基于支持向量机的页岩储层横波速度预测

Prediction of Shear Wave Velocity in Shale Reservoir Based on Support Vector Machine

为解决目前油气田现场缺少储层横波速度信息的问题,以常规测井数据为基础,基于支持向量机映射页岩横波速度与自然伽马、密度和电阻率等测井数据的相关性,提出了一种准确预测储层横波速度的方法。通过四川盆地威远页岩气区块的11 500个样本数据对所建立的模型进行训练与测试,支持向量机的预测准确性达到97.2%。

In order to solve the problem of lacking the data of shear wave velocity in oil and gas fields, a method for predicting the shear wave velocity in shale reservoir is proposed, which is based on conventional logging data. The relationship between shear wave velocity and natural gamma, density and resistivity logging data of shale reservoir was established by support vector machine （ SVM ）. The pre- diction model was trained by the data of 10 000 samples from Weiyuan block in Sichuan Basin and tested by the data of 1 500 samples from the same block, its prediction accuracy of the test set is 97.2 %.