固体地球物理学术报告通知-施韫智

Picking horizons from seismic images is a fundamental step that could critically impact the seismic interpretation quality. We propose an unsupervised approach, Waveform Embedding, based on a deep convolutional autoencoder network to learn to transform seismic waveform samples to a latent space in which any waveform can be represented as an embedded vector. The regularizing mechanism of the autoencoder ensures that similar waveform patterns are mapped to embedded vectors with shorter distance in the latent space. Within a search region, we transform all the waveform samples to latent space and compute their corresponding distance to the embedded vector of a control point that is set to the target horizon; we then convert the distance to a horizon probability map that highlights where the horizon is likely to be located. This method can guide the horizon picking across lateral discontinuities such as faults and is insensitive to noise and lateral distortions. In addition, the proposed unsupervised learning algorithm requires no training labels. We apply the proposed horizon picking method to multiple 2D/3D examples and obtain superiorly accurate results compared to the baseline method.