Machine Learning in High Performance Computing Environments Workshop (MLHPC '17)

1 / 2017-08-11 16:18:20

Prediction of shear wave velocity in shale reservoir based on logging data and support vector machine

shale reservoir；prediction of shear wave velocity；support vector machine；logging data

In order to solve the problem of lacking shear wave velocity information in oil and gas field, based on conventional logging data, a support vector machine(SVM) model is used to map the relationship between shear wave velocity and natural gamma, acoustic time difference and resistivity of shale, and then a method for shear wave velocity prediction is proposed. The model was trained and tested by 11500 sample data of Weiyuan block in Sichuan basin, and the accuracy of prediction of the test set was 97.2 percent.