Landslide displacement prediction method based on PSO-SVR and DES combination

Abstract

The invention discloses a landslide displacement prediction method based on the PSO-SVR and DES combination. The method comprises the steps of acquiring a displacement monitoring time sequence and a plurality of initial influence factors of a displacement monitoring point at a landslide, removing random noise of the displacement monitoring time sequence by adopting a wavelet denoising method, anddecomposing the displacement monitoring time sequence into two components, namely a periodic term and a trend term, by using an HP filter. On the basis, the invention further discloses a preparation method, the water level and the rainfall are used as influence factors. The main influence factor characteristics of landslide displacement are extracted by adopting a principal component analysis method, a hybrid prediction optimization model combining a PSO-SVR (particle swarm optimization support vector regression) machine and a DES (double exponential smoothing) machine is established. The landslide displacement prediction is realized by constructing periodic term and trend term training sample components respectively. Finally, the trend term displacement prediction value and the season term displacement prediction value are superposed to obtain a landslide total displacement prediction value.

Description

technical field [0001] The invention relates to the field of geological disaster monitoring, in particular to a landslide displacement prediction method based on the combination of PSO-SVR and DES. Background technique [0002] As a common geological disaster, landslides are usually caused by a variety of uncertain factors, such as geological conditions, landforms, hydrogeological and physical factors, and human activities. Landslide deformation prediction has always been an important research direction and research hotspot in landslide early warning and prediction. When landslide deformation evolution is affected by seasonal factors (such as water level regulation of the Yangtze River and periodic heavy rainfall), the cumulative displacement curve usually shows strong nonlinear dynamic characteristics, such as step change. When conventional methods are used to predict such landslides, it is very easy to mistake the step-wise deformation characteristics for the landslide ha...

AI Technical Summary

Problems solved by technology

When conventional methods are used to predict such landslides, it is very easy to mistake the stepwise deformation characteristics for the landslide has entered the stage of imminent sliding, resulting in misjudgment

Therefore, traditional analysis methods are difficult to make an accurate evaluation of the stability of landslides.

Images