Dynamic behavior monitoring of twin supertall buildings during Super Typhoon Soksuri using social sensing data

This paper presents the dynamic behavior monitoring of the 300-m-tall Xiamen twin towers during Super Typhoon Soksuri by means of social sensing, which involves two individuals equipped with six smart devices to conduct acceleration measurement and video footage filming. The measured acceleration data are first corrected by the resampling technique since the sampling rate of smart-device-based measurement is unstable, and the corrected building acceleration obtained from different smart devices shows good consistency. Based on the corrected building acceleration responses, the amplitude-dependent and time-variant structural dynamic properties of the monitored twin towers are revealed by the random decrement technique and the Bayesian spectral density approach, respectively. The determined structural dynamic properties are further compared with seven existing prediction models to evaluate their accuracy. Moreover, by employing a computer-vision technique (i.e., the Kanade-Lucas-Tomasi optical-flow approach), the structural dynamic displacement was extracted from the video footage filmed during Soksuri, and its accuracy was further validated through comparison with direct acceleration measurements. This paper aims to demonstrate the feasibility and effectiveness of social sensing for dynamic behavior monitoring of supertall buildings.