Man-made reservoirs are key components of terrestrial hydrological systems. Identifying the location and number of reservoirs is the premise for studying the impact of human activities on water resources and environmental changes. While complete bottom-up censuses can provide a comprehensive view of the reservoir landscape, they are time-consuming and laborious and are thus infeasible on a global scale. Moreover, it is challenging to distinguish man-made reservoirs from natural lakes in remote sensing images. This study proposes a convolutional neural network (CNN)-based framework to recognize global reservoirs from Landsat 8 imageries. On the basis of the HydroLAKES dataset, a Landsat 8 cloud-free mosaic of 2017 was clipped for each feature (reservoir or lake) and was resized into 224 × 224 patches, which were collected as training and testing samples. Compared to other deep learning methods (Alexnet and VGG) and state-of-the-art traditional machine learning methods (support vector machine, random forest, gradient boosting, and bag-of-visual-words), we found that fine-tuning the pretrained CNN model, ResNet-50, could reach the highest accuracy (91.45%). Application cases in Kansas (USA, North America), Mpumalanga (South Africa, Africa), and Kostanay (Kazakhstan, Asia) resulted in classification accuracies of better than 99%, which showed the applicability of the proposed ResNet-50 model to the extraction of reservoirs from a vast amount of moderate resolution images. The framework that was developed in this paper is the first attempt to combine remote sensing big data and the deep learning technique to the recognition of reservoirs at a global scale.

The availability of lake bathymetry maps is imperative for estimating lake water volumes and their variability, which is a sensitive indicator of climate. It is difficult, if not impossible, to obtain bathymetric measurements from all of the thousands of lakes across the globe due to costly labor and/or harsh topographic regions. In this study, we develop a new digital lake bathymetry model (DLBM) using the step-wise water recession method (WRM) to generate 3-dimensional lake bathymetric maps based on the digital elevation model (DEM) alone, with two assumptions: (1) typically, the lake’s bathymetry is formed and shaped by geological processes similar to those that shaped the surrounding landmasses, and (2) the agent rate of water (the thickness of the sedimentary deposit proportional to the lake water depth) is uniform. Lake Ontario and Lake Namco are used as examples to demonstrate the development, calibration, and refinement of the model. Compared to some other methods, the estimated 3D bathymetric maps using the proposed DLBM could overcome the discontinuity problem to adopt the complex topography of lake boundaries. This study provides a mathematically robust yet cost-effective approach for estimating lake volumes and their changes in regions lacking field measurements of bathymetry, for example, the remote Tibetan Plateau, which contains thousands of lakes.

High-resolution land cover mapping over large areas is a challenging task due to the lack of high-quality labels. A potential solution is to leverage the existing knowledge contained in the freely available lower-resolution land cover products. However, the relatively low resolution and low accuracy of the products lead to numerous inaccurate labels, which harms the performance of the neural network. This article addresses the challenge by jointly optimizing the network parameters and correcting the noisy labels with a novel online noise correction approach and a synergistic noise correction loss. By incorporating the information entropy as a measurement to determine the probable correct labels, the proposed noise correction approach learns to make effective correction of the noisy labels during training and eventually boosts the performance with a training set containing less noisy labels. Experimental results show that the proposed method can effectively correct the noisy labels and reduce their negative impact on network training. By employing the proposed method, we produce a refined high-resolution (3-m) land cover map from a lower-resolution (10-m) product in China and improve the accuracy from 74.96% (10-m) to 81.32% (3-m). Such an approach that can effectively learn from noisy data sets leads to many potential opportunities for using and magnifying existing knowledge and results.

Accurate precipitation data is crucial in many applications such as hydrology, meteorology, and ecology. Compared with ground observations, satellite-based precipitation estimates can provide much more spatial information to characterize precipitation. In this study, the satellite-based precipitation products of Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG) and Tropical Rainfall Measurement Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) were firstly evaluated over the Tibetan Plateau (TP) in 2015 against ground observations at both annual and monthly scales. Secondly, random forest algorithm was used to obtain the annual downscaled results (~1 km) based on IMERG and TMPA data and the downscaled results were examined against rain gauge data. Thirdly, a disaggregation algorithm was used to obtain the monthly downscaled results based on those at annual scale. The results indicated that (1) IMERG performed better than TMPA at both annual and monthly scales; (2) IMERG had few anomalies while TMPA displayed significant numbers of outliers in central and western parts of the TP; (3) random forest was a promising algorithm in acquiring high resolution precipitation data with improved accuracy; (4) the downscaled results based on IMERG had better performances than those based on TMPA.

Channel network topology plays an important role in hydrological analysis. This letter proposes an innovative method to construct it based only on remote sensing images. The method uses spectral water indexes and mask of large lakes and ocean areas derived from remote sensing data to generate the map of channels. Then, a morphological thinning algorithm is introduced to extract the initial skeleton of channels. Moreover, an iterative pruning process based on a graph algorithm is proposed to simplify the initial skeleton. Finally, according to the simplified skeleton and its adjacency matrix, a new connectivity graph can be constructed to describe the channel network topology. The proposed method can construct complete skeleton structure and the topology of channels with good connectivity in an automatic way. The output will facilitate detailed hydrological modeling and further applications.