The study on the Cilan landslide (CL) demonstrates the utilization of seismic analysis results as preliminary data for geologists during field surveys. Spectrograms revealed that the first event of CL consisted of four sliding failures accompanied by a gradual reduction in landslide volume. The second and third events were minor toppling and rockfalls. Then combining the seismological-based knowledge and field survey results, the spatiotemporal variation in landslide evolution is proposed.

We developed a machine-learning-based approach to predict the potential thickness of shallow landslides to generate improved inputs for slope stability models. We selected 21 explanatory variables, including metrics on terrain, geomorphology, vegetation height, and lithology, and used data from two Swiss field inventories to calibrate and test the models. The best-performing machine learning model consistently reduced the mean average error by at least 20 % compared to previous models.