Multisource remote sensing data have been widely used to improve land-cover classifications. The combination of synthetic aperture radar (SAR) and optical imagery can detect different land-cover types, and the use of genetic algorithms (GAs) and support vector machines (SVMs) can lead to improved classifications. Moreover, SVM kernel parameters and feature selection affect the classification accuracy. Thus, a GA was implemented for feature selection and parameter optimization. In this letter, a GA-SVM algorithm was proposed as a method of classifying multifrequency RADARSAT-2 (RS2) SAR images and Thaichote (THEOS) multispectral images. The results of the GA-SVM algorithm were compared with those of the grid search algorithm, a traditional method of parameter searching. The results showed that the GA-SVM algorithm outperformed the grid search approach and provided higher classification accuracy using fewer input features. The images obtained by fusing RS2 data and THEOS data provided high classification accuracy at over 95%. The results showed improved classification accuracy and demonstrated the advantages of using the GA-SVM algorithm, which provided the best accuracy using fewer features.

Mangrove forests, one of the highest carbon density ecosystems, are very different from other forests as they occupy saline and tidal habitats. Although previous studies in forests, shrublands and grasslands have shown a positive effect of biodiversity on plant biomass and carbon storage, it remains unclear whether this relation to biodiversity also exists in mangrove forests. Here, we evaluate the possible effects of mangrove species diversity, structural characteristics and environmental factors on mangrove biomass production and carbon storage, using survey data from 234 field plots of 30 transects in the mangrove forests along the coastlines of Hainan Island, China, during 2017 and 2018. We found that mangrove species diversity had a positive effect, not only on mangrove biomass production but also on soil carbon storage. This positive effect was more strongly evident in the forest communities than in either the shrub communities or forest‐shrub mixed communities, with the forest type having the biggest mangrove biodiversity and carbon storage. Besides, the diversity effect was affected by structural characteristics, namely, mangrove biomass increased exponentially with tree stem diameter and decreased with tree density. Furthermore, we observed a resource‐dependent mediation of the mangrove ecosystem when linking diversity to biomass. The areas with high soil Nitrogen content and Mean annual precipitation (MAP) showed higher mangrove biomass and carbon storage. This suggests that the spatial pattern of mangrove carbon storage and diversity was driven by both climate factors (MAP) and soil fertility (soil N). To our knowledge, this is the first study based on an intensive field survey that has verified the positive effect of biodiversity on mangrove biomass and carbon storage. Our findings suggest that mangrove forests with greater diversity also have higher carbon storage capacities and conservation potential. Thus, biodiversity conservation is crucial for mangroves to mitigate the greenhouse effect. Our findings strengthen the understanding of the diversity effects on mangrove ecosystem services and have important implications for mangrove restoration and conservation. A free Plain Language Summary can be found within the Supporting Information of this article.

The identification of species within an ecosystem plays a key role in formulating an inventory for use in the development of conservation management plans. The classification of mangrove species typically involves intensive field surveys, whereas remote sensing techniques represent a cost-efficient means of mapping and monitoring mangrove forests at large scales. However, the coarse spectral resolution of remote sensing technology has up until recently restricted the ability to identify individual species. The more recent development of very high-resolution spatial optical remote sensing sensors and techniques has thus provided new opportunities for the accurate mapping of species within mangrove forests over large areas. When dealing with the complex problems associated with discriminating among species, classifier performance could be enhanced through the adoption of more intrinsic features; such as textural and differential spectral features. This study explored the effectiveness of textural and differential spectral features in mapping mangrove inter-species obtained from WorldView-3 high-spatial-resolution imagery for mangrove species in Hong Kong. Due to the different arrangement of leaves, the branch density, and the average height and size of plants, we found that the differential spectral features could aid in reducing inner-species variability and increasing intra-species separation. Using a combination of textural and differential spectral features thus represents a promising tool for discriminating among mangrove species. Experimental results suggest that combining these features can greatly improve mapping accuracy, thereby providing more reliable mapping results.

Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.