Abstract
In this paper, we demonstrated a practical application of realistic river image generation using deep learning. Specifically, we explored a generative adversarial network (GAN) model capable of generating high-resolution and realistic river images that can be used to support modeling and analysis in surface water estimation, river meandering, wetland loss, and other hydrological research studies. First, we have created an extensive repository of overhead river images to be used in training. Second, we incorporated the Progressive Growing GAN (PGGAN), a network architecture that iteratively trains smaller-resolution GANs to gradually build up to a very high resolution to generate high quality (i.e., 1,024 × 1,024) synthetic river imagery. With simpler GAN architectures, difficulties arose in terms of exponential increase of training time and vanishing/exploding gradient issues, which the PGGAN implementation seemed to significantly reduce. The results presented in this study show great promise in generating high-quality images and capturing the details of river structure and flow to support hydrological modeling and research.
Highlights
Remote sensing and data-driven hydrological modeling (Chen and Han, 2016) make up two significant application areas in water resources management
The river can clearly be seen running through the center of the image, and the Progressive Growing Generative Adversarial Networks (GANs) (PGGAN) has done a good job of capturing the green detail present in the surrounding landscape
Even with thousands of river images with a green background, the GAN understood that this specific image should not have a green background, and was able to adapt to the different styles present in Dataset A
Summary
Remote sensing and data-driven hydrological modeling (Chen and Han, 2016) make up two significant application areas in water resources management These fields comprise the conjunction for monitoring and analysis of water across the terrain and simulation of the streamflow in rivers and streams. The assessment data can be relayed to first responders in the area to support rescue efforts during a flood and reduce any damage to life or property (Yildirim and Demir, 2019). Because of this very reason, it is critical for researchers and decision makers to have access to large repositories of river data (Sermet et al, 2020a)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
