Earthquake is one of the most destructive natural disasters, it can not only cause heavy casualties and economic losses, but also may even lead to serious secondary disasters. As the main bearing body in earthquake, buildings often suffer serious damage, so they can be used as an important reference for post-earthquake disaster loss assessment. Timely and accurate acquisition of regional earthquake damage information after an earthquake is of great significance for scientific and effective emergency rescue and disaster loss assessment. At present, the main methods for earthquake damage identification can be roughly divided into two categories: 1) Manual visual interpretation investigation method. It takes a lot of time for manual field investigation or manual identification of earthquake damage images to process a large amount of seismic damage information in a short period of time, and it is likely to lead to inconsistent discrimination standards for seismic damage of buildings. 2)Image recognition method based on satellite image or UAV image. The recognition method based on satellite remote sensing image after the quake identifies earthquake damage by the texture, brightness and other characteristics of the image of the seriously collapsed buildings, thus, it can quickly get the seismic damage situation in a large area, but as results of offset, low resolution and poor timeliness of the satellite image, it is hard to identify the slightly overlaying and cracking of tiles on the roof of buildings. The combination of high-resolution image obtained by UAV and machine learning algorithm can not only reduce the labor input, but also bring a high accuracy rate. Therefore, based on ant colony algorithm(ACO)and high-resolution remote sensing image of UAV, this paper proposes a new method to efficiently identify the earthquake damage of buildings in the study area, which was applied and verified in the recent Yangbi M6.4 earthquake in Yunnan Province. By improving the update strategy of pheromone concentration in ant colony algorithm and introducing the optimization operator, the better identification rules are established, and the speed and accuracy of earthquake damage identification are enhanced. The UAV high-resolution image of Yangbi county seat was obtained the first time after the Yangbi, Yunnan Province, M6.4 earthquake took place, and taking the image as experimental data, the extraction effect of regional earthquake damage is verified, and compared with ant colony algorithm and maximum likelihood method. The results show that the proposed earthquake damage identification method based on improved ant colony algorithm and UAV high-resolution image can effectively improve the identification accuracy and efficiency of damaged buildings in the region, which is of great significance for post-earthquake emergency rescue and providing accurate disaster information.

On 21 May 2021, a great earthquake of M6.4 struck Southwest China. This catastrophic event caused extensive casualties, a large number of houses collapsed, traffic disrupted, and large bridges damaged in Yunnan Province. The epicentre of the Yunnan Yangbi earthquake is located near the NW trending Weixi-Qiaohou-Weishan Fault. After this earthquake, the Institute of Geophysics of China Earthquake Administration calculated the focal mechanism solution using the global network data, the result shows that the earthquake is a strike-slip faulting event with normal component. The result of the focal mechanism solution is consistent with the strike of the Weixi-Qiaohou Fault and the distribution of aftershocks. Therefore, the strike of seismogenic structure of this earthquake was determined to be NW. Based on the strong motion observation data of 21 strong motion seismographs and 304 seismic intensity meters, the earthquake ground motion intensity map of the 21 May, 2021 Yangbi, Yunnan earthquake was obtained using the deviation correction method of magnitude shift, considering the geological tectonic background of the seismogenic fault, the focal mechanism solution and the precise location of aftershocks of this event. A commonly used proxy V_S30, the time-averaged shear wave velocity to 30m depth, was used to account for the local site effect of ground motion in the calculation of ground motion intensity map. We used V_S30-based amplification terms, which depends on the amplitude and frequency of ground motion, to account for site amplification. The V_S30 data of the macroscopic site classification was estimated using the correlation between topographic gradient and V_S30. Ground motion prediction equations(GMPEs) was used to supplement sparse data in its interpolation and estimation of ground motions. The selection of GMPEs for ground motion estimation were the attenuation relation of peak acceleration in western China in the fourth generation seismic zoning map. The observations of the ground motion for this event show that the maximum horizontal peak ground acceleration is 720.3cm/s² on the Yangbi station, 7.9km from the epicentre. Horizontal peak ground acceleration at 14 seismic stations is greater than 45cm/s². A large number of remote observation records with small values of ground motion also revealed the attenuation characteristics of ground motion for this earthquake. Using strong motion observation data available, we computed an event bias that effectively removed the inter-event uncertainty from the selected GMPE. The deviation correction method of magnitude shift minimizes the systematic deviation between the observed and estimated data produced by ground motion prediction equation, and reduces the uncertainties of the ground motion estimation in the area without stations. After the ground motion observations were corrected(de-amplified) to “rock”, we flagged any data that exceed three times the sigma of the GMPE at the observation point as abnormal data. The bias was then recalculated using different earthquake magnitudes and the flagging was repeated until systematic deviation between the observed and estimated data produced by GMPE was minimal. The results of the earthquake ground motion intensity map show that the highest seismic intensity caused by Yangbi earthquake is Ⅷ. Cangshanxi Town in Yangbi County and Taiping Town are located in the seismic intensity Ⅷ area. The area of seismic intensity Ⅵ and above covers an area of about 6 500km², spreading northwest in general. Many roads including Expressway G56 and national highway G215, pass through the estimated seismic intensity Ⅶ area, which may cause road damage and traffic disruption following this earthquake. On the other hand, the reliability of small amplitude observations recorded by far-field simple intensity meters need to be evaluated further. Finally, the seismogenic tectonic setting, the focal mechanism solution and the aftershock distribution of the earthquake also play a macro-control role in the distribution of the earthquake ground motion intensity. The results of this paper can provide theoretical basis and reference for earthquake emergency response decision-making and provide input for earthquake disaster emergency assessment.