期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：300
期号：2
页码：1-5
DOI：10.1088/1755-1315/300/2/022077
出版社：IOP Publishing
摘要：In this paper we propose a method on qualitative recognition of flushed zone. We extract the morphometric parameters of logging curves to better reflect the change relations. We use deep forest model which learns the representation layer by layer. The model is more robust and have a higher accuracy than other model. This method has an excellent application performance in Q block.
