Rapid Assessment of Building Damage Using Multi-Source Data: A Case Study of April 2015 Nepal Earthquake

It is of great significance for emergency rescue to rapidly assess damage buildings after an earthquake. Some previous methods are time-consuming, data difficult obtain, or there lack regional assessment. We proposed a novel way building by comprehensively utilizing earth observation-derived and field investigation alleviate the above problems. These related hazard-causing factors, hazard-formative environment, hazard-affected body. Specifically, predicted ground motion parameters used reflect e.g., peak velocity (PGV), acceleration (PGA), pseudo-spectral (PSA). The environment denoted underground 30 m shear wave velocity. Vulnerability reflected their structure type, age, height. take April 2015 Nepal earthquake as case study, interpreted from satellite images validate effectiveness method. Based on gradient boosting machine, this paper assesses two different spatial levels, i.e., pixel microzone, obtains potentially affected position rate. Compared with method fragility function, machine learning provide better estimation assessment based remote sensing image, in very efficient since distribution PGA, can be quickly shortly comparison experiment without vulnerability shows that important improve accuracy damage.