Uncertainty Quantification of Forecasted Oil Recovery using Dynamic Model Ranking with Application to a ME Carbonate Reservoir

Multivariate Analysis and Data Mining of Well-Stimulation Data by Use of Classification-and-Regression Tree With Enhanced Interpretation and Prediction Capabilities

“…Various clustering techniques have found use in applications such as Web search, image retrieval, gene-expression analysis, recommendation systems, and market research based on transaction data (Jiang et al 2004;Daruru et al 2009). Recently, clustering techniques were also used in the petroleum industry for distance-based reservoir-uncertainty modeling (Scheidt and Caers 2009) and dynamic ranking of history-matched reservoir models to quantify uncertainty in prediction forecasting (Maučec et al 2011;Singh et al 2014). When the data sets are Year in (2007,2008,2009) Year in (2010,2011,2012) Year in (2007,2010,2011,2012) Year in (2008,2009) small or variables exhibit a low degree of variation, clustering does not add significant value.…”

“…Trees are capable of handling missing values and can use both categorical and continuous variables as input variables. CART has been applied in several areas, such as the financial industry (Cashin and Dattagupta 2008), manufacturing and marketing (Chen and Su 2008), and medical industries (Snousy et al 2011), and even in weed science (Wiles and Brodahl 2004). Different versions of decision trees have also been applied in the petroleum industry to estimate production profiles along with uncertainty assessments in long-term production forecasts (Jensen 1998); for data classification and partitioning to predict permeability from well logs (Perez et al 2005); for case-based reasoning and planning of the execution of a fracturing job (Popa and Wood 2011); to predict average production of a well from several variables, such as producer, acid volume, and strength (Yarus et al 2006); and to predict the oil production from five significant parameters (permeability, porosity, first shut-in pressure, residual oil, and water saturation) by use of a neural-based decision-tree model (Lee and Yen 2002).…”

A Review on “Management by Exception” Surveillance for Well Management: To maximize Oil Production

“…The gathered measurements were then processed using K-Means, before it was used for prediction procedure. Singh et al proposed uncertainty quantification measure for forecasted oil recovery (27). This was done using dynamic model ranking.…”

“…Use of machine learning method (Bao & Guan, 2016) No Oil production prediction K-Meansdata discretion (Foroud, et al, 2016) No Optimize production by looking at geological models K-Meansdata discretion (Awoleke & Lane, 2011) No Well water production prediction SOMsee how data are clustered K-Meansdetermine number of clusters Neural Networkprediction (Hu, et al, 2015) No Oil production prediction K-Meansdata discretion (G. (Popa, et al, 2015) No Perforation strategy optimization C-Meanscluster log data (Grieser, et al, 2008) No Overall well investigation SOMdata clustering (Cremaschi, et al, 2015) No Flow velocity estimation in pipelines K-Meansdata clustering (Shin & Cremaschi, 2014) No Flow velocity estimation in pipelines K-Meansdata clustering (Ding, et al, 2015) No Investigate high-permeability zone C-Meansdata clustering (Cui, et al, 2016) No Oil recovery improvement for high water-cut reservoirs K-Meanscluster/group the subjects (Liu, et al, 2009) No Measurement of water content in crude oil K-Meansdata preprocessing for prediction (Singh, et al, 2014) No Measurement for forecasted oil recovery K-Meansdata discretion…”