Recent research endeavors in civil engineering have attempted to apply remote sensing technology to urban damage assessment as an aid for post-disaster reconnaissance and recovery. In these attempts, urban structural damage is identified based on pre- and post-disaster satellite images with the use of a pattern classification approach. The result is usually presented in a damage map wherein categorical damage levels, such as “fully collapsed,” “partially collapsed,” or “intact,” are assigned to urban subregions or individual structures in images. However, a major limitation in past attempts is the use of deterministic approaches to classify damage levels. In general, these approaches are not able to capture the inherent uncertainties of structural damage and lack scalability when analyzing damage to built urban subregions of different sizes. To address this, a probabilistic classification framework by means of a multiclass classifier is proposed. By applying this probabilistic approach, classification of urban damage provides posterior probabilities, which can be used to quantify decision uncertainties and to obtain regional urban damage classification. Numerical experiments are conducted using satellite images acquired from a recent earthquake and a tsunami event, namely the 2003 Bam, Iran Earthquake, and the 2004 India Ocean Tsunami.
Application of multi-objective optimization to structural damage estimation via model updating
