Principal components methodology – A novel approach to forecasting production from liquid-rich shale (LRS) reservoirs

Makinde, Ibukun; Lee, W. John

doi:10.1016/j.petlm.2018.08.002

Cited by 5 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA creates new low-dimensional components that can better describe the data distribution of multivariate data. The main variables that simulate the early-mid-term behavior of the shale reservoir were extracted [40,41].…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Method of Data-Driven Deep Learning Model to Predict Well Production Rate in the Shale Gas Reservoirs

Han

Kwon

2021

Energies

View full text Add to dashboard Cite

Reservoir modeling to predict shale reservoir productivity is considerably uncertain and time consuming. Since we need to simulate the physical phenomenon of multi-stage hydraulic fracturing. To overcome these limitations, this paper presents an alternative proxy model based on data-driven deep learning model. Furthermore, this study not only proposes the development process of a proxy model, but also verifies using field data for 1239 horizontal wells from the Montney shale formation in Alberta, Canada. A deep neural network (DNN) based on multi-layer perceptron was applied to predict the cumulative gas production as the dependent variable. The independent variable is largely divided into four types: well information, completion and hydraulic fracturing and production data. It was found that the prediction performance was better when using a principal component with a cumulative contribution of 85% using principal component analysis that extracts important information from multivariate data, and when predicting with a DNN model using 6 variables calculated through variable importance analysis. Hence, to develop a reliable deep learning model, sensitivity analysis of hyperparameters was performed to determine one-hot encoding, dropout, activation function, learning rate, hidden layer number and neuron number. As a result, the best prediction of the mean absolute percentage error of the cumulative gas production improved to at least 0.2% and up to 9.1%. The novel approach of this study can also be applied to other shale formations. Furthermore, a useful guide for economic analysis and future development plans of nearby reservoirs.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Method of Data-Driven Deep Learning Model to Predict Well Production Rate in the Shale Gas Reservoirs

Han

Kwon

2021

Energies

View full text Add to dashboard Cite

show abstract

“…Studying a certain problem involves many variables; if there is a correlation between these variables, then there must be one or more common factors that dominate the data. Based on variable covariance or correlation matrices, original variables are combined to form comprehensive variables (principal components) (Makinde and Lee 2019). These comprehensive variables play a critical role in simplifying the problem while preserving the main information of the original variables, thereby making it easier to understand the main contradictions when studying complex problems (Lam et al 2020;Mao et al 2018).…”

Section: Principal Component Analysismentioning

confidence: 99%

Influence of geological factors on coal permeability in the Sihe coal mine

Zou

Zhang

She

et al. 2022

Int J Coal Sci Technol

View full text Add to dashboard Cite

Permeability of coal reservoirs influence the extraction of coal gas from coal seams. Twelve coal samples were collected at an anticline and a syncline of the No. 3 coal seam in the Sihe coal mine. Porosity, permeability, pore size, vitrinite reflectance, and liquid nitrogen adsorption of the samples were evaluated. Structural curvatures at the sample locations, and the distance between the sampling locations and the nearest faults were calculated based on seismic data. The influences of the evaluated parameters on permeability were analyzed. Major factors that influence permeability of the No. 3 coal seam were extracted using principal component analysis (PCA). Based on the porosity–permeability model derived from the Archie formula and classic Kozeny–Carman equation, we deduced that the permeability of coal increased with an increase in porosity. With an increase in average vitrinite reflectance, permeability decreases first and then increases. PCA results showed that coal permeability was regulated by three key components representing three modes. The first component included pore size, depth, and pore complexity accounting for 52.59% of the variability indicating that it was the most important in controlling permeability. The second component included specific surface area, structural curvature, and porosity, and the third component comprised of specific surface area, porosity, and average vitrinite reflectance. Overall, pore diameter and complexity had significant effects on coal permeability. The results show that researchers and stakeholders must consider the interactions among multiple factors rather than single factors to understand the influences on permeability to facilitate efficient utilization of coalbed methane resources.

show abstract

RETRACTED ARTICLE: Assessing the nexus between financial development and energy finance through demand- and supply-oriented physical disruption in crude oil

Chien

Zhang

Hsu

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

Since 1970, numerous governments have established strategic petroleum reserves (SPRs) in relation to oil supply interruptions. In this study, important oil reserves, physical oil supply disruption and social welfare losses due to physical distribution of oil supply have been measured. The physical oil supply disruption has been measured in the form of oil supply vulnerability index and oil volatility index of the South Asian economies. Analysis reveals that the accumulation and drawdown of important national crude oil strategic petroleum reserves where the state wants to optimize individual social welfare while individuals hold over stock optimize their earnings levels. The monetary deciding factors utilize the government’s optimum important stockpile policy and simultaneously the amount and economic factors vital for the nongovernment market to actuate the optimum accumulation and nonaccumulation of important fossil fuels stockpile. Additionally, findings show that India is the lowest crude oil insecure country while Afghanistan and Bangladesh are the highest insecure countries in terms of oil supply. India’s topmost mark shows a bigger possibility to alter the fossil fuels producers while Afghanistan, Bangladesh, Bhutan and Nepal have the minimum mark corroborating the group as the utmost producer risk exposed nations.

show abstract

Principal components methodology – A novel approach to forecasting production from liquid-rich shale (LRS) reservoirs

Cited by 5 publications

References 6 publications

Application of Machine Learning Method of Data-Driven Deep Learning Model to Predict Well Production Rate in the Shale Gas Reservoirs

Application of Machine Learning Method of Data-Driven Deep Learning Model to Predict Well Production Rate in the Shale Gas Reservoirs

Influence of geological factors on coal permeability in the Sihe coal mine

RETRACTED ARTICLE: Assessing the nexus between financial development and energy finance through demand- and supply-oriented physical disruption in crude oil

Contact Info

Product

Resources

About