Search

Semantic segmentation is crucial for a wide range of downstream applications in remote sensing, aiming to classify pixels in remote sensing images (RSIs) at the semantic level. The dramatic variations in grayscale and the stacking of categories within RSIs lead to unstable inter-class variance and exacerbate the uncertainty around category boundaries. However, existing methods typically emphasize spatial information while overlooking frequency insights, making it difficult to achieve desirable results. To address these challenges, we propose a novel dual-domain fusion network that integrates both spatial and frequency features. For grayscale variations, a multi-level wavelet frequency decomposition module (MWFD) is introduced to extract and integrate multi-level frequency features to enhance the distinctiveness between spatially similar categories. To mitigate the uncertainty of boundaries, a type-2 fuzzy spatial constraint module (T2FSC) is proposed to achieve flexible higher-order fuzzy modeling to adaptively constrain the boundary features in the spatial by constructing upper and lower membership functions. Furthermore, a dual-domain feature fusion (DFF) module bridges the semantic gap between the frequency and spatial features, effectively realizes semantic alignment and feature fusion between the dual domains, which further improves the accuracy of segmentation results. We conduct comprehensive experiments and extensive ablation studies on three well-known datasets: Vaihingen, Potsdam, and GID. In these three datasets, our method achieved 74.56%, 73.60%, and 81.01% mIoU, respectively. Quantitative and qualitative results demonstrate that the proposed method significantly outperforms state-of-the-art methods, achieving an excellent balance between segmentation accuracy and computational overhead. [ABSTRACT FROM AUTHOR]

The intelligent segmentation of high-resolution remote sensing (HRS) image, also called as dense prediction task for HRS image, has been and will continue to be important research in the remote sensing community. In recent years, the growing wave of artificial intelligence (AI) technology has introduced innovative paradigms to this domain, yielding outstanding results and overcoming many challenges with conventional segmentation techniques. This paper provides a comprehensive review of these intelligent segmentation methodologies, including traditional pattern recognition, convolution neural network (CNN)-based, and Transformer-based techniques. However, the explosive but incomplete development of intelligent segmentation techniques also poses more challenges for earth observation experts, the most of which is the technical interpretability. Consequently, we consider these segmentation techniques in the aspect of explainable artificial intelligence (XAI). Data-centric XAI thinks the practical applications of the segmentation model while model-centric XAI will facilitate the understanding of decision-making processes and the adjustment of structural features. Moreover, this review identifies novel research questions and provides constructive insights and recommendations to HRS image segmentation tasks, which may shed new light on the intelligent segmentation methods within the remote sensing image understanding community. [ABSTRACT FROM AUTHOR]

The release of phosphorous (P) via chemical weathering is a vital process that regulates the global cycling of numerous key elements and shapes the size of the Earth's biosphere. It has long been postulated that global climate should theoretically play a prominent role in governing P weathering rates. Yet, there is currently a lack of direct evidence for this relationship based on empirical data at the global scale. Here, using a compilation of temperature and P content data of global surface soils (0 to 30 cm), we demonstrate that P release does enhance at high mean annual surface temperatures. We propose that this amplification of nutrient supply with warming is a critical component of Earth's natural thermostat, and that this relationship likely caused expanded oceanic anoxia during past climate warming events. The potential acceleration of phosphorus loss from soils due to anthropogenic climate warming may pose threats to agricultural production, terrestrial and marine ecosystems, and alter marine redox landscapes.

Objective: To investigate the clinical feature of a family with hereditary hemorrhagic telangiectasia (HHT), and to study the mutation of its related genes., Methods: Medical histories of the family were analyzed to detect HHT patients according to the diagnostic criteria. ENG and ALK-1 genes of the proband and her two daughters were analyzed. DNA from the three patients' peripheral blood was extracted. The exons 2-10 and their intron-exon boundaries of ALK1 were amplified with PCR, and then the PCR products were sequenced and analyzed to identify the mutation., Results: There were 11 people in 41 family members of 4 generations were diagnosed as HHT. The proband and her two daughters suffered from multiple organ damage, the younger daughter appeared only imaging features instead of corresponding clinical symptoms. A missense mutation at the 1321 bp of cDNA (c.1321G>A) was detected in the exon 9 of ALK1, which resulted in valine 441 to methionine replacement in ALK-1 protein (p.Val441Met)., Conclusion: A Chinese family with HHT was studied and a missense mutation (c.1321G>A, p.Val441Met) of ALK-1 was discovered. This mutation is the genetic basis of the family with HHT and is reported for the first time in China. This research will not only help to further investigate molecular mechanism of pathogenesis of HTT, but also provide evidences and references for the following gene screening and genetic counseling on HTT family members.