ICG2022-397
https://doi.org/10.5194/icg2022-397
10th International Conference on Geomorphology
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

GIS-based machine learning models for assessing landslide impact: A case study in King County, State of Washington, USA

Di Lu1 and Takashi Oguchi2,1
Di Lu and Takashi Oguchi
  • 1Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Japan
  • 2Center for Spatial Information Science, The University of Tokyo, Kashiwa, Japan

The impact caused by landslides can be determined by both landslide occurrence probability and the runout distance of landslides. This study aims to evaluate the potential damage caused by landslides in urbanized areas using two different methods: the Artificial Neural Networks (ANNs) method produces a landslide susceptibility map, and the constrained random walk method deals with landslide runout distance. These methods are applied to the study area in King County, Washington, USA. The landslide inventory data used include 2331 historical landslides. We divided each landslide area into the source, transportation, and deposition areas. We also selected 13 conditioning factors for landslide occurrence in the source areas: elevation, slope gradient, slope aspect, plan curvature, profile curvature, lithology, Stream Power Index (SPI), Topographic Wetness Index (TWI), Sediment Transport Index (STI), land cover, distance to roads, distance to railways, and population density. The value of the Area Under the Curve (AUC) of landslide susceptibility assessment using these factors is 0.927, showing the high performance of the applied model. Analysis of the transportation and deposition areas using the random walk model has provided additional insights into landslide hazards.

How to cite: Lu, D. and Oguchi, T.: GIS-based machine learning models for assessing landslide impact: A case study in King County, State of Washington, USA, 10th International Conference on Geomorphology, Coimbra, Portugal, 12–16 Sep 2022, ICG2022-397, https://doi.org/10.5194/icg2022-397, 2022.