Landslide displacement multilinear prediction method based on ST-SEEP segmentation method and space-time ARMA model

Abstract

The invention provides a landslide displacement multilinear prediction method based on an ST-SEEP segmentation method and a space-time ARMA model. The landslide displacement multilinear prediction method comprises the steps of data preprocessing, curve segmentation, spatial weight matrix acquisition, modeling and prediction, and prediction effect evaluation. in data preprocessing step, reading landslide displacement data and coordinate data, and preprocessing the landslide displacement data and the coordinate data; drawing a landslide displacement-time curve in a curve segmentation mode, and providing an ST-SEEP method to conduct segmentation processing on the curve; in spatial weight matrix acquisition step, performing spatial clustering on the monitoring points by adopting a K-means clustering method, and acquiring a spatial weight matrix; modeling and predicting to establish a space-time ARMA model, and predicting a landslide displacement space-time sequence; and the prediction result evaluation adopting an absolute error and a root-mean-square error to evaluate the prediction result. The method has the beneficial effects that quantitative analysis of the spatial relationship of the monitoring points is realized, and the spatial relationship is more effectively utilized; the space-time autoregressive moving average statistical model is introduced into the landslide prediction field, the physical significance of formulas and parameters is clear, the process is clear, and the landslide displacement can be accurately predicted.

Description

technical field [0001] The invention belongs to the technical field of engineering geology, and relates to a multi-linear prediction method for landslide displacement based on ST-SEEP segment method and space-time ARMA model. Background technique [0002] Prediction of landslide displacement is a frontier topic in the field of landslides, and accurate prediction of landslide displacement is of great significance to landslide hazard prediction. Most of the existing landslide displacement prediction methods are time series prediction, that is, by monitoring the historical displacement of the landslide, the historical displacement time series data of a single monitoring point is used to predict the future displacement of the monitoring point, which represents the prediction result of the landslide displacement. [0003] Compared with the traditional time series forecasting method, the space-time series forecasting method increases the spatial dimension of the data. At present,...

AI Technical Summary

Problems solved by technology

At present, the time and space sequences of the fusion sensor are obtained to obtain the network space-time sequence and input into the neural network to predict the landslide displacement. It considers the spatial factor, but the process of fitting the data by the neural network used is difficult to explain, and the physical meaning of the relevant parameters is not clear. ; at the same time, directly calculate the displacement difference of two monitoring points at the same time as the element of the space sequence, and then superimpose the space sequence of each time to obtain the network space-time sequence, which fails to quantitatively analyze the spatial relationship between the monitoring points. The use of spatial relationships is not ideal

[0004] At present, there is no technology that can quantify the spatial relationship and predict the space-time sequence of landslide displacement through an interpretable model. Prediction techniques to obtain more accurate landslide displacement prediction results

Images