期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 60, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2021.3079963
关键词
Training; Data models; Reservoirs; Rocks; Training data; Convolution; Feature extraction; Diversity of labeled data; geological and geophysical model driven CNNs (GGCNNs); seismic inversion; unconventional tight sandstone
类别
资金
- National Key R&D Program of the Ministry of Science and Technology of China [2020YFA0713403]
- National Natural Science Foundation of China [41704127]
- Fundamental Research Funds for the Central Universities [xjj2018235]
- National Key Research and Development Program of the Ministry of Science and Technology of China [2018YFC0603501]
Traditional optimization algorithms used for estimating elastic parameters from field seismic data rely heavily on prior knowledge, leading to uncertainties in inversion results. With the development of neural networks, convolutional neural networks (CNNs) have been applied to this task, but the lack of labeled seismic data and diversity in datasets can hinder their effectiveness. The proposed Geological and Geophysical Model Driven CNNs (GGCNNs) model in this study leverages synthetic labeled prestack seismic datasets to incorporate geological information and achieve a balance between inversion accuracy and labeled data size. Applications demonstrate the effectiveness of GGCNNs in predicting elastic parameters with high accuracy and smoothness.
Traditional optimization algorithms are usually applied to estimate the elastic parameters of the subsurface by using field seismic data. However, these optimization algorithms highly depend on prior knowledge (e.g., the initial model setup and sparsity), leading to serious inversion uncertainties. Nowadays, with the rapid development of neural networks, convolutional neural networks (CNNs) have been widely imposed on estimating elastic parameters from field data. However, the deficiency of labeled seismic data impedes the CNNs application in seismic inversion. Moreover, both the size and diversity of labeled datasets are also critical factors influencing the accuracy and resolution of predicted parameters when using the CNNs-based inversion techniques. In this work, taking the unconventional tight sandstone formation as an example, we develop a geological and geophysical model driven CNNs (GGCNNs), named as GGCNNs. The proposed GGCNNs allow us to take advantage of both the prior geological information and basic geophysical model from the generated synthetic labeled prestack seismic datasets, representing essential characteristics of the subsurface. Moreover, under the consideration of data diversity, the GGCNNs model enables us to make a tradeoff between the inversion accuracy and labeled data size. Applications on both synthetic and field data clearly demonstrate the effectiveness of the proposed GGCNNs model for predicting elastic parameters by using prestack seismic data, i.e., its predicted results are with high accuracy in the vertical profile and continuity and smooth in the horizon slice.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据