当前位置: X-MOL 学术Geophysics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
VP and VS prediction from digital rock images using a combination of U-Net and convolutional neural networks
Geophysics ( IF 3.3 ) Pub Date : 2021-01-21 , DOI: 10.1190/geo2020-0162.1
Rongang Cui 1 , Danping Cao 2 , Qiang Liu 1 , Zhaolin Zhu 2 , Yan Jia 1
Affiliation  

Predicting elastic parameters based on digital rock images is an interesting application of a convolutional neural network (CNN), which can improve the efficiency of prediction. Predicting elastic parameters by a conventional CNN, which is used for image classification such as LeNet and AlexNet, lacks geophysical constraints, and its accuracy in predicting elastic parameters is poor, with limited training data available. The combination of a U-Net and a convolutional neural network (CUCNN) is proposed to predict the elastic parameters from digital rock images with limited training data. In CUCNN, the rock matrix and pore types segmented from gray-scale images are treated as constraints that induce the convolutional kernels to extract the global as well as the local-scale rock features. The loss function, designed in a composite form to accelerate the convergence speed, contains the segmentation error and elastic parameters predicted from the gray-scale images. By adding geophysical constraints to the CNN, an implicit representation from the gray-scale image to the elastic parameters can be gained, which can improve the accuracy and efficiency of parameter prediction. Our method was tested using training and verification data derived from 1800 2D image slices of Berea sandstone samples, and the results were compared against the CNN model. The VP and VS were calculated by the finite-element method as the control to test the performance of both models. Our results show that CUCNN’s R2 score is 0.84, which increased by as much as 0.21 compared to the conventional CNN.

中文翻译:

结合U-Net和卷积神经网络从数字岩石图像进行VP和VS预测

基于数字岩石图像预测弹性参数是卷积神经网络(CNN)的一个有趣应用,它可以提高预测效率。通过用于图像分类(例如LeNet和AlexNet)的常规CNN预测弹性参数缺乏地球物理约束,并且其预测弹性参数的准确性很差,并且可用的训练数据有限。提出了U-Net和卷积神经网络(CUCNN)的组合来从训练数据有限的数字岩石图像中预测弹性参数。在CUCNN中,从灰度图像分割的岩石基质和孔隙类型被视为约束条件,这些条件引起卷积核提取全局和局部尺度的岩石特征。损失函数 以复合形式进行设计以加快收敛速度​​,其中包含从灰度图像预测的分割误差和弹性参数。通过向CNN添加地球物理约束,可以获得从灰度图像到弹性参数的隐式表示,这可以提高参数预测的准确性和效率。我们的方法是使用来自Berea砂岩样品的1800个2D图像切片的训练和验证数据进行测试的,并将结果与​​CNN模型进行了比较。的 可以提高参数预测的准确性和效率。我们的方法是使用来自Berea砂岩样品的1800个2D图像切片的训练和验证数据进行测试的,并将结果与​​CNN模型进行了比较。的 可以提高参数预测的准确性和效率。我们的方法是使用来自Berea砂岩样品的1800个2D图像切片的训练和验证数据进行测试的,并将结果与​​CNN模型进行了比较。的VPV小号通过有限元方法计算出作为对照,以测试两个模型的性能。我们的结果表明,CUCNN的R 2得分为0.84,与传统的CNN相比增加了0.21。
更新日期:2021-01-24
down
wechat
bug