Super-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors affecting SRM accuracy. Studies have shown that SRM methods using deep learning techniques have significantly improved land cover mapping accuracy but have not coped well with spectral-spatial errors. This study proposes an end-to-end SRM model using a spectral-spatial generative adversarial network (SGS) with the direct input of multispectral remotely sensed imagery, which deals with spectral-spatial error. The proposed SGS comprises three parts: (1) Cube-based convolution for spectral unmixing is adopted to generate land cover fraction images. (2) A residual-inresidual dense block fully and jointly considers spectral and spatial information and reduces spectral errors. (3) A relativistic average GAN is designed as a backbone to further improve super-resolution performance and reduce spectral-spatial errors. SGS was tested in one synthetic and two realistic experiments with multi-/hyper-spectral remotely sensed imagery as the input, comparing the results with those of hard classification and several classic SRM methods. The results showed that SGS performed well at reducing land cover fraction errors, reconstructing spatial details, removing unpleasant and unrealistic land cover artifacts, and eliminating false recognition.

Mapping high-spatial-resolution surface water bodies in urban and suburban areas is crucial in understanding the spatial distribution of surface water. Although Sentinel-2 images are popular in mapping water bodies, they are impacted by the mixed-pixel problem. Sub-pixel mapping can predict finer-spatial-resolution maps from the input remote sensing image and reduce the mixed-pixel problem to a great extent. This study proposes a sub-pixel surface water mapping method based on morphological dilation and erosion operations and the Markov random field (DE_MRF) to predict a 2 m resolution surface water map for heterogeneous regions from Sentinel-2 imagery. DE_MRF first segments the normalized difference water index image to extract water pixels and then detects the mixed pixels by using combined morphological dilation and erosion operations. For the mixed pixels, DE_MRF considers the intra-pixel spectral variability by extracting multiple water endmembers and multiple land endmembers within a local window to generate the water fraction images through spectral unmixing. DE_MRF was evaluated in the Jinshui Basin, China. The results suggested that DE_MRF generated a lower commission error rate for water pixels compared to the comparison methods. Because DE_MRF considers the intra-class spectral variabilities in the unmixing, it is better in mapping sub-pixel water distribution in heterogeneous regions where different water bodies with distinct spectral reflectance are present.

Snail intermediate host monitoring and control are essential for interrupting the parasitic disease schistosomiasis. Identifying large-scale high-risk areas of snail spread after floods has been greatly facilitated by remote sensing imagery. However, previous studies have usually assumed that all inundation areas carry snails and may have overestimated snail spread areas. Furthermore, these studies only used a single environmental factor to estimate the snail survival risk probability, failing to analyze multiple variables, to accurately distinguish the snail survival risk in the snail spread areas. This paper proposes a systematic framework for early monitoring of snail diffusion to accurately map snail spread areas from remote sensing imagery and enhance snail survival risk probability estimation based on the snail spread map. In particular, the flooded areas are extracted using the Sentinel-1 Dual-Polarized Water Index based on synthetic aperture radar images to map all-weather flooding areas. These flood maps are used to extract snail spread areas, based on the assumption that only inundation areas that spatially interacted with (i.e., are close to) the previous snail distribution regions before flooding are identified as snail spread areas, in order to reduce the misclassification in snail spread area identification. A multiple logistic regression model is built to analyze how various types of snail-related environmental factors, including the normalized difference vegetation index (NDVI), wetness, river and channel density, and landscape fractal dimension impact snail survival, and estimate its risk probabilities in snail spread area. An experiment was conducted in Jianghan Plain, China, where snails are predominantly linearly distributed along the tributaries and water channels of the middle and lower reaches of the Yangtze River. The proposed method could accurately map floods under clouds, and a total area of 231.5 km2 was identified as the snail spread area. The snail survival risk probabilities were thus estimated. The proposed method showed a more refined snail spread area and a more reliable degree of snail survival risk compared with those of previous studies. Thus, it is an efficient way to accurately map all-weather snail spread and survival risk probabilities, which is helpful for schistosomiasis interruption.