We build a weighted random forests classifier to identify sinkholes.
We select depression geometry and natural/human factors as predictive variables.
Higher weight for the sinkhole class improved accuracy in identifying true sinkholes.
Including variables besides shape and depth of depressions improved the classifier.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址:北京市海淀区学院路29号 邮编:100083 电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700 |