Yellow rust in winter wheat is a widespread and serious fungal disease, resulting in significant yield losses globally. Effective monitoring and accurate detection of yellow rust are crucial to ensure stable and reliable wheat production and food security. The existing standard methods often rely on manual inspection of disease symptoms in a small crop area by agronomists or trained surveyors. This is costly, time consuming and prone to error due to the subjectivity of surveyors. Recent advances in unmanned aerial vehicles (UAVs) mounted with hyperspectral image sensors have the potential to address these issues with low cost and high efficiency. This work proposed a new deep convolutional neural network (DCNN) based approach for automated crop disease detection using very high spatial resolution hyperspectral images captured with UAVs. The proposed model introduced multiple Inception-Resnet layers for feature extraction and was optimized to establish the most suitable depth and width of the network. Benefiting from the ability of convolution layers to handle three-dimensional data, the model used both spatial and spectral information for yellow rust detection. The model was calibrated with hyperspectral imagery collected by UAVs in five different dates across a whole crop cycle over a well-controlled field experiment with healthy and rust infected wheat plots. Its performance was compared across sampling dates and with random forest, a representative of traditional classification methods in which only spectral information was used. It was found that the method has high performance across all the growing cycle, particularly at late stages of the disease spread. The overall accuracy of the proposed model (0.85) was higher than that of the random forest classifier (0.77). These results showed that combining both spectral and spatial information is a suitable approach to improving the accuracy of crop disease detection with high resolution UAV hyperspectral images.

Land cover information plays an important role in mapping ecological and environmental changes in Earth’s diverse landscapes for ecosystem monitoring. Remote sensing data have been widely used for the study of land cover, enabling efficient mapping of changes of the Earth surface from Space. Although the availability of high-resolution remote sensing imagery increases significantly every year, traditional land cover analysis approaches based on pixel and object levels are not optimal. Recent advancement in deep learning has achieved remarkable success on image recognition field and has shown potential in high spatial resolution remote sensing applications, including classification and object detection. In this paper, a comprehensive review on land cover classification and object detection approaches using high resolution imagery is provided. Through two case studies, we demonstrated the applications of the state-of-the-art deep learning models to high spatial resolution remote sensing data for land cover classification and object detection and evaluated their performances against traditional approaches. For a land cover classification task, the deep-learning-based methods provide an end-to-end solution by using both spatial and spectral information. They have shown better performance than the traditional pixel-based method, especially for the categories of different vegetation. For an objective detection task, the deep-learning-based object detection method achieved more than 98% accuracy in a large area; its high accuracy and efficiency could relieve the burden of the traditional, labour-intensive method. However, considering the diversity of remote sensing data, more training datasets are required in order to improve the generalisation and the robustness of deep learning-based models.

We report the generation and analysis of mutant mice bearing a targeted disruption of the heparan sulfate (HS)-modifying enzyme GlcNAc N-deacetylase/N-sulfotransferase 3 (NDST3). NDST3؊/؊ mice develop normally, are fertile, and show only subtle hematological and behavioral abnormalities in agreement with only moderate HS undersulfation. Compound mutant mice made deficient in NDST2;NDST3 activities also develop normally, showing that both isoforms are not essential for development. In contrast, NDST1؊/؊ ;NDST3 ؊/؊ compound mutant embryos display developmental defects caused by severe HS undersulfation, demonstrating NDST3 contribution to HS synthesis in the absence of NDST1. Moreover, analysis of HS composition in dissected NDST3 mutant adult brain revealed regional changes in HS sulfation, indicating restricted NDST3 activity on nascent HS in defined wild-type tissues. Taken together, we show that NDST3 function is not essential for development or adult homeostasis despite contributing to HS synthesis in a region-specific manner and that the loss of NDST3 function is compensated for by the other NDST isoforms to a varying degree. Heparan sulfate (HS)2 is produced by most mammalian cells as part of membrane and extracellular matrix proteoglycans (1). The chain grows by the copolymerization of GlcA␤1,4 and GlcNAc␣1,4 residues and undergoes modification by one or more of the four NDST isozymes, which remove acetyl groups from subsets of GlcNAc residues and add sulfate to the free amino groups. In vertebrates, ndst1 and ndst2 mRNA are expressed in all embryonic and adult tissues examined, whereas ndst3 and ndst4 transcripts are predominantly expressed during embryonic development and in the adult brain (2). Most subsequent modifications of the HS chain by O-sulfotransferases and a GlcA C5-epimerase depend on the presence of GlcNS residues, making the NDSTs largely responsible for the generation of sulfated ligand binding sites in HS (3-5). In vitro, NDST3 differs biochemically from the other NDST isoforms by possessing a high deacetylase activity but very low sulfotransferase activity (2).Many growth factors and morphogens bind to HS. In some cases, HS-proteoglycans are thought to act as co-receptors for these ligands. Studies in Drosophila melanogaster demonstrated that HS is crucial for embryonic development (6) and that the fly NDST ortholog, Sulfateless, affects signaling mediated by Wingless (Wg), Hedgehog (HH), and fibroblast growth factor (FGF) (7-9). The ability of HS to regulate the activity of morphogens and growth factors is currently best understood for the FGFs. HS was found to be a necessary component of FGF-FGF receptor binding and assembly (10), and global changes in HS expression regulate FGF and FGF receptor assembly during mouse development (11). Due to the multiple developmental processes regulated by the 23 FGFs, including those of the lung, limbs, heart, skeleton, and brain (reviewed in Ref. 12), perturbed HS synthesis results in the generation of FGF-related phenotypes (13,14). The crucial rol...

No abstract