Abstract：The artificial bee colony (ABC) algorithm is introduced into seismic attribute clustering in this paper. In the ABC algorithm, there are three types of bees: employed bees, onlooker bees and scouter bees. The employed bees search food sources, onlooker bees search new food sources based on the information shared by employed bees. If a food source is abandoned, scouter bees search randomly a new food source to replace the abandoned one. In the ABC algorithm, every food source represents a possible solution, and the amount of nectar in the food source represented by fitness corresponds to the quality of the solution. The process of finding the optimized solution includes two steps: initialization and food source update. Through the cooperation of bee colony to search the best clustering centroids, the problem of multiple solutions could be solved in ordinary clustering algorithm. Tests on Iris and Wine datasets in the machine learning UCI dataset bank proved the clustering method based on ABC has higher accuracy than K-means. For seismic data tests, seismic attributes clustering based on ABC can accurately describe Karst reservoir microfacies of Ordovician carbonate and characterize weak flake-like reflection reservoirs in North Tarim Basin.
Yang Peijie,Yin Xingyao and Zhang Guangzhi.Cluster analysis of seismic attributes by fuzzy C-means algorithm. OGP,2007,42(3):322-324,347.
[5]
Liu Xingfang,Zheng Xiaodong,Xu Guangcheng et al.PSO-based multi-attribute dynamic clustering technology and its application.SEG Technical Program Expanded Abstracts,2011,30:1913-1917.
[6]
刘杏芳.非线性地震属性特征提取技术及应用[博士学位论文].北京:中国石油勘探开发研究院,2011] Liu Xingfang.Extraction and Application of Seismic Attributes Feature Through Non-linear Method[D]. Beijing: Research Institutes of Petroleum Exploration and Production,2011.
Yin Xingyao,Ye Duannan and Zhang Guangzhi.Application of kernel fuzzy C-means method to reservoir prediction.Journal of China University of Prtroleum(Natural Science Edition),2012, 36(1):53-59.
[8]
Beni G and Wang J.Swarm Intelligence in Cellular Robotic Systems Proceedings of NATO Advanced Workshop on Robots and Biological Systems,1993,102:703-712.
[9]
Karaboga D. An idea based on honey bee swarm for numerical optimization.Technical Report-TR06.Erciyes University Press, Erciyes,2005.
[10]
Camazine S,Deneubourg J L and Franks N R et al.Self-Organization in Biological Systems.Princeton:Princeton University Press,2003.
[11]
Dereli T and Das G S.A hybrid 'bees algorithm' for solving container loading problems.Applied Soft computing,2011,11(2):2854-2862.
[12]
Mustafa S.Artificial bee colony algorithm for optimization of truss structures.Applied Soft computing,2011, 11(2): 2406-2418.
[13]
Karaboga D and Basturk B.On the performance of artificial bee colony algorithm.Applied Soft computing,2008,8(1): 687-697.
[14]
Basturk B and Karaboga D.An artificial bee colony algorithm for numeric function optimization.IEEE Swarm Intelligence Symposium,2006,318-329.
