A semantic information-driven stepwise landslide displacement prediction model.

Landslide prediction is critical for the early warning of a landslide occurrence. Existing stepwise landslide displacement prediction methods are mostly data-driven approaches. However, these models are vulnerable to overfitting, and the low-dimensional numerical features with high numerical volatility prevent them from precisely quantifying the rapid increase in daily displacement in the acceleration phase.

[Analysis of volatile oil from Ardisia brevicaulis].

Objective: To analyze and compare the compounds in the essential oil from the leaves and roots of Ardisia brevicaulis.

Methods: The essential oil were obtained by steam distillation. The chemical components were separated and identified by gas chromatography-mass spectrometry (GC-MS).