Adaptive-phase k-means algorithm for waveform classification
Chengyun Song, Zhining Liu, Zhiyong Li, Guangmin Hu · 2016
Waveform classification techniques is a powerful tool for seismic facies analysis by describing the heterogeneity and compartments within a reservoir. The interpretation of horizon is critical to the process of waveform classification. The error of horizon, which is inevitable in seismic data analysis, may led to an unrealistic classification result. To alleviate this problem, an adaptive phase waveform classification method called adaptive phase K-means is introduced in this paper. It improves the traditional K-means algorithm using an adaptive phase distance for waveforms similar measure. The main advantage of this method is the robustness in the presence of horizon error. We tested the effectiveness of our algorithm with application to synthetic data and real data. The satisfactory results illustrate the proposed method has certain tolerance of horizon noise and is a better seismic facies analysis tool. Presentation Date: Wednesday, October 19, 2016 Start Time: 8:50:00 AM Location: Lobby D/C Presentation Type: POSTER