Semi-Supervised Interlayer Intelligent Recognition Method

Abstract The development and distribution of interlayers in sandstones can lead to increased formation heterogeneity within the reservoir, whichand further affects the movement of fluids in the formation. Therefore, it is mandatory to evaluate the interlayers accurately the fine evaluation of interlayers in sandstones is of great significance for identifying the distribution of underground the fluid systems. The logging data of interlayers are inappropriate for traditional Machine Learning training due to their low measurement proportion compared to the conventional layers. In logging data, the amount of data in interlayers is small compared to conventional reservoirs. Traditional machine learning models are mostly based on samples with balanced distribution,. By contrast, while semi-supervised learning uses requires small labeled samples for learning, and thenby Ccombineing a large number of unlabeled samples for modeling. In order to verify the effect feasibility of semi-supervised learning in the identification of interlayers, the Donghe sandstone section of H oilfield was taken as an example. First, the core analysis results were used to label the logging data; then, in order to dig out more response information that can characterize the interlayers on the logging curve, multiple features were extracted to construct cross features. Finally, an improved model based on autoencoders—probabilistic autoencoder (PAE)—is proposed to solve the problem of interlayers recognition for imbalanced samples. The PAE model can calculate a probability of belonging to a different class for unlabeled samples, and classify new samples according to the maximum probability. Experiments Results show that, compared with traditional machine learning methods and ensemble learning methods, PAE achieves higher recognition accuracy and better generalization performance by updating the algorithm, and can be used as a simple and fast method for interlayers recognition. The algorithm results prove that the semi-supervised method is of great significance for the exploration and development of complex heterogeneous oil reservoirs.The research results are of great significance for the exploration and development of complex heterogeneous oil reservoirs.