INTEGRATING INSAR INFORMATION AND SPATIAL-TEMPORAL FACTORS IN MACHINE LEARNING ANALYSIS FOR LANDSLIDE PREDICTION – A CASE STUDY FOR PROVINCIAL HIGHWAY 18 AREA IN TAIWAN

The randomised Bartlett–Lewis (RBL) model is widely used to synthesise rainfall time series with realistic statistical features. However, it tended to underestimate rainfall extremes at sub-hourly and hourly timescales. In this paper, we revisit the derivation of equations that represent rainfall properties and compare statistical estimation methods that impact model calibration. These changes effectively improved the RBL model's capacity to reproduce sub-hourly and hourly rainfall extremes.

This study incorporates volunteered geographic information (VGI), unmanned aerial vehicle (UAV), and computational flood simulation (CFS) for flood analysis in urban areas. The digital elevation model (DEM) generated by a UAV and the VGI photos acquired from social network are served to establish and validate the CFS model, respectively. The results show that the flood scenarios can be more accurately modeled and the cost of sophisticated CFS can be greatly reduced with the help of UAV and VGI.

Data from 10 urban or peri-urban catchments located in five EU countries are used to analyze the imperviousness distribution and sewer network geometry. Consistent scale invariant features are retrieved for both (fractal dimensions can be defined), which enables to define a level of urbanization. Imperviousness representation in operational model is also found to exhibit scale-invariant features (even multifractality). The research was carried out as part of the UE INTERREG IV RainGain project.

A new methodology is proposed in this paper, focusing on improving the applicability of the operational weather radar data to urban hydrology with rain gauge data. The proposed methodology employed a simple yet effective technique to extract additional information (called local singularity structure) from radar data, which was generally ignored in related works. The associated improvement can be particularly seen in capturing storm peak magnitudes, which is critical for urban applications.