Geology Reports⌕ Search

Geology topics

Ethan J. Shavers

Publications and source records attributed to Ethan J. Shavers.

At least 19 recordsLinked to original sources
USGS2026

Estimating baseline flow resistance parameters for remote sensing river discharge (RSQ) from river morphology characteristics

This study demonstrates that flow resistance in rivers, quantified via calibration of a modified Manning equation, can be estimated from channel hydrometric information available from globally derived data sets for a subset of river reaches in Alaska and with less certainty in a subset of river reaches in the contiguous United States. The channel morphometry data sets tested include the National Aeronautics and Space Administration (NASA) Surface Water Ocean Topography (SWOT) river database (SWORD) and U.S. Geological Survey (USGS) Scale Specific Sinuosity (S3) river channel morphometry metrics. It is found that for the subset of rivers considered, the meander length, number of active channels, maximum width, width variance, and slope of the channel are strongly correlated with the flow resistance term in the Manning equation. Analytical machine learned models were derived, and a statistical multiple regression model developed to map the flow resistance in rivers across Alaska that are contained in the SWORD data base. The study points to the possibility of global a priori estimation of flow resistance in rivers for application in remote sensing of river discharge from river water surface-width, slope and height measurements made by SWOT and other satellites.

Journal of the American Water Resources Associatio↗
USGS2026

Structure-aware unsupervised transmission corridor structure extraction from 3DEP lidar using graph attention embeddings and reinforcement-learned DBSCAN

Transmission corridors are critical components of power delivery infrastructure, and their large-area monitoring increasingly relies on national-scale airborne lidar programs. This study presents an unsupervised, scalable framework for extracting transmission corridor structures (including conductors and supporting towers) from U.S. Geological Survey (USGS) 3D Elevation Program (3DEP) lidar point clouds. The workflow begins with height-above-ground filtering and statistical outlier removal to isolate elevated infrastructure candidates. Local Principal Component Analysis (PCA) is then used to compute fine-scale geometric descriptors. To incorporate spatial context and improve structural separability in feature space, we learn point embeddings using a Graph Attention Network (GAT) trained with a structure-consistency triplet objective, yielding representations tailored for downstream density-based grouping rather than semantic classification. To address the spatial non-stationarity of point density and noise across large scenes, we formulate Density-Based Spatial Clustering of Applications with Noise (DBSCAN) parameter selection as a reinforcement learning problem and employ Proximal Policy Optimization (PPO) to adapt 𝜀 and minPts at the block level based on embedding statistics. The final extraction is produced via block-wise DBSCAN and spatial merging to support efficient processing of multi-million-point clouds. Experiments on USGS 3DEP data over Houston, Texas, show that the proposed method produces spatially coherent candidate corridor structures from unstructured lidar. Quantitative assessment is conducted using OpenStreetMap (OSM)-referenced spatial-agreement metrics under a consistent vector-reference protocol, alongside comparative baselines and ablation studies, to examine the relative contributions of graph embedding learning and RL-based adaptive clustering.

Texas↗
USGS2026

Evaluating U.S. Geological Survey 3D Elevation Program LiDAR data as a source for building height

Accurate building height information is used for numerous urban applications, including infrastructure modeling, disaster risk assessment, and energy demand estimation. The U.S. Geological Survey collects airborne lidar data to support the three-dimensional elevation program (3DEP). The high point density and vertical accuracy of the lidar point clouds are optimal for 3D mapping. Few studies have systematically evaluated building height extraction from 3DEP lidar point clouds in urban areas. This study assesses the accuracy and consistency of building height estimates from two publicly available data sets by comparing them to the 3DEP lidar data. The public building height data sets are USA Structures and Microsoft Global Building Footprints (GBF), and they are evaluated across two contrasting urban sites. Building heights from USA Structures are also lidar-derived, whereas GBF estimates are based on stereo matching of optical imagery. Building heights from 3DEP were extracted by classifying lidar points using a deep learning model, isolating roof and ground returns, and computing the height as the median elevation difference between the roof and surrounding ground points. For both sites, 3DEP lidar-derived heights show strong agreement with USA Structures (R 2 = 0.87 and 0.86; MAE = 1.8 and 2.2 m), confirming the internal consistency and reliability of lidar-derived measurements. In contrast, comparisons with GBF height estimates reveal significantly lower correlations (R 2 = 0.54 and 0.60; MAE = 2.5 and 3.1 m), highlighting the limitations of imagery-based height reconstruction, particularly in dense or heterogeneous urban environments. These findings indicate that lidar can be used as an accurate source for vertical structure characterization and underscore the benefits of improved integration and bias correction when using imagery-derived building heights. The results provide support for hybrid approaches that combine the broad spatial coverage of optical data sets with the accuracy of lidar for scalable 3D urban mapping.

Colorado, Texas↗
USGS2025

The effects of line simplification on planform geometry

Data on maps should retain accuracy regardless of scale. Yet, as cartographic lines are generalized, there can be impacts on properties such as topology, density, and planform geometry. Here, we investigate the use of the Scale Specific Sinuosity (S3) metric (Stanislawski et al., 2023) to evaluate the effects of line simplification on planform geometry, which is the bends of streams in map view. We employ an open-source Python S3 workflow to characterize the geometry of five diverse stream channels in the United States. The original data are extracted from the U.S. Geological Survey National Hydrography Dataset 1:24,000-scale vector data (U.S. Geological Survey, 2000) (Table 1), and the simplification is done using the Visvalingam and Whyatt method (2017) with a simplification tolerance of 0.5, 1.0, 1.5, and 2.0 km. The S3 analysis is calculated at each level of simplification and S3 derivatives are generated. Derivatives include measures of sinuosity, fractal dimension, and the dominant bend wavelength. The findings show that the change in planform geometry is scale-dependent, though simplification will have little effect on straighter lines. The change becomes more apparent in complex lines as the degree of simplification aligns with the scale of the dominant bend geometries. These logical conclusions are evidence that the S3 is a useful metric for automated characterization of bend geometry regardless of line complexity.

Conference Paper↗
USGS2025

Multi-temporal surface water mapping with high-resolution elevation and image data through weakly supervised deep learning

Monitoring the extent of surface water features (hydrography), accurately storing them in databases, and representing them on topographic maps are essential for various applications such as navigation and policy-making for legislative boundaries and permitting. In this context, hydrographic data includes features that generally have water present or image data showing signs that water is forming a terrain channel, and which would be included in 1:24,000 or larger scale topographic maps. In addition, reliable hydrographic data play a critical role to help manage environmental risks such as droughts, floods, fires, and landslides, as well as monitoring biological resources and pollutants. Inaccuracies in hydrography data can lead to modelling inaccuracies, resulting in economic, social, and environmental risks. However, generating sufficiently accurate high-resolution (HR) hydrography and terrain data for these purposes remains a substantial challenge primarily because of complex surface water dynamics and data handling limitations.

Alaska↗
USGS2025

Assessment of density pattern retention of generalized data for 1:100,000-scale United States topographic maps

Cartographic generalization reduces the complexity of geographic data to produce legible, smaller-scale displays that retain essential information and logical geographic patterns. Generalization is a vital process in topographic map production. An important challenge in this process is managing and evaluating consistency across scale in the density and spatial distribution of map features such as buildings, roads, streams, water bodies, and elevation contours. Density patterns in these features reflect underlying physiographic conditions, which include factors such as bedrock geology, tectonics, climate, and landforms. Assessments of an acceptable level of change in feature density patterns are critical to ensuring the readability, usability, and accuracy of generalized maps and data. Preserving realistic density patterns across mapping scales also supports sustainable development goals in cartography, by helping to prioritize and communicate the relative reliability of geospatial data at specific scales.

Conference Paper↗
USGS2024

Evaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds

Studies have shown that digital surface models and point clouds generated by the United States Department of Agriculture’s National Agriculture Imagery Program (NAIP) can measure basic forest parameters such as canopy height. However, all measured forest parameters from these studies are evaluated using the differences between NAIP digital surface models (DSMs) and available lidar digital terrain models (DTMs). A survey of NAIP point cloud classification and related ground point-generated DTMs has not yet been undertaken. This study applies a Support Vector Machine (SVM) to classifying ground and nonground points from NAIP point clouds for test sites in Wyoming and Arizona, USA. Light detection and ranging (lidar) data from the U.S. Geological Survey 3D Elevation Program (3DEP) are used to validate the classified NAIP ground points and their corresponding DTMs. Comparing height differences between filtered NAIP ground points and 3DEP ground points, the SVM classifier’s results show that the vertical root mean square error value is 1.87 m and 1.69 m for the Wyoming and Arizona sites, respectively. If NAIP point clouds were continuously measured, the resulting availability of medium-resolution DTMs would benefit the application of multitemporal forest health monitoring and DTM generation.

Remote Sensing Letters↗
USGS2024

Transfer learning with convolutional neural networks for hydrological streamline delineation

Hydrological streamline delineation is critical for effective environmental management, influencing agriculture sustainability, river dynamics, watershed planning, and more. This study develops a novel approach to combining transfer learning with convolutional neural networks that capitalize on image-based pre-trained models to improve the accuracy and transferability of streamline delineation. We evaluate the performance of eleven image-based pre-trained models and a baseline model using datasets from Rowan County, North Carolina, and Covington River, Virginia in the USA. Our results demonstrate that when models are adapted to a new area, the fine-tuned ImageNet pre-trained model exhibits superior predictive accuracy, markedly higher than the models trained from scratch or those only fine-tuned on the same area. Moreover, the pre-trained model achieves better smoothness and connectivity between classified streamline channels. These findings underline the effectiveness of transfer learning in enhancing the delineation of hydrological streamlines across varied geographies, offering a scalable solution for accurate and efficient environmental modelling.

North Carolina, Virginia↗
USGS2024

Unravelling spatial heterogeneity of inundation pattern domains for 2D analysis of fluvial landscapes and drainage networks

Fluvial landscape analysis is an essential part of geomorphology, hydrology, ecology, and cartography. It is traditionally focused on the transition between hillslopes and channel domain, in which the network drainage is represented by static flow lines. However, the natural fluctuations of the processes occurring in the watershed induce lateral and longitudinal expansions and contractions in the drainage patterns and variations of stream surface area. These dynamics can be better understood by introducing a two-dimensional (2D) view of catchment hydrography, in which river width and floodplain are included in the analysis. The novelty introduced in this work is the development of a hydrodynamic hierarchical framework (HHF) to analyse the transitions among geomorphic and hydrographic features of the fluvial landscape, distinguishing hillslope, unchanneled valleys, floodplains, and single/multithreads channels. HHF is based on the estimation of nested inundation pattern domains (IPDs) from digital elevation models and 2D hydrodynamic modeling. IPDs are defined by scaling laws that characterize log–log relations between watershed drainage density and unit discharge thresholds extracted from a 2D direct rainfall method (DRM) under steady state solutions. The physical significance of the IPDs is analysed within the context of both the physiographic features of the fluvial landscape and the rainfall rates employed as input for the modeling approach. Initially, the spatial heterogeneity of the IPDs is used to derive stream width metrics as a function of the rainfall rate. Then, a spatial index, representative of the IPDs' heterogeneity, is introduced as a measure of the susceptibility of the drainage network surface area to expansion and contraction. Finally, the consistency of the results is assessed in comparison to another hydrodynamic-based method for fluvial landscape analysis recently proposed in the literature. The proposed approach is analysed using challenging mountain and low-relief environments, characterized by multithread channels, meander cut-offs, oxbow lakes, and extreme landscapes that feature glacial outwash, permafrost, and peatlands.

Alaska↗
USGS2024

Adaptive fine-tuning for transferring a U-net hydrography extraction model using K-means

The United States Geological Survey (USGS) coordinates the collection of hydrographic features derived from remotely sensed interferometric synthetic aperture radar (IfSAR) elevation and intensity data in Alaska. Hydrographic features are cartographic representations of surface water features such as stream, rivers, lakes, ponds, canals, etc. Collection and validation procedures involve complex automated and manual techniques that furnish snapshots of hydrographic vector data that exist during the IfSAR surveys. The dynamic nature of fluvial conditions warrants monitoring and updating hydrographic data, but extraction procedures for updates can be cost prohibitive. This paper overviews progress on automated workflows to extract hydrography from IfSAR data using deep learning methods trained and tested with USGS collected hydrography data. This research tests transfer learning methods on a well-performing U-net model trained on a 4600-square kilometer (sq km) base model area in northcentral Alaska. The base model is transferred and fine-tuned to regions in the target domain covering roughly 127,000 sq km. The target domain is subdivided into areas with similar hydrogeomorphic conditions using principal components and k-means clustering, and the base model is adaptively fine-tuned to each hydrogeomorphic class by selecting training watersheds from each cluster within the target domain. Results are compared with transfer learning that is fine-tuned with a random sample of watersheds in the target domain.

Conference Paper↗
USGS2024

Untangling the knots: A procedure for identifying discernibility conflicts on a cartographic line

Reducing detail on polyline features aids in legibility, allowing features to appear more distinct and preventing coalescence with other features. Current metrics for evaluating generalization outcomes emphasize geometric change rather than legibility. The present study reports on development and testing of a vector-based metric of the discernibility of a single polyline feature or group of features, defined as the absence of visual coalescence at a target map scale. This metric prioritizes legibility problems due to resolution and the physical/optical limits of discernibility. The metric identifies specific locations of coalescence, and is invariant to translation and rotation, providing a consistent measure across display contexts. A procedure for computing the above definition of discernibility and identifying the locations of discernibility conflicts will be presented. The algorithm is currently being tested in python code, and the goal is to include this tool in an open source python toolbox for cartographic generalization assessment.

Conference Paper↗
USGS2023

Automated mapping of culverts, bridges, and dams

Accurate maps of built structures around stream channels, such as dams, culverts, and bridges, are vital in monitoring infrastructure, risk management, and hydrologic modeling. Hydrologic modeling is essential for research and decisionmaking related to infrastructure and development planning, emergency management, ecology, and developing hydrographic data. Technological advances in remote sensing afford increasingly fine-scale elevation data, such as the U.S. Geological Survey 1-meter digital elevation models (DEMs), that can accurately model the Earth’s surface characteristics and related hydrologic dynamics. A long-standing challenge in flow modeling is the presence of built structures in an elevation model that resist flow in a way that does not reflect actual dynamics, such as culverts, bridges, and dams. This challenge is exacerbated in fine-scale elevation data as more built structures are resolved. Here we present a test of the extensibility of a culvert and dam detection workflow, culvert-net (CN). CN was developed using a large dataset of field-validated culverts, bridges, and dam locations for Alexander County, North Carolina, USA, supplemented by manual review and identification of additional features. In this workflow, the CN model is tested on a new study area in western Michigan, USA, where culverts and associated hydrography have recently been manually compiled.

Conference Paper↗
USGS2023

At what scales does a river meander? Scale-specific sinuosity (S3) metric for quantifying stream meander size distribution

Stream bend geometry is linked to terrain features, hydrologic and ecologic conditions, and anthropogenic forces. Knowledge of the distributions of geometric properties of streams advances understanding of changing landscape conditions and associated processes that operate over a range of spatial scales. Statistical decomposition of sinuosity in natural linear features has proven a longstanding challenge and a particular impediment to automated analysis. This paper demonstrates that sinuosity can vary with the magnitude of units at which it is measured (measurement scales). The paper derives a scale-specific sinuosity (S3) metric intended to measure stream bend geometry across a range of measurement scales. The metric is warranted for analysis and modeling at measurement scales equal or similar to the spatial process and landscape conditions under investigation. Derived from the Richardson (1961) plot, the S3 metric quantifies a frequency signature of planform bend sizes spanning a range of measurement units, enabling visual and quantitative analysis of bend geometry in linear stream features. Derivation of the metric makes evident a systematic relationship between stream bend size, sinuosity, and measurement scale, formalizing a relationship between sinuosity and fractal dimension. The paper shows the utility of the S3 metric in examining bend patterns for synthetic and real-world linear stream data.

Geomorphology↗
USGS2023

Generalization quality metrics to support multiscale mapping: Hausdorff and average distance between polylines

Large geospatial datasets must often be generalized for analysis and display at reduced scales. Automated methods including artificial intelligence and deep learning are being applied to this problem, but the results are often analyzed on the basis of limited and subjective measures. To better support automation, a project is underway to develop a robust Python toolkit for computing objective metrics of the quality of generalized vector data. Six metrics are currently under development: Hausdorff and average distance between polylines, feature density difference, polyline legibility, change in topological adjacency, and change in sinuosity. This paper discusses the development progress on tools to compute the Hausdorff and average distance between polylines, generating quality metrics to quantify displacement.

Conference Paper↗
USGS2023

Transferring deep learning models for hydrographic feature extraction from IfSAR data in Alaska

The National Hydrography Dataset (NHD) managed by the U.S. Geological Survey (USGS) is being updated with higher-quality feature representations through efforts that derive hydrography from 3DEP HR elevation datasets. Deriving hydrography from elevation through traditional flow routing and interactive methods is a complex, time-consuming process that must be tailored for different hydrogeomorphic conditions. The large volume of surface water features and HR remote sensing data make manual annotation of the water features over the entire nation infeasible. Furthermore, annual and seasonal variations of surface waters warrant some level of periodic updates to hydrography. Advances in deep learning technologies provide an opportunity to automate hydrography extraction and scale up the process to a nationwide level. One major challenge, however, is the effect of spatial heterogeneity due to the wide variety of hydrogeomorphic conditions in the United States. In other words, it is unclear how a deep learning model pre-trained in one set of hydrogeomorphic conditions can be effectively applied to other conditions for hydrographic feature extraction. This paper aims to provide some clarity in this regard by testing automated deep learning and its transferability to the extraction of hydrography from digital elevation model (DEM) data spanning a range of hydrogeomorphic conditions in Alaska. In transfer learning, the knowledge (e.g., neural network weights) from one domain is transferred to other domains and thereby decrease training requirements in the target domain.

Alaska↗
USGS2022

Scaling-up deep learning predictions of hydrography from IfSAR data in Alaska

The United States National Hydrography Dataset (NHD) is a database of vector features representing the surface water features for the country. The NHD was originally compiled from hydrographic content on U.S. Geological Survey topographic maps but is being updated with higher quality feature representations through flow-routing techniques that derive hydrography from high-resolution elevation data. However, deriving hydrography through flow-routing methods is a complex process that needs to be tailored to different geographic conditions, which can lead to varying solutions. To address this problem, this paper evaluates automated deep learning and its transferability to extract hydrography from interferometric synthetic aperture radar (IfSAR) elevation data spanning a range of geographic conditions in Alaska.

Alaska↗
USGS2022

Weakly supervised spatial deep learning for Earth image segmentation based on imperfect polyline labels

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy.

ACM Transactions on Intelligent Systems and Techno↗