Search

The wireline log prediction of sedimentary microfacies plays a significant role in sedimentary study. It is mainly achieved through the manual interpretation of wireline logs according to the differences of sedimentary microfacies in wireline log shapes. Influenced by interpreters' expertise and proficiency in manual interpretation, the classification results maybe subjective and uncertain. Moreover, the task is labor intensive. Developing an automatic method based on wireline logs to accurately classify sedimentary microfacies is thus, a worthy consideration. The proposed automatic classification of sedimentary microfacies in this study can be implemented in terms of object detection, which involves aspects of machine learning and computer vision. In the stage of machine learning, we manually extract the features that can represent the different well log shapes of sedimentary microfacies. To solve the problem of imbalanced training samples, we use the oversampling technique to propagate the training classes with few samples. In addition, based on the augmented samples, we systematically conduct cross-validation and hyperparameter optimization on a series of machine learning algorithms with different mechanisms. The oversampling algorithm and machine learning model with the best performance can then be selected. In the stage of computer vision, we design an object detection strategy to detect the classes and locations of sedimentary microfacies by integrating the trained classifier. The practical application of the proposed method to the clastic strata of the Ordos basin proves its efficiency and consistency in automatically classifying sedimentary microfacies. [ABSTRACT FROM AUTHOR]

Seismic waveform clustering is a useful technique for lithologic identification and reservoir characterization. The current seismic waveform clustering algorithms are predominantly based on a fixed time window, which is applicable for layers of stable thickness. When a layer exhibits variable thickness in the seismic response, a fixed time window cannot provide comprehensive geologic information for the target interval. Therefore, we propose a novel approach for a waveform clustering workflow based on a variable time window to enable broader applications. The dynamic time warping (DTW) distance is first introduced to effectively measure the similarities between seismic waveforms with various lengths. We develop a DTW distance-based clustering algorithm to extract centroids, and we then determine the class of all seismic traces according to the DTW distances from centroids. To greatly reduce the computational complexity in seismic data application, we propose a superpixel-based seismic data thinning approach. We further propose an integrated workflow that can be applied to practical seismic data by incorporating the DTW distance-based clustering and seismic data thinning algorithms. We evaluated the performance by applying the proposed workflow to synthetic seismograms and seismic survey data. Compared with the the traditional waveform clustering method, the synthetic seismogram results demonstrate the enhanced capability of the proposed workflow to detect boundaries of different lithologies or lithologic associations with variable thickness. Results from a practical application show that the planar map of seismic waveform clustering obtained by the proposed workflow correlates well with the geological characteristics of wells in terms of reservoir thickness. [ABSTRACT FROM AUTHOR]