Submarine landslide risk analysis method based on unsupervised machine learning

Abstract

The invention discloses a submarine landslide risk analysis method based on unsupervised machine learning, and the method comprises the steps: building a submarine landslide risk evaluation and analysis model based on a determined kernel function parameter type through employing a plurality of groups of geological environment parameters, such as the water depth of a research region and the type ofsediments, as input parameters; carrying out classification processing on input parameters of an actual research region, inputting the input parameters into the constructed unsupervised machine learning model, and obtaining a final submarine landslide risk analysis result through classification and label endowing. According to the scheme, a danger analysis means before the submarine landslide isdangerous is provided, and danger evaluation and prediction can be carried out on the area where the submarine landslide is not generated yet; evaluation can be carried out according to different types of geological parameters, and submarine landslide risk zoning can be rapidly and effectively carried out on a research area according to various geological parameters.

Description

technical field [0001] The invention relates to the technical field of submarine landslide risk analysis, in particular to a method for analyzing the risk of submarine landslides based on unsupervised machine learning. Background technique [0002] Submarine landslide is a submarine geological disaster phenomenon caused by the sliding of submarine soil, which can pose a huge threat to marine engineering facilities such as submarine cables, optical cables, and offshore platforms. Carrying out risk assessment research on submarine landslides can guide the site selection and risk prevention of marine engineering facilities. At present, the classification methods of submarine landslides mainly include: using high-precision geophysical detection to identify landslides, calculating the stability of submarine landslides through numerical analysis, and using physical model tests such as conventional tanks or centrifuges to simulate the landslide process. Although great progress has...

AI Technical Summary

Problems solved by technology

However, the morphological classification of submarine landslides can only be classified according to the morphology of submarine landslides after they occur, and can be distinguished based on a series of characteristics such as size, water depth, and slope; and this classification method is too much human intervention, such as the construction of the weight matrix. Operators manually as

Images