No abstract

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.

Nano-silicon composites have been extensively studied as anode materials for next-generation lithium-ion batteries due to their excellent electrochemical performances. However, the high production cost and complex synthesis methods of the composites are not conducive to their practical application. Here, we aim to use low-cost raw materials to prepare micron-scale carbon-coated porous silicon anode materials, overcoming the problem of silicon volume expansion, while improving the conductivity of anode and promoting the diffusion of lithium ions. The reduced production cost of the micron-scale silicon-based anode and its simple preparation method are beneficial to high tap density and practical application. Due to the synergistic effect of the carbon shell and porous structure, the prepared micron-scale silicon-based anode shows good cycle stability, with a high specific capacity of 845 mA h g–1 after 150 cycles and a capacity retention rate of 97.5% at a current density of 1000 mA g–1. Furthermore, the capacity retention is 83.7% after 300 cycles. Full cells assembled with LiNi0.8Mn0.1Co0.1O2 cathode also exhibited good cycle stability and high stack cell energy density.

No abstract