Estimating terrestrial water storage (TWS) with high spatial resolution is crucial for hydrological and water resource management. Comparing to traditional in-situ data measurement, observation from space borne sensor such as Gravity Recovery and Climate Experiment (GRACE) satellites is quite effective to obtain a large-scale TWS data. However, the coarse resolution of the GRACE data restricts its application at a local scale. This paper presents three novel convolutional neural network (CNN) based approaches including the Super-Resolution CNN (SRCNN), the Very Deep Super-Resolution (VDSR), and the Residual Channel Attention Networks (RCAN) to spatial downscaling of the monthly GRACE TWS products using the outputs of the Ecological Assimilation of Land and Climate Observations (EALCO) model over Canada. We also compare the performance of CNN-based methods with the empirical linear regression-based downscaling method. All comparison results were evaluated by root mean square error (RMSE) between the reconstructed GRACE TWS and the original one. RMSEs over the matched pixels are 22.3, 14.4, 18.4 and 71.6 mm of SRCNN, VDSR, RCAN and linear regression-based method respectively. Obviously, VDSR shows the best accuracy among all methods. The result shows all CNN-based super resolution methods preform much better than traditional method in spatial downscaling.

Image mosaicking which is a process of constructing multiple orthoimages into a single seamless composite orthoimage, is one of the key steps for the production of large-scale digital orthophoto maps (DOM). Seamline determination is one of the most difficult technologies in the automatic mosaicking of orthoimages. The seamlines that follow the centerlines of roads where no significant differences exist are beneficial to improve the quality of image mosaicking. Based on this idea, this paper proposes a novel method of seamline determination based on road probability map from the D-LinkNet neural network for urban image mosaicking. This method optimizes the seamlines at both the semantic and pixel level as follows. First, the road probability map is obtained with the D-LinkNet neural network and related post processing. Second, the preferred road areas (PRAs) are determined by binarizing the road probability map of the overlapping area in the left and right image. The PRAs are the priority areas in which the seamlines cross. Finally, the final seamlines are determined by Dijkstra’s shortest path algorithm implemented with binary min-heap at the pixel level. The experimental results of three group data sets show the advantages of the proposed method. Compared with two previous methods, the seamlines obtained by the proposed method pass through the less obvious objects and mainly follow the roads. In terms of the computational efficiency, the proposed method also has a high efficiency.

Building rooftop data are of importance in several urban applications and in natural disaster management. In contrast to traditional surveying and mapping, by using high spatial resolution aerial images, deep learning-based building rooftops extraction methods are efficient and accurate. Although more training data is preferred in deep learning-based tasks, the effect of data volume on building extraction models is underexplored. Therefore, the paper explores the impact of data volume on the performance of building rooftop extraction from very-high-spatial-resolution (VHSR) images using deep learning-based methods. To do so, we manually labelled 0.12m spatial resolution aerial images and perform a comparative analysis of models trained on datasets of different sizes using popular deep learning architectures for segmentation tasks, including Fully Convolutional Networks (FCN)-8s, U-Net and DeepLabv3+. The experiments showed that with more training data, algorithms converged faster and achieved higher accuracy, while better algorithms were able to better mitigate the lack of training data.