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., 1024x1024) 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 research, which often requires extensive imagery for model performance.
翻译:在这份文件中,我们展示了利用深层学习产生现实的河流图像的实际应用。具体地说,我们探索了能够产生高分辨率和现实的河流图像的基因对抗网络模型(GAN),该模型可用于支持地表水估计、河流间游、湿地损耗和其他水文研究方面的建模和分析。首先,我们建立了一个广泛的河上间接图像储存库,用于培训。第二,我们纳入了一个网络架构,即进步增长GAN(PGGAN),这一网络架构反复培训小分辨率的GAN(PGAN),以逐步形成一个非常高的分辨率(即1024x1024)的合成河流图像。在较简单的GAN结构下,在培训时间迅速增加和消失/爆炸梯度问题方面出现了困难,而PGGAN的实施似乎大大减少了这些困难。本研究的结果显示,在生成高质量图像和捕捉河流结构和水流的细节以支持水文研究方面大有希望,而水文研究通常需要广泛的图像才能产生模型性。