Automatic Image-Based Event Detection for Large-N Seismic Arrays Using a Convolutional Neural Network

A Multidisciplinary Approach for the Vulnerability Assessment of a Venetian Historic Palace: High Water Phenomena and Climate Change Effects

This paper illustrates a multidisciplinary approach aimed at the vulnerability assessment of historic masonry heritage in Venice, focusing on questions of method and practice, which specifically involve the disciplines of restoration, building archaeology and structural engineering. Taking into account the existing standards for the management and assessment of cultural heritage, an integrated methodology is proposed for analyzing and interpreting historic constructions. Particular reference is made to Venetian scenery and its relationship with water, from the worldwide known high tide phenomena to the new perspectives offered by MOSE (i.e., Experimental Electromechanical Module, a system of a series of retractable mobile gates) and the new challenges due to climate change. Within such an approach, the different disciplines, including the building archeology, contribute to obtaining an interpretative model for historic buildings subjected to the high tide phenomena, with the aim of performing a vulnerability assessment and to design possible restoration interventions. The proposed methodology is applied to the case study of a Venetian historic palace facing the Grand Canal. For this palace, all the steps of the knowledge path have been carried out, from historical study to geometrical, Material-Constructive Survey, Crack Pattern and Degradation Analysis to stratigraphic analysis. The interpretative model obtained at the end of this path is enriched with the results of preliminary numerical analyses that investigate, in greater depth, the effects of high water phenomena on the rising damp front in masonry walls. Some previsions on the effects of MOSE activation and of climatic change, in particular in terms of sea-level rise, are presented.

A Two-Stage Seismic Damage Assessment Method for Small, Dense, and Imbalanced Buildings in Remote Sensing Images

Large-scale optical sensing and precise, rapid assessment of seismic building damage in urban communities are increasingly demanded in disaster prevention and reduction. The common method is to train a convolutional neural network (CNN) in a pixel-level semantic segmentation approach and does not fully consider the characteristics of the assessment objectives. This study developed a machine-learning-derived two-stage method for post-earthquake building location and damage assessment considering the data characteristics of satellite remote sensing (SRS) optical images with dense distribution, small size, and imbalanced numbers. It included a modified You Only Look Once (YOLOv4) object detection module and a support vector machine (SVM) based classification module. In the primary step, the multiscale features were successfully extracted and fused from SRS images of densely distributed buildings by optimizing the YOLOv4 model toward the network structures, training hyperparameters, and anchor boxes. The fusion improved multi-channel features, optimization of network structure and hyperparameters have significantly enhanced the average location accuracy of post-earthquake buildings. Thereafter, three statistics (i.e., the angular second moment, dissimilarity, and inverse difference moment) were further discovered to effectively extract the characteristic value for earthquake damage from located buildings in SRS optical images based on the gray level co-occurrence matrix. They were used as the texture features to distinguish damage intensities of buildings, using the SVM model. The investigated dataset included 386 pre- and post-earthquake SRS optical images of the 2017 Mexico City earthquake, with a resolution of 1024 × 1024 pixels. Results show that the average location accuracy of post-earthquake buildings exceeds 95.7% and that the binary classification accuracy for damage assessment reaches 97.1%. The proposed two-stage method was validated by its extremely high precision in respect of densely distributed small buildings, indicating the promising potential of computer vision in large-scale disaster prevention and reduction using SRS datasets.