Hybrid Data Driven Approach for Reservoir Production Forecast

2021 ◽  
Author(s):  
Achraf Ourir ◽  
Jed Oukmal ◽  
Baptiste Rondeleux ◽  
Zinyat Agharzayeva ◽  
Philippe Barrault
Keyword(s):  
Data Science ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Machine Learning Algorithms ◽  
Analytical Models ◽  
Reservoir Engineering ◽  
Full Data ◽  
Production Forecast ◽  
Data Set ◽  
Well Completion

Abstract Analytical models, in particular Decline Curve Analysis (DCA) are widely used in the oil and gas industry. However, they are often solely based on production data from the declining wells and do not leverage the other data available in the field e.g. petrophysics at well, completion length, distance to contacts... This paper describes a workflow to quickly build hybrid models for reservoir production forecast based on a mix of classic reservoir methods and machine learning algorithms. This workflow is composed of three main steps applied on a well by well basis. First, we build an object called forecaster which contains the subject matter knowledge. This forecaster can represent parametric functions trained on the well itself or more complex models that learn from a larger data set (production and petrophysics data, synthesis properties). Secondly this forecaster is tested on a subset of production history to qualify it. Finally, the full data set is used to forecast the production profile. It has been applied to all fluids (oil, water, gas, liquid) and revealed particularly useful for fields with large number of wells and long history, as an alternative to classical simulations when grid models are too complex or difficult to history match. Two use cases from conventional and unconventional fields will be presented in which this workflow helped quickly generate robust forecast for existing wells (declining or non-declining) and new wells. This workflow brings the technology, structure and measurability of Data Science to Reservoir Engineering. It enables the application of the state of the art data science methods to solve concrete reservoir engineering problems. In addition, forecast results can be confronted to historical data using what we call "Blind Testing" which allows a quantification of the forecast uncertainty and avoid biases. Finally, the automated workflow has been used to generate a range of possible realizations and allows the quantification the uncertainty associated with the models.

Data Science Applied to Pedagogical Methodologies Focused on Changing the Negative Perception of the Oil and Gas Industry in Colombia

2020 ◽  
Author(s):  
Israel Guevara ◽  
David Ardila ◽  
Kevin Daza ◽  
Oscar Ovalle ◽  
Paola Pastor ◽  
...  
Keyword(s):  
Data Science ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Gas Industry ◽  
Negative Perception

Boosting Algorithm Choice in Predictive Machine Learning Models for Fracturing Applications

2021 ◽  
Author(s):  
Abdul Muqtadir Khan
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Injection Rate ◽  
Model Construction ◽  
Gradient Boosting ◽  
Light Gradient ◽  
Fracture Damage ◽  
Boosting Technique

Abstract With the advancement in machine learning (ML) applications, some recent research has been conducted to optimize fracturing treatments. There are a variety of models available using various objective functions for optimization and different mathematical techniques. There is a need to extend the ML techniques to optimize the choice of algorithm. For fracturing treatment design, the literature for comparative algorithm performance is sparse. The research predominantly shows that compared to the most commonly used regressors and classifiers, some sort of boosting technique consistently outperforms on model testing and prediction accuracy. A database was constructed for a heterogeneous reservoir. Four widely used boosting algorithms were used on the database to predict the design only from the output of a short injection/falloff test. Feature importance analysis was done on eight output parameters from the falloff analysis, and six were finalized for the model construction. The outputs selected for prediction were fracturing fluid efficiency, proppant mass, maximum proppant concentration, and injection rate. Extreme gradient boost (XGBoost), categorical boost (CatBoost), adaptive boost (AdaBoost), and light gradient boosting machine (LGBM) were the algorithms finalized for the comparative study. The sensitivity was done for a different number of classes (four, five, and six) to establish a balance between accuracy and prediction granularity. The results showed that the best algorithm choice was between XGBoost and CatBoost for the predicted parameters under certain model construction conditions. The accuracy for all outputs for the holdout sets varied between 80 and 92%, showing robust significance for a wider utilization of these models. Data science has contributed to various oil and gas industry domains and has tremendous applications in the stimulation domain. The research and review conducted in this paper add a valuable resource for the user to build digital databases and use the appropriate algorithm without much trial and error. Implementing this model reduced the complexity of the proppant fracturing treatment redesign process, enhanced operational efficiency, and reduced fracture damage by eliminating minifrac steps with crosslinked gel.

Evaluation of Machine-Learning Tools for Predicting Sand Production

2021 ◽  
Author(s):  
Afungchwi Ronald Ngwashi ◽  
David O. Ogbe ◽  
Dickson O. Udebhulu
Keyword(s):  
Machine Learning ◽  
Niger Delta ◽  
Oil And Gas ◽  
Back Propagation ◽  
Oil And Gas Industry ◽  
Learning Tools ◽  
Sand Production ◽  
Data Set ◽  
Test Set ◽  
Gas Industry

Abstract Data analytics has only recently picked the interest of the oil and gas industry as it has made data visualization much simpler, faster, and cost-effective. This is driven by the promising innovative techniques in developing artificial intelligence and machine-learning tools to provide sustainable solutions to ever-increasing problems of the petroleum industry activities. Sand production is one of these real issues faced by the oil and gas industry. Understanding whether a well will produce sand or not is the foundation of every completion job in sandstone formations. The Niger Delta Province is a region characterized by friable and unconsolidated sandstones, therefore it's more prone to sanding. It is economically unattractive in this region to design sand equipment for a well that will not produce sand. This paper is aimed at developing a fast and more accurate machine-learning algorithm to predict sanding in sandstone formations. A two-layered Artificial Neural Network (ANN) with back-propagation algorithm was developed using PYTHON programming language. The algorithm uses 11 geological and reservoir parameters that are associated with the onset of sanding. These parameters include depth, overburden, pore pressure, maximum and minimum horizontal stresses, well azimuth, well inclination, Poisson's ratio, Young's Modulus, friction angle, and shale content. Data typical of the Niger Delta were collected to validate the algorithm. The data was further split into a training set (70%) and a test set (30%). Statistical analyses of the data yielded correlations between the parameters and were plotted for better visualization. The accuracy of the ANN algorithm is found to depend on the number of parameters, number of epochs, and the size of the data set. For a completion engineer, the answer to the question of whether or not a well will require sand production control is binary-either a well will produce sand or it does not. Support vector machines (SVM) are known to be better suited as the machine-learning tools for binary identification. This study also presents a comparative analysis between ANN and SVM models as tools for predicting sand production. Analysis of the Niger Delta data set indicated that SVM outperformed ANN model even when the training data set is sparse. Using the 30% test set, ANN gives an accuracy, precision, recall, and F1 - Score of about 80% while the SVM performance was 100% for the four metrics. It is then concluded that machine learning tools such as ANN with back-propagation and SVM are simple, accurate, and easy-to-use tools for effectively predicting sand production.

A New Approach To Estimating Ultimate Recovery for Multistage Hydraulically Fractured Horizontal Wells by Utilizing Completion Parameters Using Machine Learning

2021 ◽  
pp. 1-16
Author(s):  
Sulaiman A. Alarifi ◽  
Jennifer Miskimins
Keyword(s):  
Oil And Gas ◽  
Horizontal Wells ◽  
Oil And Gas Industry ◽  
Gas Industry ◽  
New Approach ◽  
History Data ◽  
Well Completion ◽  
Production History ◽  
Early Production ◽  
Fractured Horizontal Wells

Summary Reserves estimation is an essential part of developing any reservoir. Predicting the long-term production performance and estimated ultimate recovery (EUR) in unconventional wells has always been a challenge. Developing a reliable and accurate production forecast in the oil and gas industry is mandatory because it plays a crucial part in decision-making. Several methods are used to estimate EUR in the oil and gas industry, and each has its advantages and limitations. Decline curve analysis (DCA) is a traditional reserves estimation technique that is widely used to estimate EUR in conventional reservoirs. However, when it comes to unconventional reservoirs, traditional methods are frequently unreliable for predicting production trends for low-permeability plays. In recent years, many approaches have been developed to accommodate the high complexity of unconventional plays and establish reliable estimates of reserves. This paper provides a methodology to predict EUR for multistage hydraulically fractured horizontal wells that outperforms many current methods, incorporates completion data, and overcomes some of the limitations of using DCA or other traditional methods to forecast production. This new approach is introduced to predict EUR for multistage hydraulically fractured horizontal wells and is presented as a workflow consisting of production history matching and forecasting using DCA combined with artificial neural network (ANN) predictive models. The developed workflow combines production history data, forecasting using DCA models and completion data to enhance EUR predictions. The predictive models use ANN techniques to predict EUR given short early production history data (3 months to 2 years). The new approach was developed and tested using actual production and completion data from 989 multistage hydraulically fractured horizontal wells from four different formations. Sixteen models were developed (four models for each formation) varying in terms of input parameters, structure, and the production history data period it requires. The developed models showed high accuracy (correlation coefficients of 0.85 to 0.99) in predicting EUR given only 3 months to 2 years of production data. The developed models use production forecasts from different DCA models along with well completion data to improve EUR predictions. Using completion parameters in predicting EUR along with the typical DCA is a major addition provided by this study. The end product of this work is a comprehensive workflow to predict EUR that can be implemented in different formations by using well completion data along with early production history data.

Machine Learning Techniques for Internet of Things

2019 ◽  
pp. 160-180
Author(s):  
P. Priakanth ◽  
S. Gopikrishnan
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Independent Learning ◽  
Machine Learning Techniques ◽  
Analytical Models ◽  
Guided Learning ◽  
Learning Techniques ◽  
Learning Machine

The idea of an intelligent, independent learning machine has fascinated humans for decades. The philosophy behind machine learning is to automate the creation of analytical models in order to enable algorithms to learn continuously with the help of available data. Since IoT will be among the major sources of new data, data science will make a great contribution to make IoT applications more intelligent. Machine learning can be applied in cases where the desired outcome is known (guided learning) or the data is not known beforehand (unguided learning) or the learning is the result of interaction between a model and the environment (reinforcement learning). This chapter answers the questions: How could machine learning algorithms be applied to IoT smart data? What is the taxonomy of machine learning algorithms that can be adopted in IoT? And what are IoT data characteristics in real-world which requires data analytics?

Machine Learning Techniques for Internet of Things

2021 ◽  
pp. 1490-1506
Author(s):  
P. Priakanth ◽  
S. Gopikrishnan
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Independent Learning ◽  
Machine Learning Techniques ◽  
Analytical Models ◽  
Guided Learning ◽  
Learning Techniques ◽  
Learning Machine

The idea of an intelligent, independent learning machine has fascinated humans for decades. The philosophy behind machine learning is to automate the creation of analytical models in order to enable algorithms to learn continuously with the help of available data. Since IoT will be among the major sources of new data, data science will make a great contribution to make IoT applications more intelligent. Machine learning can be applied in cases where the desired outcome is known (guided learning) or the data is not known beforehand (unguided learning) or the learning is the result of interaction between a model and the environment (reinforcement learning). This chapter answers the questions: How could machine learning algorithms be applied to IoT smart data? What is the taxonomy of machine learning algorithms that can be adopted in IoT? And what are IoT data characteristics in real-world which requires data analytics?

Subsurface engineering of CCUS in Australia (case studies)

2019 ◽  
Vol 59 (2) ◽  
pp. 762
Author(s):  
Mohammad B. Bagheri ◽  
Matthias Raab
Keyword(s):  
Uncertainty Analysis ◽  
Case Studies ◽  
Oil And Gas ◽  
Co2 Storage ◽  
Oil And Gas Industry ◽  
Reservoir Engineering ◽  
Co2 Injection ◽  
Gas Industry ◽  
Co2 Plume

Carbon capture utilisation and storage (CCUS) is a rapidly emerging field in the Australian oil and gas industry to address carbon emissions while securing reliable energy. Although there are similarities with many aspects of the oil and gas industry, subsurface CO2 storage has some unique geology and geophysics, and reservoir engineering considerations, for which we have developed specific workflows. This paper explores the challenges and risks that a reservoir engineer might face during a field-scale CO2 injection project, and how to address them. We first explain some of the main concepts of reservoir engineering in CCUS and their synergy with oil and gas projects, followed by the required inputs for subsurface studies. We will subsequently discuss the importance of uncertainty analysis and how to de-risk a CCUS project from the subsurface point of view. Finally, two different case studies will be presented, showing how the CCUS industry should use reservoir engineering analysis, dynamic modelling and uncertainty analysis results, based on our experience in the Otway Basin. The first case study provides a summary of CO2CRC storage research injection results and how we used the dynamic models to history match the results and understand CO2 plume behaviour in the reservoir. The second case study shows how we used uncertainty analysis to improve confidence on the CO2 plume behaviour and to address regulatory requirements. An innovative workflow was developed for this purpose in CO2CRC to understand the influence of each uncertainty parameter on the objective functions and generate probabilistic results.

Wheel Box Test Aeromechanical Verification of New First Stage Bucket With Integrated Cover Plates for MS5002 GT

2019 ◽  
Author(s):  
Marco Mariottini ◽  
Nicola Pieroni ◽  
Pietro Bertini ◽  
Beniamino Pacifici ◽  
Alessandro Giorgetti
Keyword(s):  
Gas Turbine ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Response Assessment ◽  
Operating Conditions ◽  
Analytical Models ◽  
Gas Industry ◽  
Improved Performance ◽  
Cover Plates

Abstract In the oil and gas industry, manufacturers are continuously engaged in providing machines with improved performance, reliability and availability. First Stage Bucket is one of the most critical gas turbine components, bearing the brunt of very severe operating conditions in terms of high temperature and stresses; aeromechanic behavior is a key characteristic to be checked, to assure the absence of resonances that can lead to damage. Aim of this paper is to introduce a method for aeromechanical verification applied to the new First Stage Bucket for heavy duty MS5002 gas turbine with integrated cover plates. This target is achieved through a significantly cheaper and streamlined test (a rotating test bench facility, formally Wheel Box Test) in place of a full engine test. Scope of Wheel Box Test is the aeromechanical characterization for both Baseline and New bucket, in addition to the validation of the analytical models developed. Wheel Box Test is focused on the acquisition and visualization of dynamic data, simulating different forcing frequencies, and the measurement of natural frequencies, compared with the expected results. Moreover, a Finite Elements Model (FEM) tuning for frequency prediction is performed. Finally, the characterization of different types of dampers in terms of impact on frequencies and damping effect is carried out. Therefore, in line with response assessment and damping levels estimation, the most suitable damper is selected. The proposed approach could be extended for other machine models and for mechanical audits.

CEO Entrenchment and Corporate Hedging: Evidence from the Oil and Gas Industry

2013 ◽  
Vol 48 (3) ◽  
pp. 887-917 ◽  
Author(s):  
Praveen Kumar ◽  
Ramon Rabinovitch
Keyword(s):  
Cash Flow ◽  
Financial Distress ◽  
Agency Costs ◽  
Oil And Gas ◽  
Price Volatility ◽  
Chief Executive ◽  
Oil And Gas Industry ◽  
Free Cash Flow ◽  
Data Set ◽  
Corporate Hedging

AbstractUsing a unique data set with detailed information on the derivative positions of upstream oil and gas firms during 1996–2008, we find that hedging intensity is positively related to factors that amplify chief executive officer (CEO) entrenchment and free cash flow agency costs. There is also robust evidence that hedging is motivated by the reduction of financial distress and borrowing costs, and that it is influenced by both intrinsic cash flow risk and temporary spikes in commodity price volatility. We present a comprehensive perspective on the determinants of corporate hedging, and the results are consistent with the predictions of the risk management and agency costs literatures.

Sign in / Sign up

Export Citation Format

Share Document