POST-EARTHQUAKE STRUCTURAL DAMANGE ASSESSMENT OF BUIDINGS USING GEOSPATIAL PARAMETERS

Abstract

Earthquakes are among the most destructive natural disasters, often causing severe
damage to buildings and infrastructure, leading to significant loss of life and property.
Rapid and accurate assessment of structural damage is essential for effective disaster
response, rescue operations, and recovery planning. Traditional damage assessment
methods, such as manual field inspections, are time-consuming, labor-intensive, and
often restricted by accessibility and safety challenges. To overcome these limitations,
this project proposes a geospatial-based approach for post-earthquake structural
damage assessment of buildings.
The system utilizes geospatial technologies such as remote sensing, high-resolution
satellite imagery, and Geographic Information Systems (GIS) to analyze affected
areas. Various spatial and structural parameters, including building footprint, height,
construction type, surrounding density, and proximity to fault lines, are considered for
damage evaluation. The collected data is preprocessed and analyzed using machine
learning algorithms to classify buildings into different damage categories such as
minor, moderate, and severe.
By integrating geospatial analysis with predictive modeling, the proposed system
enables faster, more accurate, and scalable damage assessment compared to
traditional methods. It also generates spatial maps that highlight affected regions,
assisting authorities in prioritizing emergency response and resource allocation.