With the popular use of high-resolution satellite images, remote sensing scene classification has always been a hot research topic in its related areas. However, limited to the issues of remote sensing datasets including the small scale of scene classes, the lack of rich label information and so on, it is quite challenging for deep learning methods to learn powerful feature representation. To overcome this problem, we propose a rotation-invariant feature learning and joint decision-making method based on Siamese convolutional neural networks with the combination of identification and verification models. Firstly, a novel data augmentation strategy is proposed specially for the Siamese model to learning rotation-invariant features. Secondly, a joint decision mechanism is introduced in our method, which is realized by the identification and verification model to better improve the classification performance. The proposed method can not only suppress problems caused by lack of rich label samples but also improve the robustness of Siamese convolutional neural networks. Experimental results demonstrate that the proposed method is effective and efficient for remote sensing scene classification.
Photochemical and biological degradation of dissolved organic carbon (DOC) and their interactions jointly contribute to the carbon dioxide released from surface waters in permafrost regions. However, the mechanisms that govern the coupled photochemical and biological degradation of DOC are still poorly understood in thermokarst lakes. Here, by combining Fourier transform ion cyclotron resonance mass spectrometry and microbial high-throughput sequencing, we conducted a sunlight and microbial degradation experiment using water samples collected from 10 thermokarst lakes along a 1100-km permafrost transect. We demonstrate that the enhancement of sunlight on DOC biodegradation is not associated with the low molecular weight aliphatics produced by sunlight, but driven by the photo-produced aromatics. This aromatic compound-driven acceleration of biodegradation may be attributed to the potential high abilities of the microbes to decompose complex compounds in thermokarst lakes. These findings highlight the importance of aromatics in regulating the sunlight effects on DOC biodegradation in permafrost-affected lakes.
Significant attention has been given to the way in which the soil nitrogen (N) cycle responds to permafrost thaw in recent years, yet little is known about anaerobic N transformations in thermokarst lakes, which account for more than one‐third of thermokarst landforms across permafrost regions. Based on the N isotope dilution and tracing technique, combined with qPCR and high‐throughput sequencing, we presented large‐scale measurements of anaerobic N transformations of sediments across 30 thermokarst lakes over the Tibetan alpine permafrost region. Our results showed that gross N mineralization, ammonium immobilization, and dissimilatory nitrate reduction rates in thermokarst lakes were higher in the eastern part of our study area than in the west. Denitrification dominated in the dissimilatory nitrate reduction processes, being two and one orders of magnitude higher than anaerobic ammonium oxidation (anammox) and dissimilatory nitrate reduction to ammonium (DNRA), respectively. The abundances of the dissimilatory nitrate reduction genes (nirK, nirS, hzsB, and nrfA) exhibited patterns consistent with sediment N transformation rates, while α diversity did not. The inter‐lake variability in gross N mineralization and ammonium immobilization was dominantly driven by microbial biomass, while the variability in anammox and DNRA was driven by substrate supply and organic carbon content, respectively. Denitrification was jointly affected by nirS abundance and organic carbon content. Overall, the patterns and drivers of anaerobic N transformation rates detected in this study provide a new perspective on potential N release, retention, and removal upon the formation and development of thermokarst lakes.
The influencing factors of coal and gas outburst are complex, now the accuracy and efficiency of outburst prediction and are not high, in order to obtain the effective features from influencing factors and realize the accurate and fast dynamic prediction of coal and gas outburst, this article proposes an outburst prediction model based on the coupling of feature selection and intelligent optimization classifier. Firstly, in view of the redundancy and irrelevance of the influencing factors of coal and gas outburst, we use Boruta feature selection method obtain the optimal feature subset from influencing factors of coal and gas outburst. Secondly, based on Apriori association rules mining method, the internal association relationship between coal and gas outburst influencing factors is mined, and the strong association rules existing in the influencing factors and samples that affect the classification of coal and gas outburst are extracted. Finally, svm is used to classify coal and gas outbursts based on the above obtained optimal feature subset and sample data, and Bayesian optimization algorithm is used to optimize the kernel parameters of svm, and the coal and gas outburst pattern recognition prediction model is established, which is compared with the existing coal and gas outbursts prediction model in literatures. Compared with the method of feature selection and association rules mining alone, the proposed model achieves the highest prediction accuracy of 93% when the feature dimension is 3, which is higher than that of Apriori association rules and Boruta feature selection, and the classification accuracy is significantly improved, However, the feature dimension decreased significantly; The results show that the proposed model is better than other prediction models, which further verifies the accuracy and applicability of the coupling prediction model, and has high stability and robustness.
Cloud computing is low-cost, high-performance network application model, is gradually affecting study, work and life of people. This article introduces cloud computing and function of cloud computing, then analyzes the exiting problems of campus network resource management, the cloud computing technology and methods are applied in the construction of college information sharing platform, which can not only improve the utilization of college information resource and college information resources management, but also achieve efficient application and centralized management of college information resource with the help of efficient cloud computing capabilities and unlimited storage capacity.Index Terms-cloud computing, campus network, resource management.I.
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.