Human societies evolved alongside rivers, but how has the relationship between human settlement locations and water resources evolved over time? We conducted a dynamic analysis in the conterminous US to assess the coevolution of humans and water resources from 1790 to 2010. Here we show that humans moved closer to major rivers in pre-industrial periods but have moved farther from major rivers after 1870, demonstrating the dynamics of human reliance on rivers for trade and transport. We show that humans were preferentially attracted to areas overlying major aquifers since industrialization due to the emergent accessibility of groundwater in the 20^th century. Regional heterogeneity resulted in diverse trajectories of settlement proximity to major rivers, with the attractiveness of rivers increasing in arid regions and decreasing in humid areas. Our results reveal a historical coevolution of human-water systems, which could inform water management and contribute to societal adaptation to future climate change.

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.

In the published article [1], the authors realized some errors in the affiliation and email address of Yang Hong, and thus wish to make the following revisions: Add the Affiliation 5 “School of Civil Engineering and Environmental Science, University of Oklahoma, Norman, OK 73019, USA” for Yang Hong Change the email address of Yang Hong to yanghong@ou