Hyperspectral remote sensing of salinity stress on red (Rhizophora mangle) and white (Laguncularia racemosa) mangroves on Galapagos Islands

Mangroves are an assemblage of salt-tolerant woody hydrophytes that are the foundational species along tropical and subtropical coastlines, estuaries, lagoons and rivers. Once covering 75% of the world's tropical and subtropical coastlines, mangrove forests have been declining rapidly throughout the world in the last few decades. Monitoring and modelling mangrove forest growth are critical for their conservation. Salinity is one of the primary limiting factors for mangrove forest growth. In this letter, we report the potential of using hyperspectral remotely sensed data collected in the field for monitoring the photosynthesis rate of red (Rhizophora mangle) and white (Laguncularia racemosa) mangroves with regard to salinity gradient. Using photochemical reflectance index (PRI) as proxy for photosynthetic rate, PRI for both species are strongly related to salinity gradient, indicating the potential of monitoring mangrove forest growth on a regional scale using hyperspectral remote sensing.     

Extraction of snow cover from high-resolution remote sensing imagery using deep learning on a small dataset

ABSTRACT

Snow cover is of great significance for many applications. However, automatic extraction of snow cover from high spatial resolution remote sensing (HSRRS) imagery remains challenging, owing to its multiscale characteristics, similarities to clouds, and occlusion by the shadows of mountains and clouds. Deep convolutional neural networks for semantic segmentation are the most popular approach to automatic map generation, but they require huge computing time and resources, as well as a large dataset of pixel-wise annotated HSRRS images, which precludes the application of many superior models. In this study, these limitations are overcome by using a sequence of transfer learning steps. The method starts with a modified aligned ‘Xception’ model pre-trained for object classification on ImageNet. Subsequently, a ‘DeepLab version three plus’ (DeepLabv3+) model is trained using a large dataset of Landsat images and corresponding snow cover products. Finally, a second transfer learning step is employed to fine-tune the model on the small dataset of GaoFen-2, the highest resolution HSRRS satellite in China. Experiments demonstrate the feasibility and effectiveness of this framework for automatic snow cover extraction.