Open AccessDFOS-based association rules analysis on the multi-fields information of Majiagou landslide
Author(s) -
Lei Zhang,
Bin Shi,
Zheng Xing,
Yunxiang Sun
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/570/4/042023
Subject(s) - landslide , field (mathematics) , warning system , deformation (meteorology) , stability (learning theory) , association (psychology) , geology , seismology , data mining , mining engineering , computer science , telecommunications , machine learning , philosophy , oceanography , mathematics , epistemology , pure mathematics
The multi-fields information of landslide can be obtained using distributed optical fiber sensing (DFOS) technology. Nevertheless, it is still a quite complicated work to analyze massive amounts of multi-fields information, and to evaluate the slope stability under multifields coupling effect. This paper introduced a data mining method named association rules analysis, and designed a DFOS-based monitoring system to record the multi-field information, including strain field, deformation field, seepage field, temperature field and environmental parameters, respectively. Taking Majiagou landslide as an example, the association rules analysis of the multi-field monitoring information revealed the reservoir water level is the domain factor that influences the deformation of Majiagou landslide. The correlation analysis method can explore the internal relationship among different fields of a landslide and provide scientific basis for slope stability evaluation and landslide early-warning.