Assisted history matching in shale gas well using multiple-proxy-based Markov chain Monte Carlo algorithm: The comparison of K-nearest neighbors and neural networks as proxy model

•A new assisted history matching workflow for shale gas reservoirs was developed.•K-nearest neighbors and neural networks as proxy model was compared.•Hydraulic fracture properties were identified in a probabilistic manner.•Hydraulic fractures were modeled using EDFM. We performed assisted history m...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Fuel (Guildford) Ročník 262; s. 116563
Hlavní autoři:	Tripoppoom, Sutthaporn, Ma, Xinhua, Yong, Rui, Wu, Jianfa, Yu, Wei, Sepehrnoori, Kamy, Miao, Jijun, Li, Ning
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Kidlington Elsevier Ltd 15.02.2020 Elsevier BV
Témata:	Algorithms Assisted history matching Bayesian analysis Computer simulation Design optimization Economic forecasting EDFM Gas wells K-nearest neighbors Markov analysis Markov chain Monte Carlo Markov chains Mathematical models Monte Carlo simulation Neural networks Parameter robustness Parameter uncertainty Permeability Probability theory Shale Shale gas Shales Workflow ECDF NN EUR WGR HM AHM EDFM MCMC KNN BHP Assisted history matching Neural networks LGR LHS Markov chain Monte Carlo K-nearest neighbors MH WHP
ISSN:	0016-2361, 1873-7153
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!