Ice collapse infrasound feature extraction and classification identification method and medium

Abstract

The invention discloses an ice collapse infrasound feature extraction and classification identification method and a medium, and the method comprises the steps: cleaning an original signal, and obtaining an infrasound signal; analyzing the time domain and the frequency domain of the infrasound signal to obtain a sound pressure range, kurtosis, skewness and a power spectrum; based on the infrasound signal, determining energy distribution of the infrasound signal on each scale through discrete wavelet transform, and extracting characteristic values to obtain three types of characteristics of wavelet energy entropy, scale entropy and singular entropy; and obtaining a Hilbert marginal spectrum through Hilbert-Huang transform based on the infrasound signal. According to the method, the original infrasound database, the video database and the infrasound sample feature database are established, and the classification model can be trained based on the infrasound sample feature database to identify the occurrence of the ice collapse event.

Description

technical field [0001] The invention relates to the technical field of infrasound processing, in particular to a method and medium for extracting, classifying and identifying ice avalanche infrasound features. Background technique [0002] Ice avalanche is an instantaneous ice collapse event that occurs at the front of a glacier under the action of gravity. In recent years, under the influence of human activities and climate change, the global warming trend has intensified, and the cryosphere has been seriously affected. In particular, the Qinghai-Tibet Plateau, as a sensitive area of ​​global climate change, has experienced large-scale glaciers melting and retreating, resulting in The instability of glaciers is gradually increasing, and at the same time, affected by internal and external forces such as topography, earthquakes, and precipitation, the probability of ice avalanche disasters is gradually increasing. [0003] Because most of the ice avalanches occurred in remot...

AI Technical Summary

Problems solved by technology

Because ice avalanche disasters often occur in remote mountainous areas, the terrain is dangerous, and the on-site survey is difficult and dangerous, so the actual collected data is extremely limited; the development of remote sensing technology has promoted the progress of research on ice avalanche disasters, and remote sensing images can fully analyze glaciers. Azimuth monitoring, but remote sensing images rely on the spatial and temporal resolution of satellites, and cannot perform real-time monitoring; seismographs are currently mainly used to record the frequency of ice avalanches, not the entire dynamic process of ice avalanches; numerical simulation can The main influencing factors of the process are simulated, but the simulation of its mechanism is still difficult

Images