A Modified Blasingame Production Analysis Method for Vertical Wells Considering the Quadratic Gradient Term

Ren, Junjie; Qiao, Zheng; Zhao, Chen

doi:10.3390/en12112092

Cited by 6 publications

(1 citation statement)

References 44 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of R 2 being used improperly to determine the appropriateness of production analysis methods include Gupta et al (2018), Ren et al (2019), and many, many others. In our experience, this misuse of R 2 does not result in incorrect comparisons between multiple production forecasting approaches, but it always leads to overconfidence in the final model.…”

Section: Misstep 3: Interpreting R 2 Incorrectlymentioning

confidence: 99%

Three common statistical missteps we make in reservoir characterization

Columbu¹,

Jensen²

2022

Bulletin

View full text Add to dashboard Cite

Reservoir characterization analysis resulting from incorrect applications of statistics can be found in the literature, particularly in applications where integration of various disciplines is needed. Here, we look at three misapplications of ordinary least squares linear regression (LSLR) and show how they can lead to poor results and offer better alternatives, where available. The issues are 1. Application of algebra to an LSLR-derived model to reverse the roles of explanatory and response variables that may give biased predictions. In particular, we examine pore throat size equations (e.g., Winland's and Pittman's equations) and find that claims of over-predicted permeability may in part be due to statistical mistakes.2. Using a log-transformed variable in an LSLR model, de-transforming without accounting for the role of noise gives an equation which under-predicts the mean value. Several approaches exist to address this problem.3. Mis-application of R 2 in three cases that lead to misleading results. For example, model fitting in decline curve analysis gives optimistic R 2 values, as is also the case where a multimodal explanatory variable is present.3 Using actual and synthetic datasets, we illustrate the effects that these errors have on analysis and some implications for using machine learning results.

show abstract

Section: Misstep 3: Interpreting R 2 Incorrectlymentioning

confidence: 99%