Sök i SwePub databas

  Utökad sökning

Träfflista för sökning "WFRF:(Huang GuoRui) "

Sökning: WFRF:(Huang GuoRui)

  • Resultat 1-2 av 2
Sortera/gruppera träfflistan
  • Yu, ChaoQing, et al. (författare)
  • Managing nitrogen to restore water quality in China
  • 2019
  • Ingår i: Nature. - : Nature Publishing Group. - 0028-0836 .- 1476-4687. ; 567:7749, s. 516-520
  • Tidskriftsartikel (refereegranskat)abstract
    • The nitrogen cycle has been radically changed by human activities(1). China consumes nearly one third of the world's nitrogen fertilizers. The excessive application of fertilizers(2,3) and increased nitrogen discharge from livestock, domestic and industrial sources have resulted in pervasive water pollution. Quantifying a nitrogen 'boundary'(4) in heterogeneous environments is important for the effective management of local water quality. Here we use a combination of water-quality observations and simulated nitrogen discharge from agricultural and other sources to estimate spatial patterns of nitrogen discharge into water bodies across China from 1955 to 2014. We find that the critical surface-water quality standard (1.0 milligrams of nitrogen per litre) was being exceeded in most provinces by the mid-1980s, and that current rates of anthropogenic nitrogen discharge (14.5 +/- 3.1 megatonnes of nitrogen per year) to fresh water are about 2.7 times the estimated 'safe' nitrogen discharge threshold (5.2 +/- 0.7 megatonnes of nitrogen per year). Current efforts to reduce pollution through wastewater treatment and by improving cropland nitrogen management can partially remedy this situation. Domestic wastewater treatment has helped to reduce net discharge by 0.7 +/- 0.1 megatonnes in 2014, but at high monetary and energy costs. Improved cropland nitrogen management could remove another 2.3 +/- 0.3 megatonnes of nitrogen per year-about 25 per cent of the excess discharge to fresh water. Successfully restoring a clean water environment in China will further require transformational changes to boost the national nutrient recycling rate from its current average of 36 per cent to about 87 per cent, which is a level typical of traditional Chinese agriculture. Although ambitious, such a high level of nitrogen recycling is technologically achievable at an estimated capital cost of approximately 100 billion US dollars and operating costs of 18-29 billion US dollars per year, and could provide co-benefits such as recycled wastewater for crop irrigation and improved environmental quality and ecosystem services.
  • Feng, Wenqing, et al. (författare)
  • Building extraction from VHR remote sensing imagery by combining an improved deep convolutional encoder-decoder architecture and historical land use vector map
  • 2020
  • Ingår i: International Journal of Remote Sensing. - : Taylor & Francis. - 0143-1161. ; 41:17, s. 6595-6617
  • Tidskriftsartikel (refereegranskat)abstract
    • Building extraction has attracted considerable attention in the field of remote sensing image analysis. Fully convolutional network modelling is a recently developed technique that is capable of significantly enhancing building extraction accuracy. It is a prominent branch of deep learning and uses advanced state-of-the-art techniques, especially with regard to building segmentation. In this paper, we present an enhanced deep convolutional encoder-decoder (DCED) network by incorporating historical land use vector maps (HVMs) customized for building extraction. The approach combines enhanced DCED architecture with multi-scale image pyramid for pixel-wise building segmentation. The improved DCED network, together with symmetrical dense-shortcut connection structures, is employed to establish the encoders for automatic extraction of building features. The feature maps from early layers were fused with more discriminative feature maps from the deeper layers through ‘Res path’ skip connections for superior building extraction accuracy. To further reduce the occurrence of falsely segmented buildings, and to sharpen the buildings’ boundaries, the new temporal testing image is segmented under the constraints of an HVM. A majority voting strategy is employed to ensure the homogeneity of the building objects as the post-processing method. Experimental results indicate that the proposed approach exhibits competitive quantitative and qualitative performance, effectively alleviating the salt-and-pepper phenomenon and block effects, and retaining the edge structures of buildings. Compared with other state-of-the-art methods, our method demonstrably achieves the optimal final accuracies.
Skapa referenser, mejla, bekava och länka
  • Resultat 1-2 av 2

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy