Short-Term Forecasting of Well Production Based on a Hybrid Probabilistic Approach

2021 ◽  
Author(s):  
Anton Sergeevich Evseenkov ◽  
Denis Kamilevich Kuchkildin ◽  
Konstantin Igorevich Krechetov ◽  
Semyon Alexandrovich Ospishchev ◽  
Victor Sergeevich Kotezhekov ◽  
...  
Keyword(s):  
Probabilistic Approach ◽  
Hybrid Approach ◽  
Material Balance ◽  
Real Data ◽  
Small Error ◽  
Real Field ◽  
Short Term ◽  
Well Production ◽  
Bayes Formula ◽  
Production History

Abstract The presented article is dedicated to creation and testing of probabilistic ensemble computational tool for operational forecasting of well production in short term (STF). The ensemble consisted of models based on such physical and mathematical tools as: the equation of non-stationary filtration, material balance, Darcy's law and machine learning models. After calculations by each model, their forecasts are combined into a single ensemble forecast. The hybrid approach is based on the Monte Carlo method on Markov chains as a separate probabilistic model using Bayes’ formula. In this case, statistical weights of each model (the degree of confidence in each model) is determined in the form of a probability distribution based on the reliability of previously performed forecasts. The test results presented in this article were obtained on the real field data. The obtained forecasts of individual models and the ensemble were compared to real data. Real data tool usage analysis showed that the proposed approach gives a small error in comparison with actual measurements. Efficiency of calculations allows to automatically adapt the model to the entire well production history (several hundred wells) within a few hours.

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 Photovoltaic Prediction Software: Evaluation with Real Data from Northern Spain

2021 ◽  
Vol 11 (11) ◽  
pp. 5025
Author(s):  
David González-Peña ◽  
Ignacio García-Ruiz ◽  
Montserrat Díez-Mediavilla ◽  
Mª. Isabel Dieste-Velasco ◽  
Cristina Alonso-Tristán
Keyword(s):  
Energy Production ◽  
Field Data ◽  
Real Data ◽  
Software Tools ◽  
Horizontal Axis ◽  
Real Field ◽  
Tracking Systems ◽  
Northern Spain ◽  
Commercial Software ◽  
Solar Tracking

Prediction of energy production is crucial for the design and installation of PV plants. In this study, five free and commercial software tools to predict photovoltaic energy production are evaluated: RETScreen, Solar Advisor Model (SAM), PVGIS, PVSyst, and PV*SOL. The evaluation involves a comparison of monthly and annually predicted data on energy supplied to the national grid with real field data collected from three real PV plants. All the systems, located in Castile and Leon (Spain), have three different tilting systems: fixed mounting, horizontal-axis tracking, and dual-axis tracking. The last 12 years of operating data, from 2008 to 2020, are used in the evaluation. Although the commercial software tools were easier to use and their installations could be described in detail, their results were not appreciably superior. In annual global terms, the results hid poor estimations throughout the year, where overestimations were compensated by underestimated results. This fact was reflected in the monthly results: the software yielded overestimates during the colder months, while the models showed better estimates during the warmer months. In most studies, the deviation was below 10% when the annual results were analyzed. The accuracy of the software was also reduced when the complexity of the dual-axis solar tracking systems replaced the fixed installation.

scholarly journals Can Long-Term Experiments Predict Real Field N and P Balance and System Sustainability? Results from Maize, Winter Wheat, and Soybean Trials Using Mineral and Organic Fertilisers

Agronomy ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1472
Author(s):  
Ilaria Piccoli ◽  
Felice Sartori ◽  
Riccardo Polese ◽  
Maurizio Borin ◽  
Antonio Berti
Keyword(s):  
Winter Wheat ◽  
Nutrient Balance ◽  
Environmental Indicators ◽  
Nutrient Loss ◽  
Real Field ◽  
Short Term ◽  
Organic Fertiliser ◽  
Long Term Experiments ◽  
P Balance

Agri-environmental indicators such as nutrient balance may play a key role in soil and water quality monitoring, although short-term experiments might be unable to capture the sustainability of cropping systems. Therefore, the objectives of this study are: (i) to evaluate the reliability of long-term experimental N and P balance estimates to predict real field (RF) (i.e., short-term transitory) conditions; and (ii) to compare the sustainability of short- and long-term experiments. The LTE-based predictions showed that crops are generally over-fertilised in RF conditions, particularly maize. Nutrient balance predictions based on the LTE data tended to be more optimistic than those observed under RF conditions, which are often characterised by lower outputs; in particular, 13, 44, and 47% lower yields were observed for winter wheat, maize, and soybean, respectively, under organic management. The graphical evaluation of N and P use efficiency demonstrated the benefit of adopting crop rotation practices and the risk of nutrient loss when liquid organic fertiliser was applied on a long-term basis. In conclusion, LTE predictions may depend upon specific RF conditions, representing potential N and P use efficiencies that, in RF, may be reduced by crop yield-limiting factors and the specific implemented crop sequence.

Short Term Injection Re-Distribution STIR: Real-Time Waterflood Optimization Technique Using Advanced Data Analytics

2021 ◽  
Author(s):  
Gaurav Modi ◽  
Manu Ujjwal ◽  
Srungeer Simha
Keyword(s):  
Real Time ◽  
Data Analytics ◽  
Optimization Technique ◽  
Material Balance ◽  
Oil Production ◽  
Data Driven ◽  
Petroleum Engineering ◽  
Short Term ◽  
Injection Water ◽  
Facility Level

Abstract Short Term Injection Re-distribution (STIR) is a python based real-time WaterFlood optimization technique for brownfield assets that uses advanced data analytics. The objective of this technique is to generate recommendations for injection water re-distribution to maximize oil production at the facility level. Even though this is a data driven technique, it is tightly bounded by Petroleum Engineering principles such as material balance etc. The workflow integrates and analyse short term data (last 3-6 months) at reservoir, wells and facility level. STIR workflow is divided into three modules: Injector-producer connectivity Injector efficiency Injection water optimization First module uses four major data types to estimate the connectivity between each injector-producer pair in the reservoir: Producers data (pressure, WC, GOR, salinity) Faults presence Subsurface distance Perforation similarity – layers and kh Second module uses connectivity and watercut data to establish the injector efficiency. Higher efficiency injectors contribute most to production while poor efficiency injectors contribute to water recycling. Third module has a mathematical optimizer to maximize the oil production by re-distributing the injection water amongst injectors while honoring the constraints at each node (well, facility etc.) of the production system. The STIR workflow has been applied to 6 reservoirs across different assets and an annual increase of 3-7% in oil production is predicted. Each recommendation is verified using an independent source of data and hence, the generated recommendations align very well with the reservoir understanding. The benefits of this technique can be seen in 3-6 months of implementation in terms of increased oil production and better support (pressure increase) to low watercut producers. The inherent flexibility in the workflow allows for easy replication in any Waterflooded Reservoir and works best when the injector well count in the reservoir is relatively high. Geological features are well represented in the workflow which is one of the unique functionalities of this technique. This method also generates producers bean-up and injector stimulation candidates opportunities. This low cost (no CAPEX) technique offers the advantages of conventional petroleum engineering techniques and Data driven approach. This technique provides a great alternative for WaterFlood management in brownfield where performing a reliable conventional analysis is challenging or at times impossible. STIR can be implemented in a reservoir from scratch in 3-6 weeks timeframe.

Short Term Electric Load Forecasting with Back Propagation Neural Network and Simulated Annealing Genetic Algorithm

2015 ◽  
Vol 785 ◽  
pp. 14-18 ◽  
Author(s):  
Badar ul Islam ◽  
Zuhairi Baharudin ◽  
Perumal Nallagownden
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Simulated Annealing ◽  
Hybrid Approach ◽  
Back Propagation ◽  
Forecast Accuracy ◽  
Back Propagation Neural Network ◽  
Search Performance ◽  
Training Algorithm ◽  
Short Term

Although, Back Propagation Neural Network are frequently implemented to forecast short-term electricity load, however, this training algorithm is criticized for its slow and improper convergence and poor generalization. There is a great need to explore the techniques that can overcome the above mentioned limitations to improve the forecast accuracy. In this paper, an improved BP neural network training algorithm is proposed that hybridizes simulated annealing and genetic algorithm (SA-GA). This hybrid approach leads to the integration of powerful local search capability of simulated annealing and near accurate global search performance of genetic algorithm. The proposed technique has shown better results in terms of load forecast accuracy and faster convergence. ISO New England data for the period of five years is employed to develop a case study that validates the efficacy of the proposed technique.

Sign in / Sign up

Export Citation Format

Share Document