Slope displacement time sequence prediction method and device and storage medium

The invention discloses a slope displacement time sequence prediction method and device and a storage medium, and the method comprises the steps: collecting corresponding multi-source data through a plurality of common geological data collection devices, including a soil moisture meter, an inclinometer rope, a stay wire displacement meter and a GNSS, and collecting corresponding soil moisture content, deep displacement, crack displacement and slope displacement data; slope data is slope displacement required to be predicted, and soil moisture content, deep displacement and crack displacement are used as characteristic data for assisting in predicting the slope. Slope displacement data are divided into overall trend data and fluctuation data by adopting a decomposition method, the trend data are independently input into a GRU network model for prediction, the fluctuation data and feature data are input into a Seq2Seq + Attention network model together for training, and the predicted trend data and fluctuation