Evaluating gas production performances in marcellus using data mining technologies

Zhou, Qin; Dilmore, Robert; Kleit, Andrew N.; Wang, John Yilin

doi:10.1016/j.jngse.2014.06.014

Cited by 47 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, it has been found in the literature that the lateral length in horizontal shale gas wells is a key factor in determining gas production since the lateral length determines the area of contact with the shale gas reservoir . However, each one of the existing reservoirs has different lateral length ranges due to their geology and many times the optimal lateral length is not the longest.…”

Section: Methodsmentioning

confidence: 99%

Development and Evaluation of Deep Learning Models for Forecasting Gas Production and Flowback Water in Shale Gas Reservoirs

López-Flores

Lira-Barragán

Rubio-Castro

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In this paper, deep learning models are developed based on a multilayer perceptron to forecast 12 month cumulative produced shale gas and 90 day produced flowback water using a study area within the Eagle Ford Formation as a database. These models can help decision-makers have important references when drilling new wells. Latitude, longitude, true vertical depth, lateral longitude, total proppant, and total fracture water are used as input variables. The trained models are evaluated in a study area within the Burgos Basin to analyze the energy benefits, freshwater consumption, and flowback water produced through well drilling for the first time in Mexico. A non-dominated sorting genetic algorithm is used for the minimization of total freshwater consumption and maximization of cumulative produced gas. The multilayer perceptron models showed good results. The coefficient of determination and the mean absolute error of the single-output models remained above 0.93 and below 3.00 for the validation set, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Development and Evaluation of Deep Learning Models for Forecasting Gas Production and Flowback Water in Shale Gas Reservoirs

López-Flores

Lira-Barragán

Rubio-Castro

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…9) shows some problems with correlated variables. A solution will be to use principal components (PCs) as variables in the model (Everitt and Hothorn 2009;Hastie et al 2009;Jolliffe 2002;Zhou et al 2014). An additional advantage of using PC is for dimensionality reduction when the number of covariates is high.…”

Section: Bakken Formationmentioning

confidence: 99%

“…Siddiqui, et al (2019) used machine learning modes to study fluid type variation and completion optimization in the Eagleford. Zhou et al (2014) applied data mining techniques to evaluate gas production performance in the Marcellus. Wigwe et al (2019a, b) presented both spatial and neural network techniques to analyze Bakken oil production while Zargari and Mohaghegh (2010) showed an application of machine learning models for the Bakken field development planning.…”

Section: Introductionmentioning

confidence: 99%

Comparative evaluation of multi-basin production performance and application of spatio-temporal models for unconventional oil and gas production prediction

Wigwe

Bougre

Watson

et al. 2020

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Modern data analytic techniques, statistical and machine-learning algorithms have received widespread applications for solving oil and gas problems. As we face problems of parent–child well interactions, well spacing, and depletion concerns, it becomes necessary to model the effect of geology, completion design, and well parameters on production using models that can capture both spatial and temporal variability of the covariates on the response variable. We accomplish this using a well-formulated spatio-temporal (ST) model. In this paper, we present a multi-basin study of production performance evaluation and applications of ST models for oil and gas data. We analyzed dataset from 10,077 horizontal wells from 2008 to 2019 in five unconventional formations in the USA: Bakken, Marcellus, Eagleford, Wolfcamp, and Bone Spring formations. We evaluated well production performance and performance of new completions over time. Results show increased productivity of oil and gas since 2008. Also, the Bakken wells performed better for the counties evaluated. We present two methods for fitting spatio-temporal models: fixed rank kriging and ST generalized additive models using thin plate and cubic regression splines as basis functions in the spline-based smooths. Results show a significant effect on production by the smooth term, accounting for between 60 and 95% of the variability in the six-month production. Overall, we saw a better production response to completions for the gas formations compared to oil-rich plays. The results highlight the benefits of spatio-temporal models in production prediction as it implicitly accounts for geology and technological changes with time.

show abstract

“…These studies have examined economic factors (e.g., economic growth) [14][15][16][17][18], social factors (e.g., legislation and politics) [19][20][21][22][23], technical factors (e.g., improved mining technology) [24][25][26], and external environment factors (e.g., geopolitics of natural gas and international environment) [27][28][29][30][31]. There have also been some integrated studies, both quantitative and qualitative, that have analyzed the impacts of multiple factors on a natural gas supply system.…”

Section: Literature Review Of Analysis Of Natural Gas Supply Systemmentioning

confidence: 99%

An Assessment of the Security of China’s Natural Gas Supply System Using Two Network Models

Zhang

Lü

2015

Energies

View full text Add to dashboard Cite

Abstract:In the context of climate change, natural gas is becoming increasingly important for low-carbon development in China. The gap between the demand and supply of natural gas, domestically, and China's high dependence on foreign sources, highlights the importance of ensuring a secure system for supplying natural gas in the country. This study applied ecological network analysis, a powerful systems-oriented method, to simulate interactions between different nodes of the natural gas supply system and to evaluate the system's security level. Two network models were constructed at the regional and national layers, respectively, by dividing external natural gas suppliers into multiple regions and countries. These models were used to evaluate the overall security level and related characteristics of China's natural gas supply system from 2000 to 2012. The results showed stable improvement in the system's security during this period. With the exceptions of some specific indicators (e.g., the mutualism index (MI)), analyses of network information and structure yielded the mostly similar results for the two models. In conclusion, a regional layer (RL) network model is considered more economical than a national layer (NL) model for evaluating the overall security of China's natural gas supply system, especially when available data are limited.

show abstract

Evaluating gas production performances in marcellus using data mining technologies

Cited by 47 publications

References 11 publications

Development and Evaluation of Deep Learning Models for Forecasting Gas Production and Flowback Water in Shale Gas Reservoirs

Development and Evaluation of Deep Learning Models for Forecasting Gas Production and Flowback Water in Shale Gas Reservoirs

Comparative evaluation of multi-basin production performance and application of spatio-temporal models for unconventional oil and gas production prediction

An Assessment of the Security of China’s Natural Gas Supply System Using Two Network Models

Contact Info

Product

Resources

About