RESUMO
Cloud detection is a crucial step in the optical satellite image processing pipeline for Earth observation. Clouds in optical remote sensing images seriously affect the visibility of the background and greatly reduce the usability of images for land applications. Traditional methods based on thresholding, multi-temporal or multi-spectral information are often specific to a particular satellite sensor. Convolutional Neural Networks for cloud detection often require labeled cloud masks for training that are very time-consuming and expensive to obtain. To overcome these challenges, this paper presents a hybrid cloud detection method based on the synergistic combination of generative adversarial networks (GAN) and a physics-based cloud distortion model (CDM). The proposed weakly-supervised GAN-CDM method (available online https://github.com/Neooolee/GANCDM) only requires patch-level labels for training, and can produce cloud masks at pixel-level in both training and testing stages. GAN-CDM is trained on a new globally distributed Landsat 8 dataset (WHUL8-CDb, available online doi:https://doi.org/10.5281/zenodo.6420027) including image blocks and corresponding block-level labels. Experimental results show that the proposed GAN-CDM method trained on Landsat 8 image blocks achieves much higher cloud detection accuracy than baseline deep learning-based methods, not only in Landsat 8 images (L8 Biome dataset, 90.20% versus 72.09%) but also in Sentinel-2 images ("S2 Cloud Mask Catalogue" dataset, 92.54% versus 77.00%). This suggests that the proposed method provides accurate cloud detection in Landsat images, has good transferability to Sentinel-2 images, and can quickly be adapted for different optical satellite sensors.
RESUMO
INTRODUCTION: Recent research focused on the interaction between land cover and the development of allergic and respiratory disease has provided conflicting results and the underlying mechanisms are not fully understood. In particular, green space, which confers an overall positive impact on general health, may be significantly contributing to adverse respiratory health outcomes. This study evaluates associations between surrounding residential land cover (green, grey, agricultural and blue space), including type of forest cover (deciduous, coniferous and mixed), and childhood allergic and respiratory diseases. METHODS: Data from 8063 children, aged 3-14 years, were obtained from nine European population-based studies participating in the HEALS project. Land-cover exposures within a 500 m buffer centred on each child's residential address were computed using data from the Coordination of Information on the Environment (CORINE) program. The associations of allergic and respiratory symptoms (wheeze, asthma, allergic rhinitis and eczema) with land coverage were estimated for each study using logistic regression models, adjusted for sex, age, body mass index, maternal education, parental smoking, and parental history of allergy. Finally, the pooled effects across studies were estimated using meta-analyses. RESULTS: In the pooled analyses, a 10% increase in green space coverage was significantly associated with a 5.9%-13.0% increase in the odds of wheezing, asthma, and allergic rhinitis, but not eczema. A trend of an inverse relationship between agricultural space and respiratory symptoms was observed, but did not reach statistical significance. In secondary analyses, children living in areas with surrounding coniferous forests had significantly greater odds of reporting wheezing, asthma and allergic rhinitis. CONCLUSION: Our results provide further evidence that exposure to green space is associated with increased respiratory disease in children. Additionally, our findings suggest that coniferous forests might be associated with wheezing, asthma and allergic rhinitis. Additional studies evaluating both the type of green space and its use in relation to respiratory conditions should be conducted in order to clarify the underlying mechanisms behind associated adverse impacts.
