Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling

Abstract

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 NHD features are often digitized representations of historic topographic map blue lines and may be outdated.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.

Mapping small watercourses with deep learning – impact of training watercourse types separately

“…A CNN model based on U-Net (Ronneberger, Fisher and Brox 2015) was developed using the PyTorch 3 Python library. U-Net was chosen as base as it has been used for hydrographic feature extraction from DEMs before (e.g., Stanislawski et al 2021).…”

Automatic Pollen Classification and Segmentation Using U-Nets and Synthetic Data

“…Since they were initially proposed [29], U-nets have become a staple in many scientific fields in the task of class segmentation of complex tissues [30], cellular components [31], satellite image processing [32] and even geological studies [33].…”

GeoAI in the US Geological Survey for topographic mapping

“…An example of extending reference hydrographic data to extract additional features for the surrounding area using DL is shown in Figure 1. Methods are also being tested for fully automated extraction of hydrography from elevation by controlling flow accumulation models through DL (Stanislawski et al, 2021). HPC systems provide the computing power to rapidly generate or derive input data layers and test diverse strategies at speeds that make such testing viable.…”