The Logistic Regression Based on Diagnostic Ratio for Identification of the Middle East Crude Oil
HUANG Yi
WANG Sitong
ZHANG Tingting
GONG Weimin
QI Chaoyue
LI Jia
LIU Xiaoxing
Abstract：Diagnostic ratio of crude C17/Pr,C18/Ph and Pr/Ph has good resistance to weathering and is an important parameter for identification of oil spills into the sea.Adjusted cosine similarity among eighteen types of crude oil was investigated with diagnostic ratio as a parameter.The Middle East crude oils show high similarity because their similarity average value is 0.76,while the Middle East crude oil and non-Middle East crude oil have significant differences since their similarity average value is-0.42.A binary Logistic regression model was established to identify the Middle East crude oil using diagnostic ratio as variables,C statistic is 0.99(＞0.90),indicating there is good relative consistency between diagnostic ratio and model forecast probability.By this model,the identification accuracy is 100％ for oil samples weathered for 30 days,and for 9 types of crude oil reported in the literature.This model is applicable not only for identification of crude oil,but also for crude oil weathered on the sea during short-term.
Keywords：Logistic regressiondiagnostic ratiosadjusted cosine similarityMiddle East crude oilweathering
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 66-70 )