Many studies of Earth surface processes and landscape evolution rely on having accurate and extensive data sets of surficial geologic units and landforms. Automated extraction of geomorphic features using deep learning provides an objective way to consistently map landforms over large spatial extents. However, there is no consensus on the optimal input feature space for such analyses. We explore the impact of input feature space for extracting geomorphic features from land surface parameters (LSPs) derived from digital terrain models (DTMs) using convolutional neural network (CNN)‐based semantic segmentation deep learning. We compare four input feature space configurations: (a) a three‐layer composite consisting of a topographic position index (TPI) calculated using a 50 m radius circular window, square root of topographic slope, and TPI calculated using an annulus with a 2 m inner radius and 10 m outer radius, (b) a single illuminating position hillshade, (c) a multidirectional hillshade, and (d) a slopeshade. We test each feature space input using three deep learning algorithms and four use cases: two with natural features and two with anthropogenic features. The three‐layer composite generally provided lower overall losses for the training samples, a higher F1‐score for the withheld validation data, and better performance for generalizing to withheld testing data from a new geographic extent. Results suggest that CNN‐based deep learning for mapping geomorphic features or landforms from LSPs is sensitive to input feature space. Given the large number of LSPs that can be derived from DTM data and the variety of geomorphic mapping tasks that can be undertaken using CNN‐based methods, we argue that additional research focused on feature space considerations is needed and suggest future research directions. We also suggest that the three‐layer composite implemented here can offer better performance in comparison to using hillshades or other common terrain visualization surfaces and is, thus, worth considering for different mapping and feature extraction tasks.
- Award ID(s):
- 1654462
- NSF-PAR ID:
- 10425442
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 13
- Issue:
- 22
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 4630
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
null (Ed.)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.more » « less
-
Improving high-resolution (meter-scale) mapping of snow-covered areas in complex and forested terrains is critical to understanding the responses of species and water systems to climate change. Commercial high-resolution imagery from Planet Labs, Inc. (Planet, San Francisco, CA, USA) can be used in environmental science, as it has both high spatial (0.7–3.0 m) and temporal (1–2 day) resolution. Deriving snow-covered areas from Planet imagery using traditional radiometric techniques have limitations due to the lack of a shortwave infrared band that is needed to fully exploit the difference in reflectance to discriminate between snow and clouds. However, recent work demonstrated that snow cover area (SCA) can be successfully mapped using only the PlanetScope 4-band (Red, Green, Blue and NIR) reflectance products and a machine learning (ML) approach based on convolutional neural networks (CNN). To evaluate how additional features improve the existing model performance, we: (1) build on previous work to augment a CNN model with additional input data including vegetation metrics (Normalized Difference Vegetation Index) and DEM-derived metrics (elevation, slope and aspect) to improve SCA mapping in forested and open terrain, (2) evaluate the model performance at two geographically diverse sites (Gunnison, Colorado, USA and Engadin, Switzerland), and (3) evaluate the model performance over different land-cover types. The best augmented model used the Normalized Difference Vegetation Index (NDVI) along with visible (red, green, and blue) and NIR bands, with an F-score of 0.89 (Gunnison) and 0.93 (Engadin) and was found to be 4% and 2% better than when using canopy height- and terrain-derived measures at Gunnison, respectively. The NDVI-based model improves not only upon the original band-only model’s ability to detect snow in forests, but also across other various land-cover types (gaps and canopy edges). We examined the model’s performance in forested areas using three forest canopy quantification metrics and found that augmented models can better identify snow in canopy edges and open areas but still underpredict snow cover under forest canopies. While the new features improve model performance over band-only options, the models still have challenges identifying the snow under trees in dense forests, with performance varying as a function of the geographic area. The improved high-resolution snow maps in forested environments can support studies involving climate change effects on mountain ecosystems and evaluations of hydrological impacts in snow-dominated river basins.more » « less
-
more » « less
Abstract The availability of high‐resolution digital elevation models (DEMs) derived from airborne light detection and ranging (LiDAR) surveys has spurred the development of several methods to identify and map fluvial terraces. The post‐glacial landscape of the Sheepscot River watershed, Maine, where land‐use change has produced fill terraces upstream of historic dam sites, was selected to implement a comparison between terrace mapping methodologies. At four study sites within the watershed, terraces were manually mapped on LiDAR‐DEM‐derived hillshade images to facilitate the comparison among fully and semi‐automated DEM‐based procedures, including: (1) spatial relationships between interpreted terraces and surrounding natural topography, (2) feature classification algorithms, and (3) the TerEx terrace mapping toolbox. Each method was evaluated based on its accuracy and ease of implementation. The four study sites have varying longitudinal slope (0.0008–0.006 m/m), channel width (< 5–30 m), surrounding landscape relief (20–80 m), type and density of surrounding land use, and mapped surficial geologic units. All methods generally overestimate terrace areas (average predicted area 210% of manually defined area) with the most accurate results achieved within confined river valleys surrounded by the steep hillslopes. Accuracy generally decreases for study sites surrounded by low‐relief landscapes (predicted areas ranged 4–953% of manual delineations). We conclude with the advantages and drawbacks of each method tested and make recommendations for the scenarios where the use of each method is most appropriate. Copyright © 2016 John Wiley & Sons, Ltd.
-
more » « less
Abstract Lidar datasets have been crucial for documenting the scale and nature of human ecosystem engineering and land use. Automated analysis methods, which have been rising in popularity and efficiency, allow for systematic evaluations of vast landscapes. Here, we use a Mask R‐CNN deep learning model to evaluate terracing—artificially flattened areas surrounded by steeper slopes—on islands in American Sāmoa. Mask R‐CNN is notable for its ability to simultaneously perform detection and segmentation tasks related to object recognition, thereby providing robust datasets of both geographic locations of terracing features and their spatial morphometry. Using training datasets from across American Sāmoa, we train this model to recognize terracing features and then apply it to the island of Tutuila to undertake an island‐wide survey for terrace locations, distributions and morphologies. We demonstrate that this model is effective (F1 = 0.718), but limitations are also documented that relate to the quality of the lidar data and the size of terracing features. Our data show that the islands of American Sāmoa display shared patterns of terracing, but the nature of these patterns are distinct on Tutuila compared with the Manu'a island group. These patterns speak to the different interior configurations of the islands. This study demonstrates how deep learning provides a better understanding of landscape construction and behavioural patterning on Tutuila and has the capacity to expand our understanding of these processes on other islands beyond our case study.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs13224630
