云南省潜在震源区综合统计判定之一

本文将云南省地震局多年来积累的关于中强震发生的地质构造、地貌、地球物理场、地形变等特征基础资料,用于Cora-3算法的模式识别,得出云南省潜在震源区的背景指标,结果是比较理想的。“投票”结果表明,80%的学习集D类对象仍被识别为D类,85%的学习集N类对象仍被识别为N类,控制试验的结果也表明识别结果是比较稳定和可靠的。

ONE OF THE SYNTHETICALLY STATISTICAL DETERMINATIONS FOR POTENTIAL FOCAL REGION IN YUNNAN

The model determination of CORA-3 algorithm has been carried out on the data (accumulated for years by Seismological Bureau of Yunan Province) concerning characteristics of geological structure, geomorphology, geophysical. field and deformation ior occurenecs of moderate events. The background indicators for potential focal regions in Yunnan have been obtained with a comparatively ideal result. The "vote" result shows that 80% model D candidates of the studied data set has been still recognized as model D members, and 85% model N candidates as model N members. The result from controlled test has also suggested that the determinative result is comparatively stable and reliable.