Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling
Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling
复制标题
DOI：
10.3390/rs13122368
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
L. Stanislawski;E. Shavers;Shaowen Wang;Zhe Jiang;E. L. Usery;E. Moak;Alexander Duffy;Joel Schott-Joel-S
中科院分区：
文献类型：
--
作者：
L. Stanislawski;E. Shavers;Shaowen Wang;Zhe Jiang;E. L. Usery;E. Moak;Alexander Duffy;Joel Schott-Joel-S
区域地表水特征的精确地图对于推进生态、大气和土地开发研究是不可或缺的。阿拉斯加唯一全面的地表水特征图是国家水文数据集（NHD）。NHD要素通常是历史地形图蓝线的数字化表示，可能已经过时。在这里，我们测试深度学习方法，从机载干涉合成孔径雷达（IfSAR）数据中自动提取地表水特征，以更新和验证阿拉斯加水文数据库。U-net人工神经网络（ANN）和高性能计算（HPC）被用于监督水文特征提取的研究区域内，包括50个连续的流域在阿拉斯加。通过自动流量路由和手动编辑从高程导出的地表水特征用作训练数据。模型的可扩展性是用一系列16个U-网模型进行测试的，这些U-网模型在研究区域的百分比从大约3%增加到35%。水文预测的每个模型的所有流域没有使用的培训。输入栅格层来自数字地形模型、数字表面模型和来自IfSAR数据的强度图像。结果表明，约15%的研究区域需要最佳训练的人工神经网络提取水文时，F1分数测试流域平均在66和68之间。超过15%的研究区域进行培训几乎没有什么好处。完全连接的水文网络生成的U-网预测使用一种新的方法，约束的D-8流量路由的方法，以遵循U-网预测。这项工作展示了深度学习从广阔区域的复杂地形中获取地表水特征地图的能力。
Accurate maps of regional surface water features are integral for advancing ecologic, atmospheric and land development studies. The only comprehensive surface water feature map of Alaska is the National Hydrography Dataset (NHD). NHD features are often digitized representations of historic topographic map blue lines and may be outdated. Here we test deep learning methods to automatically extract surface water features from airborne interferometric synthetic aperture radar (IfSAR) data to update and validate Alaska hydrographic databases. U-net artificial neural networks (ANN) and high-performance computing (HPC) are used for supervised hydrographic feature extraction within a study area comprised of 50 contiguous watersheds in Alaska. Surface water features derived from elevation through automated flow-routing and manual editing are used as training data. Model extensibility is tested with a series of 16 U-net models trained with increasing percentages of the study area, from about 3 to 35 percent. Hydrography is predicted by each of the models for all watersheds not used in training. Input raster layers are derived from digital terrain models, digital surface models, and intensity images from the IfSAR data. Results indicate about 15 percent of the study area is required to optimally train the ANN to extract hydrography when F1-scores for tested watersheds average between 66 and 68. Little benefit is gained by training beyond 15 percent of the study area. Fully connected hydrographic networks are generated for the U-net predictions using a novel approach that constrains a D-8 flow-routing approach to follow U-net predictions. This work demonstrates the ability of deep learning to derive surface water feature maps from complex terrain over a broad area.