Landslide Hazard Assessment for Situational Awareness (LHASA) version 2.0(GSC-18595-1)

In order to advance LHASAs capabilities to characterize landslide hazards and impactsdynamically, we have implemented a new approach that leverages machine learning, newparameters, and new inventories. LHASA 2.0 uses the XGBoost machine learning model to bring indynamic variables as well as additional static variables to better represent landslide hazardglobally. Global rainfall forecasts are also being evaluated to provide a 1-3 day forecast of potentiallandslide activity. Additional factors such as recent seismicity and burned areas are also beingconsidered to represent the preconditioning or changing interactions with subsequent rainfallover affected areas.