two real-world scenarios relying on EEG signals: seizure detection and prediction of predisposition to alcoholism. A supervised machine learning-based approach is formulated, and training is performed using a direct (non-iterative) fitting method that requires a fixed and deterministic number of steps. Experiments on synthetic data of varying size and complexity are performed to determine the impact on runtime and error accumulation. The computational time for training the models increases but remains manageable, while the inference time remains in the order of milliseconds. The prediction performance of the models operating on encoded and encrypted data is comparable to that of standard models operating on plaintext data.

scholarly journals Machine learning on field data for hydraulic fracturing design optimization

2019 ◽  
Author(s):  
Renata Mutalova ◽  
Anton Morozov ◽  
Andrei Osiptsov ◽  
Albert Vainshtein ◽  
Evgeny Burnaev ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hydraulic Fracturing ◽  
Design Optimization ◽  
Field Data

Forecasting US movies box office performances in Turkey using machine learning algorithms

2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin
Keyword(s):  
Machine Learning ◽  
Global Economy ◽  
Learning Algorithms ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
High Stakes ◽  
Box Office ◽  
Industry Forecast ◽  
The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Sign in / Sign up

Export Citation Format

Share Document