Litcius/Paper detail

Real-time seismic damage prediction and comparison of various ground motion intensity measures based on machine learning

Yongjia Xu, Xinzheng Lu, Yuan Tian, Yuli Huang

2021Report26 citationsDOI

Abstract

<p>After earthquakes, an accurate and efficient seismic damage prediction is indispensable for emergency response. Existing methods face the dilemma between accuracy and efficiency. A real-time and accurate seismic damage prediction method based on machine-learning is proposed here. 48 intensity measures are used as input to represent the ground motion comprehensively. Besides, the workload of the NLTHA method is replaced by model training/testing and moved to a non-urgent stage to promote efficiency. Case studies with various building cases prove the accuracy and efficiency of the proposed method. Key intensity measures for each building are identified by iteratively using the proposed framework.</p>

Topics & Concepts

Computer scienceWorkloadGround motionIntensity (physics)Key (lock)Motion (physics)Face (sociological concept)Ground truthArtificial intelligenceMachine learningEngineeringStructural engineeringComputer securitySociologyOperating systemQuantum mechanicsSocial sciencePhysicsSeismic Performance and AnalysisStructural Health Monitoring TechniquesStructural Response to Dynamic Loads
Real-time seismic damage prediction and comparison of various ground motion intensity measures based on machine learning | Litcius