Rivers are important elements of the earth’s ecosystem, and their spatial distribution information is critical for the study of hydrological and biogeochemical processes. Moderate Resolution Imaging Spectroradiometer (MODIS) imagery has been widely used for river mapping due to its high temporal resolution and long-term observation records, which are essential to capture the rapid fluctuation of rivers. However, when the conventional hard classification methods are used, the accuracy of the river maps produced from MODIS data (and especially for those rivers with narrow widths) is often limited because mixed pixels are common in MODIS imagery, due to coarse spatial resolution. In this article, a cascaded spectral–spatial information combined deep convolutional neural network (CNN) model for super-resolution river mapping (DeepRivSRM) is proposed to produce Landsat-like fine-resolution river maps from MODIS images. In DeepRivSRM, a CNN made up of a spectral unmixing module and a super-resolution mapping (SRM) module is introduced to handle the spectral and spatial information simultaneously. Moreover, for training the DeepRivSRM model, an adaptive cross-entropy loss function incorporating the fraction information of the rivers is designed to improve the performance of the DeepRivSRM model for small rivers. The proposed method was evaluated with MODIS images from three test sites and was compared with hard classification, a conventional SRM method, and a CNN-based SRM method. The results show that DeepRivSRM can generate more accurate river maps by effectively learning the subpixel-scale spatial–spectral information in MODIS imagery.

The spatiotemporal reflectance fusion method is used to blend high-temporal and low-spatial resolution images with their low-temporal and high-spatial resolution counterparts that were previously acquired by various satellite sensors. Recently, a wide variety of learning-based solutions have been developed, but challenges remain. These solutions usually require two sets of data acquired before and after the prediction time, making them unsuitable for near-real-time predicting. The solutions are always trained band by band and thus do not consider the spectral correlation. High-resolution temporal changes are difficult to reconstruct accurately with the network structure used, which lowers the accuracy of the fusion result. To address these problems, this study proposes a novel spatiotemporal adaptive reflectance fusion model using a generative adversarial network (GASTFN). In GASTFN, an end-to-end network, including a generative and discriminative network, is simultaneously trained for all spectral bands. The proposed model can be applied to the one-pair case, consider the spectral correlation of each band, and improve the process of producing super-resolution imagery by adopting the discriminative network for image reflectance values rather than temporal changes in reflectance. The proposed model has been verified with two actual satellite data sets acquired in heterogeneous landscapes and areas with abrupt changes, with a comparison of the state-of-art methods. The results show that GASTFN can generate the most accurate fusion images with more detailed textures, more realistic spatial shapes, and higher accuracy, demonstrating that the GASTFN is effective for predicting near-real-time changes in image reflectance and preserves the most valuable spatial information.

Mixed pixels often hinder accurate cropland mapping from remote sensing images with coarse spatial resolution. Image spatial super-resolution reconstruction technology is widely applied to address this issue, typically transforming coarse-resolution remote sensing images into fine spatial resolution images, which are then used to generate fine-resolution land cover maps using classification techniques. Deep learning has been widely used for image spatial super-resolution reconstruction; however, collecting training samples is often difficult for cropland mapping. Given that the quality of spatial super-resolution reconstruction directly impacts classification accuracy, this study aims to assess the impact of different types of training samples on image spatial super-resolution reconstruction and cropland mapping results by employing a Residual Channel Attention Network (RCAN) model combined with a spatial attention mechanism. Four types of samples were used for spatial super-resolution reconstruction model training, namely fine-resolution images and their corresponding coarse-resolution images, including original Sentinel-2 and degraded Sentinel-2 images, original GF-2 and degraded GF-2 images, histogram-matched GF-2 and degraded GF-2 images, and registered original GF-2 and Sentinel-2 images. The results indicate that the samples acquired by the histogram-matched GF-2 and degraded GF-2 images can resolve spectral band mismatches when simulating training samples from fine spatial resolution imagery, while the other three methods have limitations in their inability to fully address spectral and spatial mismatches. The histogram-matched method yielded the best image quality with PSNR, SSIM, and QNR values of 42.2813, 0.9778, and 0.9872, respectively, and produced the best mapping results, achieving an overall accuracy of 0.9306. By assessing the impact of training samples on image spatial super-resolution reconstruction and classification, this study addresses data limitations and contributes to improving the accuracy of cropland mapping, which is crucial for agricultural management and decision-making.