Iran is located in the collision and compression zone between the Arabian Plate and the Eurasian Plate, where earthquakes occur frequently. The tectonic earthquake in north-central Iran on October 5, 2024, was once questioned as a nuclear explosion, drawing widespread attention. P/S spectral ratio was demonstrated to be an effective method for event discrimination. To distinguish whether an event is abnormal, this study established a basic screening baseline via the P/S spectral ratios from earthquakes in Iran with stations both inside and outside Iran. We firstly investigated the amplitude characteristics of regional seismic phases Pn, Pg, Sn, and Lg in Iran. For Iranian seismic events recorded by stations inside Iran, the Pn, Pg, Sn, and Lg phases are well-developed at most stations. For Iranian seismic events recorded by stations outside Iran, the Pn, Pg, Sn, and Lg phases are well-developed for earthquakes in northwestern Iran at many stations. For earthquakes in southern and east-central Iran, the Pn and Sn phases are developed at some stations, while the Pg and Lg phases are not. Based on the phase attenuation characteristics, we calculated the magnitude and distance amplitude corrected P/S ratios for each stations. According to the corrected Pg/Lg, Pn/Lg and Pn/Sn spectral ratios of earthquakes in Iran, we selected stations with relatively smaller P/S ratios as advantageous stations for screening abnormal seismic events. The distributions of Pg/Lg, Pn/Lg, and Pn/Sn spectral ratios for historical tectonic earthquakes in Iran are presented, providing a baseline for rapidly screening of abnormal earthquakes. We calculated the P/S spectral ratio residuals of the earthquake occurred on October 5, 2024 in north-central Iran. The results show that the P/S ratios of the earthquake are similar to the historical tectonic earthquakes in a common region.
Extracting precise road information from remote sensing images (RSIs) remains challenging due to the interference from similar objects and occlusion from surroundings. To alleviate these issues, we propose a novel road extraction network to enhance both the precision and topological connectivity of extracted road networks, dubbed as CRNet. Specifically, a global-local context decoupling module (GLCDM) is introduced to explicitly model long-range contextual dependencies while preserving fine-grained local road features, thereby improving the model's inference capability in occluded regions. Furthermore, a semantic-spatial feature refinement module (SSFRM) is integrated into the skip connections, which leverages deep semantic features to guide the suppression of background noise in shallow feature maps across both channel and spatial dimensions, ensuring the decoder receives structurally accurate road representations. Experimental results on the remote sensing road datasets demonstrate that CRNet achieves state-of-the-art performance in terms of both segmentation accuracy and road connectivity.
Heterogeneous change detection (HeCD) is a highly valuable yet challenging task in remote sensing. However, existing HeCD methods primarily focus on well-registered images, without considering unregistered heterogeneous image pairs, which are more common in real-world applications. In this paper, we first analyze why unregistered images significantly complicate the HeCD problem: they not only cause boundary errors in change detection but also undermine the image transformation process required for making heterogeneous images comparable. These effects are further amplified by the intrinsic complexity of HeCD. In light of this, we propose an unsupervised iterative global mapping-local searching method (IGmLs) for HeCD subject to registration errors. Specifically, IGmLs utilizes the global mapping to transform images into a common structural space to enable the comparison of heterogeneous images, and uses the local searching to reduce the direct influence of registration errors on change metrics, which is based on the analysis that misregistration would cause an unwanted increment on the change metric in unchanged region. Then, IGmLs builds a Markov random field (MRF) model to combine the global mapping and local searching processes, which enhances the robustness to misregistrations by considering spatial correlations. Finally, an iterative framework is employed to backpropagate the matching and changing results to refine the global mapping and local searching processes, which further eliminates the indirect influence of changes and misregistration on the image transformation and change metrics. Extensive experiments on five datasets have demonstrated the effectiveness of the proposed IGmLs. The codes will be released at https://github.com/yulisun/IGmLs .
In this paper, a physics-informed multiresolution wavelet neural network (PIMWNN) method is proposed for solving partial differential equations (PDEs). This method uses the multiresolution wavelet neural network (MWNN) to approximate unknown functions, then substituting the MWNN into PDEs and training the MWNN by least-squares algorithm. We apply the proposed method to various problems, including stationary/nonstationary advection, diffusion and advection-diffusion problems, and linear/nonlinear time-dependent problems. Numerical experiments show that the PIMWNN method can achieve higher accuracy and faster speed than Physics Informed Neural Networks (PINNs). Moreover, the PIMWNN method can handle different boundary conditions easily and solve the time-dependent problems efficiently. The proposed method is expected to solve the spectral bias problem in network training. These characteristics show the great potential of the PIMWNN method used in the field of numerical solving methods for PDEs.
Remote sensing image change captioning aims to generate natural language descriptions of dynamic changes between bitemporal images. This task faces challenges of aligning high-level semantics with sparse change regions and modeling long-range dependencies in diverse change patterns. To alleviate these limitations, we propose the spatial-semantic alignment and change-aware network, dubbed SACNet. It introduces a semantic-spatial collaborative encoding module synergizing a CNN-based spatial encoder with a CLIP-based semantic encoder, using precise spatial cues to refine global semantic features. A change-driven adaptive feature calibration module emphasizes discriminative change signals via intertemporal feature dissimilarity modeling, suppressing background noise and highlighting key changes. In addition, a multipath state space model (SSM)-guided spatial representation module is designed to capture diverse complex spatial change topologies. Extensive experiments on the LEVIR-CC and WHU-CDC datasets demonstrate that SACNet achieves state-of-the-art performance, generating both high-precision textual descriptions and approximate change masks. Code will be available at https://github.com/CVer-Yang/SACNet
