A fast approach for unsupervised karst feature identification using GPU. (October 2018)

• Record Type: Journal Article
• Authors: Afonso, Luis C.S.; Basso, Mateus; Kuroda, Michelle C.; Vidal, Alexandre C.; Papa, João P.
• Is Part Of: Computers & geosciences. Volume 119(2018)
• Page Start: 1
• Page End: 8
• Publication Date: 2018-10
• Subjects: Self-organizing map -- Paleokarst -- Graphics processing unit -- Campos basin; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2018.06.004
• Languages: English
• ISSNs: 0098-3004

Abstract

Abstract: Among the geological features, karst is the one that has received special attention in oil and gas exploration for being a strong indicator of the potential existence of hydrocarbon reservoirs. The integration of automatic pattern recognition methods and Graphics Processing Units (GPU) provides a powerful tool to help geological interpretation of seismic data. In order to provide insightful information for interpreters, this work investigates the usage of GPUs in addition to image segmentation by means of unsupervised classification for the identification of karst features in 3D seismic data. For this purpose, an implementation of the robust Self-Organizing Map for GPUs (SOM/GPU) is provided, and a comparison against a Central Processing Unit (CPU)-based SOM (SOM/CPU) is performed to assess the speeding-up provided by GPU. Experiments have shown promising results for geological interpretation using seismic data. Highlights: We proposed an unsupervised approach for the identi_cation of karst features. The GPU code overcomes issues of the amount of data and computing time. The proposed approach identi_ed karst features using multi-attribute data. It was obtained a speed-up of over 31 times compared with a sequential CPU code.