An official website of the United States government
Abstract Delineating accurate flowlines using digital elevation models is a critical step for overland flow modeling. However, extracting surface flowlines from high‐resolution digital elevation models (HRDEMs) can be biased, partly due to the absence of information on the locations of anthropogenic drainage structures (ADS) such as bridges and culverts. Without the ADS, the roads may act as “digital dams” that prevent accurate delineation of flowlines. However, it is unclear what variables for terrain‐based hydrologic modeling can be used to mitigate the effect of “digital dams.” This study assessed the impacts of ADS locations, spatial resolution, depression processing methods, and flow direction algorithms on hydrologic connectivity in an agrarian landscape of Nebraska. The assessment was conducted based on the offset distances between modeled drainage crossings and actual ADS on the road. Results suggested that: (a) stream burning in combination with the D8 or D‐Infinity flow direction algorithm is the best option for modeling surface flowlines from HRDEMs in an agrarian landscape; (b) increasing the HRDEM resolution was found significant for facilitating accurate drainage crossing near ADS locations; and (c) D8 and D‐Infinity flow direction algorithms resulted in similar patterns of drainage crossing at ADS locations. This research is expected to result in improved parameter settings for HRDEMs‐based hydrologic modeling.
more »
« less
Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations
The accurate and efficient determination of hydrologic connectivity has garnered significant attention from both academic and industrial sectors due to its critical implications for environmental management. While recent studies have leveraged the spatial characteristics of hydrologic features, the use of elevation models for identifying drainage paths can be influenced by flow barriers. To address these challenges, our focus in this study is on detecting drainage crossings through the application of advanced convolutional neural networks (CNNs). In pursuit of this goal, we use neural architecture search to automatically explore CNN models for identifying drainage crossings. Our approach not only attains high accuracy (over 97% for average precision) in object detection but also excels in efficiently inferring correct drainage crossings within a remarkably short time frame (0.268 ms). Furthermore, we perform a detailed profiling of our approach on GPU systems to analyze performance bottlenecks.
more »
« less
- PAR ID:
- 10473763
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400707858
- Page Range / eLocation ID:
- 1780 to 1788
- Subject(s) / Keyword(s):
- CNN inference throughput GPU profiling SPP-Net
- Format(s):
- Medium: X
- Location:
- Denver CO USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Drainage canals associated with logging and agriculture dry out organic soils in tropical peatlands, thereby threatening the viability of long‐term carbon stores due to increased emissions from decomposition, fire, and fluvial transport. In Southeast Asian peatlands, which have experienced decades of land use change, the exact extent and spatial distribution of drainage canals are unknown. This has prevented regional‐scale investigation of the relationships between drainage, land use, and carbon emissions. Here, we create the first regional map of drainage canals using high resolution satellite imagery and a convolutional neural network. We find that drainage is widespread—occurring in at least 65% of peatlands and across all land use types. Although previous estimates of peatland carbon emissions have relied on land use as a proxy for drainage, our maps show substantial variation in drainage density within land use types. Subsidence rates are 3.2 times larger in intensively drained areas than in non‐drained areas, highlighting the central role of drainage in mediating peat subsidence. Accounting for drainage canals was found to improve a subsidence prediction model by 30%, suggesting that canals contain information about subsidence not captured by land use alone. Thus, our data set can be used to improve subsidence and associated carbon emissions predictions in peatlands, and to target areas for hydrologic restoration.more » « less
-
null (Ed.)Abstract. Topography is a fundamental input to hydrologic models criticalfor generating realistic streamflow networks as well as infiltration andgroundwater flow. Although there exist several national topographic datasetsfor the United States, they may not be compatible with gridded models thatrequire hydrologically consistent digital elevation models (DEMs). Here, wepresent a national topographic dataset developed to support griddedhydrologic simulations at 1 km and 250 m spatial resolution over the contiguousUnited States. The workflow is described step by step in two parts: (a) DEMprocessing using a Priority Flood algorithm to ensure hydrologicallyconsistent drainage networks and (b) slope calculation and smoothing toimprove drainage performance. The accuracy of the derived stream network isevaluated by comparing the derived drainage area to drainage areas reportedby the national stream gage network. The slope smoothing steps are evaluatedusing the runoff simulations with an integrated hydrologic model. Our DEMproduct started from the National Water Model DEM to ensure our finaldatasets will be as consistent as possible with this existing nationalframework. Our analysis shows that the additional processing we provideimproves the consistency of simulated drainage areas and the runoffsimulations that simulate gridded overland flow (as opposed to a networkrouting scheme). The workflow uses an open-source R package, and all outputdatasets and processing scripts are available and fully documented. All ofthe output datasets and scripts for processing are published through CyVerseat 250 m and 1 km resolution. The DOI link for the dataset is https://doi.org/10.25739/e1ps-qy48 (Zhang and Condon, 2020).more » « less
-
Abstract. This paper studies how to improve the accuracy of hydrologic models using machine-learning models as post-processors and presents possibilities to reduce the workload to create an accurate hydrologic model by removing the calibration step. It is often challenging to develop an accurate hydrologic model due to the time-consuming model calibration procedure and the nonstationarity of hydrologic data. Our findings show that the errors of hydrologic models are correlated with model inputs. Thus motivated, we propose a modeling-error-learning-based post-processor framework by leveraging this correlation to improve the accuracy of a hydrologic model. The key idea is to predict the differences (errors) between the observed values and the hydrologic model predictions by using machine-learning techniques. To tackle the nonstationarity issue of hydrologic data, a moving-window-based machine-learning approach is proposed to enhance the machine-learning error predictions by identifying the local stationarity of the data using a stationarity measure developed based on the Hilbert–Huang transform. Two hydrologic models, the Precipitation–Runoff Modeling System (PRMS) and the Hydrologic Modeling System (HEC-HMS), are used to evaluate the proposed framework. Two case studies are provided to exhibit the improved performance over the original model using multiple statistical metrics.more » « less
-
Abstract. Calculating flow routing across a landscape is a routine process in geomorphology, hydrology, planetary science, and soil and water conservation. Flow-routing calculations often require a preprocessing step to remove depressions from a DEM to create a “flow-routing surface” that can host a continuous, integrated drainage network. However, real landscapes contain natural depressions that trap water. These are an important part of the hydrologic system and should be represented in flow-routing surfaces. Historically, depressions (or “pits”) in DEMs have been viewed as data errors, but the rapid expansion of high-resolution, high-precision DEM coverage increases the likelihood that depressions are real-world features. To address this long-standing problem of emerging significance, we developed FlowFill, an algorithm that routes a prescribed amount of runoff across the surface in order to flood depressions if enough water is available. This mass-conserving approach typically floods smaller depressions and those in wet areas, integrating drainage across them, while permitting internal drainage and disruptions to hydrologic connectivity. We present results from two sample study areas to which we apply a range of uniform initial runoff depths and report the resulting filled and unfilled depressions, the drainage network structure, and the required compute time. For the reach- to watershed-scale examples that we ran, FlowFill compute times ranged from approximately 1 to 30 min, with compute times per cell of 0.0001 to 0.006 s.more » « less
