Machine learning to improve natural gas reservoir simulations

2022 ◽  
pp. 55-82
Author(s):  
Abouzar Choubineh ◽  
Jie Chen ◽  
Frans Coenen ◽  
Fei Ma ◽  
David A. Wood
Keyword(s):  
Machine Learning ◽  
Natural Gas ◽  
Gas Reservoir ◽  
Reservoir Simulations

scholarly journals Quantitative study on natural gas production risk of Carboniferous gas reservoir in eastern Sichuan

2021 ◽  
Author(s):  
Guo Yu ◽  
Haitao Li ◽  
Yanru Chen ◽  
Linqing Liu ◽  
Chenyu Wang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Risk Factor ◽  
Natural Gas ◽  
Gas Production ◽  
Probability Method ◽  
Gas Reservoir ◽  
Production Risk ◽  
Probability Interval ◽  
Natural Gas Production ◽  
Stable Production

AbstractQuantifying natural gas production risk can help guide natural gas exploration and development in Carboniferous gas reservoirs. In this study, the Monte Carlo probability method is used to obtain the probability distribution and growth curve of each production risk factor and production in a Carboniferous gas reservoir in eastern Sichuan. In addition, the fuzzy comprehensive evaluation method is used to conduct the sensitivity analysis of the risk factors, and the natural gas production and realization probability under different risk factors are obtained. The research results show that: (1) the risk factor–production growth curve and probability distribution are calculated by the Monte Carlo probability method. The average annual production under the stable production stage under different realization probabilities is obtained. The maximum probability range of annual production is $$\left( {43.43 - 126.35} \right) \times 10^{8} {\text{m}}^{3} /{\text{year}}$$ 43.43 - 126.35 × 10 8 m 3 / year , and the probability range is 14.59–92.88%. (2) The risk factor sensitivity analysis is significantly affected by the probability interval. In the entire probability interval, the more sensitive risk factors are the average production of the kilometer-deep well (D) and the production rate in the stable production stage (A). During the exploration and development of natural gas, these two risk factors can be adjusted to increase production.

Application of Machine Learning in Gas-Hydrate Formation and Trendline Prediction

2021 ◽  
Author(s):  
Celestine Udim Monday ◽  
Toyin Olabisi Odutola
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Natural Gas ◽  
Gas Hydrate ◽  
Gas Flow ◽  
Flow Line ◽  
Learning Algorithms ◽  
Hydrate Formation ◽  
Machine Learning Algorithms ◽  
Gas Hydrate Formation

Abstract Natural Gas production and transportation are at risk of Gas hydrate plugging especially when in offshore environments where temperature is low and pressure is high. These plugs can eventually block the pipeline, increase back pressure, stop production and ultimately rupture gas pipelines. This study seeks to develops machine learning models after a kinetic inhibitor to predict the gas hydrate formation and pressure changes within the natural gas flow line. Green hydrate inhibitor A, B and C were obtained as plant extracts and applied in low dosages (0.01 wt.% to 0.1 wt.%) on a 12meter skid-mounted hydrate closed flow loop. From the data generated, the optimal dosages of inhibitor A, B and C were observed to be 0.02 wt.%, 0.06 wt.% and 0.1 wt.% respectively. The data associated with these optimal dosages were fed to a set of supervised machine learning algorithms (Extreme gradient boost, Gradient boost regressor and Linear regressor) and a deep learning algorithm (Artificial Neural Network). The output results from the set of supervised learning algorithms and Deep Learning algorithms were compared in terms of their accuracies in predicting the hydrate formation and the pressure within the natural gas flow line. All models had accuracies greater than 90%. This result show that the application Machine learning to solving flow assurance problems is viable. The results show that it is viable to apply machine learning algorithms to solve flow assurance problems, analyzing data and getting reports which can improve accuracy and speed of on-site decision making process.

scholarly journals Split Sales of Gas

1971 ◽  
Vol 9 (3) ◽  
pp. 496
Author(s):  
Robert C. Muir
Keyword(s):  
Natural Gas ◽  
Gas Reservoir ◽  
Gas Industry ◽  
Natural Gas Industry ◽  
Gas Market

The Natural Gas Industry is highly competitive and once a gas reservoir is discovered the various producers are anxious to enter into Gas Purchase Contracts. The contracts are with different purchasers and on different terms giving rise to split stream deliveries - there would never be any split stream problems if all producers made simultaneous deliveries to one or more purchasers in exactly the same volumes at exactly the same price. This article examines the position of the producers in the gas reservoir in the absence of an agreement and then discusses different contractual methods which the producers may use to resolve the conflict between the Doctrine of Correlative Rights and the Rule of Capture, such as gas market sharing contracts, cash adjustments, gas balancing schemes and deferred production agreements. To further complicate the problems of 'the producer in dealing with split sales of gas, the lessee-producer must keep in mind the interests of the lessor-royalty owner. The article concludes with a consideration of the interest of the royalty owner in the prepayment received by the producer and in the price for which the producer is selling the gas.

Economic Comparison of Alternatives for a Stranded Offshore Gas Reservoir

2021 ◽  
Vol 73 (08) ◽  
pp. 63-64
Author(s):  
Chris Carpenter
Keyword(s):  
Natural Gas ◽  
Economic Feasibility ◽  
Sensitivity Analyses ◽  
Pricing Models ◽  
Gas Reservoirs ◽  
Gas Reservoir ◽  
Pipe Length ◽  
Offshore Technology ◽  
University Of Oklahoma ◽  
Natural Gas Industry

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 30732, “Economic Feasibility Study of Several Usage Alternatives for a Stranded Offshore Gas Reservoir,” by Khoi Viet Trinh, SPE, and Rouzbeh G. Moghanloo, SPE, University of Oklahoma, prepared for the 2020 Offshore Technology Conference, originally scheduled to be held in Houston, 4–7 May. The paper has not been peer reviewed. Copyright 2020 Offshore Technology Conference. Reproduced by permission. This paper compares economics of a floating liquefied natural gas (FLNG) project with those of an onshore LNG plant and gas-to-wire (GTW) processes. Sensitivity analyses and tornado charts are used to evaluate the importance of various uncertain parameters associated with FLNG construction and operation. This study will be helpful for future considerations in using FLNG to convert offshore gas reservoirs previously considered stranded into economically viable resources. The results from this economic model can play a key role in the future of the natural gas industry and energy market in West Africa. Assumptions Before presenting different economic scenarios, the following assumptions must be established: * The pipeline will have the correct diameter, pressure rating, and metallurgy to transport produced gas. Only the pipe length will be considered a variable. * Operating expenses (OPEX) of both onshore LNG and FLNG will be the same. Realistically, however, OPEX of FLNG will be different from that of onshore LNG. * A subsidy from the Nigerian government has been obtained for the onshore LNG plant. * The electricity price is assumed to be $0.25/kWh. * An assumed upstream cost of $2/Mscf to cover onshore LNG gas pretreatment is assumed. * The onshore LNG plant and FLNG will have the same lifespan. However, in reality, availability of FLNG can be lower than that of onshore LNG. Pricing Models FNLG. Because of the relative recency of FNLG, few pricing models have been readily available. For the complete paper, Shell’s Prelude project is the basis for pricing of FLNG. Prelude costs averaged out to approximately $14 billion, which will be used as the cost of the facility for the FLNG scenario in the economic analysis.

Sign in / Sign up

Export Citation Format

Share Document