Geological disaster space prediction method and system based on similarity measurement, and storage medium
A technology of similarity measurement and geological disasters, applied in the field of geological disaster prediction, can solve the problems of less application of geographical similarity theory and single research method of geological disaster prediction model
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0110] Aiming at the above defects or vacancies in the prior art, the present invention proposes a spatial prediction method of geological disasters based on similarity measurement based on the geographical similarity theory of the third law of geography. Based on the third law of geography, this method can propose a new idea of spatial prediction, which can focus on the similarity of location and geographical configuration for spatial prediction of geological disasters, thereby filling the gap in the application of this theory in the existing technology.
[0111] In order to achieve the above object, the present invention provides a method for spatial prediction of geological disasters based on similarity measurement, which includes the following steps in turn:
[0112] (1) Extraction of influencing factors of geological hazards: Obtain alternative influencing factors of geological hazards from DEM data, remote sensing images, geological maps and other data, and standardize ...
Embodiment 2
[0123] In order to make the object, technical scheme and advantages of the present invention clearer, the following combination figure 2 The specific embodiment of the present invention will be described in detail.
[0124] like figure 2 As shown, the specific implementation method of the spatial similarity geological hazard prediction based on the coupling model is as follows:
[0125] (1) Extraction of alternative disaster factors: Based on the ArcGIS platform, the preliminary selected impact factors are extracted from the basic data such as DEM data and remote sensing images of the research area. Since the dimensions of each factor are different, regularization is adopted for the continuous factors after the factors are extracted. Processing, that is, calculating its p-norm for each sample, and then dividing each element in the sample by the norm, the result of this processing is to make the p-norm (l1-norm,l2 -norm) is equal to 1, the calculation formula of p-norm is a...
Embodiment
[0166] The research area is Qichun County, Hubei Province. Using 116 landslide data and non-landslide sample data in the research area, 14 environmental factor data were selected: elevation, slope aspect, slope, topography, NDVI, curvature, topographic moisture index, soil type , the distance from the river, the distance from the road, the distance from the railway, the distance from the fault, the average annual rainfall, and lithology.
[0167] Carry out PCC factor correlation analysis and random forest factor importance analysis: such as Figure 4 The factor correlation analysis shows. Figure 5 The factor importance analysis shows.
[0168] Combined with the results of importance analysis and correlation analysis, the topographic humidity index factor was eliminated, and 13 factors were finally selected;
[0169] Regularization and principal component analysis were performed on landslide samples and non-landslide environmental samples, and similarity clustering was perfo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


