Classification of drainage crossings on high-resolution digital elevation models: A deep learning approach
Classification of drainage crossings on high-resolution digital elevation models: A deep learning approach
复制标题
DOI：
10.1080/15481603.2023.2230706
复制
发表时间：
2023-07
影响因子：
6.7
通讯作者：
Di Wu;Ruopu Li;Banafsheh Rekabdar;Claire Talbert;Michael Edidem;Guangxing Wang
中科院分区：
文献类型：
--
作者：
Di Wu;Ruopu Li;Banafsheh Rekabdar;Claire Talbert;Michael Edidem;Guangxing Wang
摘要高分辨率数字高程模型（HRDEM）已被用于在地形相对平坦的景观中描绘精细尺度的水文特征。然而，已知与道路相关的人工流动障碍物会导致不正确的建模流线，因为这些障碍物大大增加了地形高程，并经常终止流线。一种常见的做法是破坏排水交叉点附近道路的高程，但这些交叉点通常无法获得。因此，开发一个可靠的流域交叉数据集是必不可少的，以改善水文划定HRDEM。本研究的目的是开发深度学习模型，用于对包含流动障碍物位置的图像进行分类。基于HRDEM和航空正射影像，不同的卷积神经网络（CNN）模型进行了训练和比较，以评估其在美国中西部四个不同流域的图像分类的有效性。我们的研究结果表明，大多数深度学习模型都可以持续达到90%以上的准确率。以HRDEM作为唯一输入特征的CNN模型被认为是最适合的模型。增加航空正射影像及其衍生的光谱指数对模型的精度来说是微不足道的，甚至是微不足道的。所选的最佳拟合模型在不同的地理环境下具有良好的可移植性。这项工作可以应用于改善高程派生水文制图在精细的空间尺度。
ABSTRACT High-Resolution Digital Elevation Models (HRDEMs) have been used to delineate fine-scale hydrographic features in landscapes with relatively level topography. However, artificial flow barriers associated with roads are known to cause incorrect modeled flowlines, because these barriers substantially increase the terrain elevation and often terminate flowlines. A common practice is to breach the elevation of roads near drainage crossing locations, which, however, are often unavailable. Thus, developing a reliable drainage crossing dataset is essential to improve the HRDEMs for hydrographic delineation. The purpose of this research is to develop deep learning models for classifying the images that contain the locations of flow barriers. Based on HRDEMs and aerial orthophotos, different Convolutional Neural Network (CNN) models were trained and compared to assess their effectiveness in image classification in four different watersheds across the U.S. Midwest. Our results show that most deep learning models can consistently achieve over 90% accuracies. The CNN model with HRDEMs as the sole input feature was found to be the best-fit one. The addition of aerial orthophotos and their derived spectral indices is insignificant to or even worsens the model’s accuracy. The selected best-fit model exhibits excellent transferability over different geographic contexts. This work can be applied to improve elevation-derived hydrography mapping at fine spatial scales.