Soil oil content hyperspectral model in Gudong Oilfield
孤东油田土壤石油类含量的高光谱反演模型

The detection of oil content in soil has an important practical significance in oil pollution prevention and control. Wemeasure the hyperspectral reflectivity and the oil content for soil samples in Gudong Oilfield. Using variable forecast model andstepwise regression method, we analyze the linear and nonlinear relationships between soil spectral characteristic parameters andoil content. The experiment shows that there is a significant correlation between the third broken line segment slope of envelopeline analysis and the oil content. The cubic function of this section slope is the best single variate estimation model. The standardnormal variate transformation has the best effect on spectrum pretreatment. When the transformed spectral are used to build multivariateregression model, the adjusted coefficient of determination R2 is 0.826, and the total RMSE is 0.531, which is the bestforecast model. The method of using hyperspectral data to detect the oil content will provide an effective new way for detectingthe oil pollution in soil.