In recent years, deep-learning-based hyperspectral image (HSI) classification networks have become one of the most dominant implementations in HSI classification tasks. Among these networks, convolutional neural networks (CNNs) and attention-based networks have prevailed over other HSI classification networks. While convolutional neural networks with perceptual fields can effectively extract local features in the spatial dimension of HSI, they are poor at capturing the global and sequential features of spectral–spatial information; networks based on attention mechanisms, for example, Transformer, usually have better ability to capture global features, but are relatively weak in discriminating local features. This paper proposes a fusion network of convolution and Transformer for HSI classification, known as FusionNet, in which convolution and Transformer are fused in both serial and parallel mechanisms to achieve the full utilization of HSI features. Experimental results demonstrate that the proposed network has superior classification results compared to previous similar networks, and performs relatively well even on a small amount of training data.
In recent years, earthquakes have occurred frequently on the southeastern edge of the Tibetan Plateau, and the seismic hazard is high. However, because of the remote location of the Ganzi-Yushu fault zone, no high-resolution geodetic measurements of this region have been made. The radar line-of-sight deformation field of the Ganzi-Yushu fault was obtained using seven-track ascending and descending Sentinel-A/B interferometric synthetic aperture radar (InSAR) data from 2014 to 2020. Using the InSAR and published Global Navigation Satellite System (GNSS) data, we calculated the 3D deformation field in the study area, investigated the segment-specific fault slip rate, and inverted the fault slip distribution pattern using the steepest descent method. We then evaluated the seismic hazard using the strain rate field and slip deficit rate. The main findings of this study include the following. 1) The slip rate of the Ganzi-Yushu fault gradually increases from 2.5 to 6.8 mm/yr from northwest to southeast. 2) A high-resolution strain rate map shows high-value anomalies in the Yushu and Dangjiang areas. 3) Our comprehensive analysis suggests that the seismic hazard of the Dangjiang and Dengke segments with high slip deficits cannot be ignored.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.