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.

Optimization Proration Research in Volcanic Reservoir in Songnan Gas Field

2012 ◽  
Vol 616-618 ◽  
pp. 858-863
Author(s):  
Hua Liu ◽  
Zhi Liang Shi ◽  
Xiang Fang Li ◽  
Yun Cong Gao
Keyword(s):  
Production Method ◽  
Gas Production ◽  
Production Optimization ◽  
Gas Field ◽  
Field Development ◽  
Volcanic Reservoir ◽  
Geological Conditions ◽  
High Efficient ◽  
Single Well ◽  
Line Technology

Volcanic Reservoir in Songnan gas field is now in the early development, the scale of the single well and stable development put forward important requirements, reasonable match is efficient in gas reservoir development of the key. According to the geological conditions of volcanic rock reservoirs special, in the full analysis of the dynamic and static data, and on the basis of preliminary mastered the gas, water relations; And the use of gas production method, the method of curve, economic boundary method and the improvement of horizontal Wells method of the gas line technology reasonable production optimization and argument, high efficient and economical for gas field development.

Training deep networks with only synthetic data: Deep-learning-based near-offset reconstruction for closed-loop surface-related multiple estimation on shallow-water field data

Geophysics ◽  
2021 ◽  
pp. 1-32
Author(s):  
Shan Qu ◽  
Eric Verschuur ◽  
Dong Zhang ◽  
Yangkang Chen
Keyword(s):  
Deep Learning ◽  
Shallow Water ◽  
Network Architecture ◽  
Field Data ◽  
Closed Loop ◽  
Waveform Inversion ◽  
Synthetic Data ◽  
Water Layer ◽  
Limited Information ◽  
Loop Surface

Accurate removal of surface-related multiples remains a challenge in shallow-water cases. One reason is that the success of the surface-related multiple estimation (SRME) related algorithms is sensitive to the quality of the near-offset reconstruction. When it comes to a larger missing gap and a shallower water-bottom, the state-of-the-art near-offset gap construction method — parabolic Radon transform (PRT) — fails to provide a reliable recovery of the shallow reflections due to the limited information from the data and highly curved events at near offsets with strong lateral amplitude variations. Therefore, we propose a novel workflow, which first deploys a deep-learning(DL)-based reconstruction of the shallow reflections and then uses the reconstructed data as the input for the subsequent surface multiple removal. In particular, we use a convolutional neural network architecture --- U-net, which was developed from convolutional autoencoders with extra direct skip connections between different levels of encoders and the corresponding decoders. Instead of using field data directly in network training, the training set is carefully synthesized based on the prior water-layer information of the field data; thus, a fully sampled field dataset, which is hard to obtain, is not needed for training in the proposed workflow. An inversion-based approach — closed-loop surface-related multiple estimation (CL-SRME) -- is used for the surface multiple removal, in which the primaries are directly estimated via full waveform inversion in a data-driven manner. Finally, the effectiveness of the proposed workflow is demonstrated based on a 2D North Sea field data in a shallow-water scenario (92.5 m water depth) with a relatively large minimum offset (150 m).

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.

scholarly journals Real UAV-Bird Image Classification Using CNN with a Synthetic Dataset

2021 ◽  
Vol 11 (9) ◽  
pp. 3863
Author(s):  
Ali Emre Öztürk ◽  
Ergun Erçelebi
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Synthetic Data ◽  
Real Data ◽  
Corner Detection ◽  
Batch Size ◽  
Test Accuracy ◽  
Classification Problems ◽  
Auc Value ◽  
Classification Test

A large amount of training image data is required for solving image classification problems using deep learning (DL) networks. In this study, we aimed to train DL networks with synthetic images generated by using a game engine and determine the effects of the networks on performance when solving real-image classification problems. The study presents the results of using corner detection and nearest three-point selection (CDNTS) layers to classify bird and rotary-wing unmanned aerial vehicle (RW-UAV) images, provides a comprehensive comparison of two different experimental setups, and emphasizes the significant improvements in the performance in deep learning-based networks due to the inclusion of a CDNTS layer. Experiment 1 corresponds to training the commonly used deep learning-based networks with synthetic data and an image classification test on real data. Experiment 2 corresponds to training the CDNTS layer and commonly used deep learning-based networks with synthetic data and an image classification test on real data. In experiment 1, the best area under the curve (AUC) value for the image classification test accuracy was measured as 72%. In experiment 2, using the CDNTS layer, the AUC value for the image classification test accuracy was measured as 88.9%. A total of 432 different combinations of trainings were investigated in the experimental setups. The experiments were trained with various DL networks using four different optimizers by considering all combinations of batch size, learning rate, and dropout hyperparameters. The test accuracy AUC values for networks in experiment 1 ranged from 55% to 74%, whereas the test accuracy AUC values in experiment 2 networks with a CDNTS layer ranged from 76% to 89.9%. It was observed that the CDNTS layer has considerable effects on the image classification accuracy performance of deep learning-based networks. AUC, F-score, and test accuracy measures were used to validate the success of the networks.

scholarly journals A Novel Deep Learning-Based Diagnosis Method Applied to Power Quality Disturbances

Energies ◽  
2021 ◽  
Vol 14 (10) ◽  
pp. 2839
Author(s):  
Artvin-Darien Gonzalez-Abreu ◽  
Miguel Delgado-Prieto ◽  
Roque-Alfredo Osornio-Rios ◽  
Juan-Jose Saucedo-Dorantes ◽  
Rene-de-Jesus Romero-Troncoso
Keyword(s):  
Deep Learning ◽  
Power Quality ◽  
Electrical Power ◽  
Synthetic Data ◽  
Industrial Sector ◽  
Industrial Facilities ◽  
Diagnosis Method ◽  
Neural Network Structure ◽  
Power Quality Disturbances ◽  
Disturbance Detection

Monitoring electrical power quality has become a priority in the industrial sector background: avoiding unwanted effects that affect the whole performance at industrial facilities is an aim. The lack of commercial equipment capable of detecting them is a proven fact. Studies and research related to these types of grid behaviors are still a subject for which contributions are required. Although research has been conducted for disturbance detection, most methodologies consider only a few standardized disturbance combinations. This paper proposes an innovative deep learning-based diagnosis method to be applied on power quality disturbances, and it is based on three stages. Firstly, a domain fusion approach is considered in a feature extraction stage to characterize the electrical power grid. Secondly, an adaptive pattern characterization is carried out by considering a stacked autoencoder. Finally, a neural network structure is applied to identify disturbances. The proposed approach relies on the training and validation of the diagnosis system with synthetic data: single, double and triple disturbances combinations and different noise levels, also validated with available experimental measurements provided by IEEE 1159.2 Working Group. The proposed method achieves nearly a 100% hit rate allowing a far more practical application due to its capability of pattern characterization.

scholarly journals New Hybrid Approach for Developing Automated Machine Learning Workflows: A Real Case Application in Evaluation of Marcellus Shale Gas Production

Fuels ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 286-303
Author(s):  
Vuong Van Pham ◽  
Ebrahim Fathi ◽  
Fatemeh Belyadi
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Shale Gas ◽  
Field Data ◽  
Marcellus Shale ◽  
Hybrid Approach ◽  
Gas Production ◽  
Bayesian Optimization ◽  
Real Field ◽  
Engineering Problems

The success of machine learning (ML) techniques implemented in different industries heavily rely on operator expertise and domain knowledge, which is used in manually choosing an algorithm and setting up the specific algorithm parameters for a problem. Due to the manual nature of model selection and parameter tuning, it is impossible to quantify or evaluate the quality of this manual process, which in turn limits the ability to perform comparison studies between different algorithms. In this study, we propose a new hybrid approach for developing machine learning workflows to help automated algorithm selection and hyperparameter optimization. The proposed approach provides a robust, reproducible, and unbiased workflow that can be quantified and validated using different scoring metrics. We have used the most common workflows implemented in the application of artificial intelligence (AI) and ML in engineering problems including grid/random search, Bayesian search and optimization, genetic programming, and compared that with our new hybrid approach that includes the integration of Tree-based Pipeline Optimization Tool (TPOT) and Bayesian optimization. The performance of each workflow is quantified using different scoring metrics such as Pearson correlation (i.e., R2 correlation) and Mean Square Error (i.e., MSE). For this purpose, actual field data obtained from 1567 gas wells in Marcellus Shale, with 121 features from reservoir, drilling, completion, stimulation, and operation is tested using different proposed workflows. A proposed new hybrid workflow is then used to evaluate the type well used for evaluation of Marcellus shale gas production. In conclusion, our automated hybrid approach showed significant improvement in comparison to other proposed workflows using both scoring matrices. The new hybrid approach provides a practical tool that supports the automated model and hyperparameter selection, which is tested using real field data that can be implemented in solving different engineering problems using artificial intelligence and machine learning. The new hybrid model is tested in a real field and compared with conventional type wells developed by field engineers. It is found that the type well of the field is very close to P50 predictions of the field, which shows great success in the completion design of the field performed by field engineers. It also shows that the field average production could have been improved by 8% if shorter cluster spacing and higher proppant loading per cluster were used during the frac jobs.

scholarly journals SEX, GENDER AND CARDIOVASCULAR HEALTH, AN ANALYSIS OF SYNTHETIC DATA FROM A POPULATION BASED STUDY

2021 ◽  
Vol 77 (18) ◽  
pp. 3258
Author(s):  
Zahra Azizi ◽  
Louise Pilote ◽  
Valeria Raparelli ◽  
Colleen Norris ◽  
Karolina Kublickiene ◽  
...  
Keyword(s):  
Cardiovascular Health ◽  
Synthetic Data ◽  
Population Based ◽  
Population Based Study

scholarly journals A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data

2021 ◽  
Vol 210 ◽  
pp. 106371
Author(s):  
Elisa Moya-Sáez ◽  
Óscar Peña-Nogales ◽  
Rodrigo de Luis-García ◽  
Carlos Alberola-López
Keyword(s):  
Deep Learning ◽  
Synthetic Data ◽  
Learning Approach ◽  
And Training ◽  
Synthetic Mri

scholarly journals Evaluation of natural gas production optimization in Kailashtila gas field in Bangladesh using decline curve analysis method

2015 ◽  
Vol 50 (1) ◽  
pp. 29-38 ◽  
Author(s):  
MS Shah ◽  
HMZ Hossain
Keyword(s):  
Production System ◽  
Gas Production ◽  
Curve Analysis ◽  
Production Optimization ◽  
Reservoir Pressure ◽  
Gas Field ◽  
Wellhead Pressure ◽  
Decline Curve Analysis ◽  
Decline Curve ◽  
Overall Performance

Decline curve analysis of well no KTL-04 from the Kailashtila gas field in northeastern Bangladesh has been examined to identify their natural gas production optimization. KTL-04 is one of the major gas producing well of Kailashtila gas field which producing 16.00 mmscfd. Conventional gas production methods depend on enormous computational efforts since production systems from reservoir to a gathering point. The overall performance of a gas production system is determined by flow rate which is involved with system or wellbore components, reservoir pressure, separator pressure and wellhead pressure. Nodal analysis technique is used to performed gas production optimization of the overall performance of the production system. F.A.S.T. Virtu Well™ analysis suggested that declining reservoir pressure 3346.8, 3299.5, 3285.6 and 3269.3 psi(a) while signifying wellhead pressure with no changing of tubing diameter and skin factor thus daily gas production capacity is optimized to 19.637, 24.198, 25.469, and 26.922 mmscfd, respectively.Bangladesh J. Sci. Ind. Res. 50(1), 29-38, 2015

Sign in / Sign up

Export Citation Format

Share Document