Landslide susceptibility evaluation model training method, evaluation method, device and medium

Abstract

The invention provides a landslide susceptibility evaluation model training method, evaluation method and device, and a medium. The training method comprises the following steps: collecting landslide evaluation factor data and landslide distribution data of a plurality of grid units in a specified area; marking the landslide evaluation factor data of each grid unit according to the landslide distribution data to obtain landslide sample marking data of each grid unit; for each grid unit, combining the landslide sample labeling data of the grid unit with the landslide sample labeling data of the adjacent grid unit to generate a landslide data matrix corresponding to the grid unit; and constructing a convolutional neural network, and training the convolutional neural network by adopting a data set formed by all the landslide data matrixes to obtain a landslide susceptibility evaluation model. According to the technical scheme of the invention, the comprehensiveness and accuracy of landslide susceptibility evaluation can be improved.

Description

technical field [0001] The invention relates to the technical field of geological hazard assessment, in particular to a landslide susceptibility assessment model training method, assessment method, device and medium. Background technique [0002] Landslide refers to the soil or rock mass on the slope, affected by factors such as river scouring, groundwater activity, rainwater immersion, earthquake and artificial slope cutting, under the action of gravity, along a certain weak surface or weak zone, the whole or scattered The natural phenomenon of land sliding downhill. When a landslide occurs, farmland, roads, and houses will be destroyed, and it will cause huge losses to people's lives and property. In order to detect and deal with it in time, the landslide susceptibility of mountains and other areas is often assessed. [0003] At present, when evaluating the susceptibility of landslide disasters in an area, the monitoring data of each monitoring point is often collected, a...

AI Technical Summary

Problems solved by technology

However, since the landslide is often the whole local mountain body sliding downward, each monitoring point is regarded as an independent point in the prior art, and the connection between each monitoring point is not considered, so the assessment of landslide susceptibility is not comprehensive enough and the assessment is accurate Sex is not high

Images