23 Apr 2020

PUBLICATION NOTICE: Use of Convolutional Neural Networks for Semantic Image Segmentation Across Different Computing Systems

ABSTRACT: The advent of powerful computing platforms coupled with deep learning architectures have resulted in novel approaches to tackle many traditional computer vision problems in order to automate the interpretation of large and complex geospatial data. Such tasks are particularly important as data are widely available and UAS are increasingly being used. This document presents a workflow that leverages the use of CNNs and GPUs to automate pixel-wise segmentation of UAS imagery for faster image processing. GPU-based computing and parallelization is explored on multi-core GPUs to reduce development time, mitigate the need for extensive model training, and facilitate exploitation of mission critical information. VGG-16 model training times are compared among different systems (single, virtual, multi-GPUs) to investigate each platform’s capabilities. CNN results show a precision accuracy of 88% when applied to ground truth data. Coupling the VGG-16 model with GPU-accelerated processing and parallelizing across multiple GPUs decreases model training time while preserving accuracy. This signifies that GPU memory and cores available within a system are critical components in terms of preprocessing and processing speed. This workflow can be leveraged for future segmentation efforts, serve as a baseline to benchmark future CNN, and efficiently support critical image processing tasks for the Military.

23 Apr 2020

PUBLICATION NOTICE: Optimized Low Size, Weight, Power and Cost (SWaP-C) Payload for Mapping Interiors and Subterranean on an Unmanned Ground Vehicle

ABSTRACT: Section 3 of the FY15 Force 2025 Maneuvers Annual Report indicates that in Dense Urban Areas (DUA), specifically in a subsurface, surface, or super-surface structure, the ability to identify threats will be diminished. Most commercially available LIght Detection And Ranging (LIDAR) systems are specifically designed for high-resolution aerial imaging and mapping applications. As a result, they tend to be large, heavy, power-hungry, data bandwidth intensive, and expensive. They also employ lasers that are not typically eye-safe, which limits their overall effectiveness in subterranean and the interiors of subsurface or super-surface structures. However, due to recent advances in the automotive industry, there are new generations of Size, Weight, Power, and Cost (SWaP-C) sensors that are eye-safe, making them suitable for use indoors and in subterranean environments. While these tradeoffs limit their effective use to hundreds of meters (compared to kilometers for their more expensive counterparts), they are ideal candidates for use in subterranean and building interiors. While cameras fill this niche to some extent, the volumetric calculations provided by these sensors provide additional intelligence to shape the security of the environment and offer more precision when maneuvering troops. These sensors would provide the warfighter with situational understanding in previously inaccessible locations. Therefore, to aid in the Army’s need to obtain and maintain situational understanding in DUAs, the authors propose utilizing low size, weight, power, and cost (SWaP-C) sensors, on a robot platform, for surveying and mapping underground structures and building interiors. Rapid/near real-time data processing is possible by utilizing open-source software and commercial off the shelf (COTS) components. Using the preferred sensor payload autonomously was also explored.

22 Apr 2020

PUBLICATION NOTICE: The Forefront : A Review of ERDC Publications, Spring 2020

Abstract: The Engineer Research and Development Center (ERDC) is the premier civil works engineering and environmental sciences research and development arm of the U.S. Army Corps of Engineers (USACE). As such, it partners with the Army, Department of Defense (DoD), federal agencies, and civilian organizations to help solve our Nation’s most challenging problems in civil and military engineering, geospatial sciences, water resources, and environmental sciences. A special government knowledge center, ERDC Information Technology Laboratory’s Information Science and Knowledge Management (ISKM) Branch is critical to ERDC’s mission, fulfilling research requirements by offering a variety of editing and library services to advance the creation, dissemination, and curation of ERDC and USACE research knowledge. Serving as the publishing authority for the ERDC, ISKM publishes all ERDC technical publications to the Digital Repository Knowledge Core, sends a copy to the Defense Technical Information Center (DTIC) and creates a press release about each publication on the ERDC website. The Forefront seeks to provide an additional mechanism for highlighting some of our technical publications to the ERDC, USACE, Army, and DoD communities. This publication also encourages those outside ERDC to contact us about using ERDC editing services. For more information regarding the reports highlighted in this publications or others that ERDC researchers’ have created, please contact the ISKM virtual reference desk at erdclibrary@ask-a-librarian.info or visit the ISKM’s online repository, Knowledge Core, at https://erdc-library.erdc.dren.mil/ .

22 Apr 2020

PUBLICATION NOTICE: SPDAT Rainfall and Streamflow Analysis at Mobile, Alabama

ABSTRACT: This Dredging Operations and Environmental Research (DOER) program technical note (TN) seeks to explain how the Storm and Precipitation Dredging Analysis Tool (SPDAT) can be used to determine dredging response to varying rainfall levels at a given site. This TN will focus on the historical dredging records in the Mobile Bay Ship Channel and rainfall levels in that area. The analysis presented in this TN will form the basis for how the tool methodology can be used to and compare rainfall and dredging records to determine response trends at other sites. The results from the tool analysis can inform dredging managers about how much dredging may be expected under similar rainfall or tropical storm conditions for future cycles.

22 Apr 2020

PUBLICATION NOTICE: Analysis of Nearshore Placement of Sediments at Ogden Dunes, Indiana

ABSTRACT: The harbor structures/shoreline armoring on the southern Lake Michigan shoreline interrupt sand migration. Ogden Dunes, Indiana, and the nearby Indiana Dunes National Lakeshore observed shoreline erosion due to engineered structures associated with Burns Waterway Harbor (east of Ogden Dunes) impeding natural east-to-west sediment migration. To remedy this, USACE placed over 450,000 cubic meters (m3) of dredged material post-2006 in the nearshore of Ogden Dunes. However, the effectiveness of nearshore placements for shoreline protection and littoral nourishment is not fully established. To improve nearshore placement effectiveness, USACE monitored the June/July 2016 placement and subsequent movement of 107,000 m3 of dredged material in the nearshore region at Ogden Dunes. This involved an extensive monitoring scheme (three bathymetry surveys, and two acoustic Doppler current profiler deployments), a Coastal Modeling System (CMS) numerical model of the changes following placement, and a prediction of sediment transport direction using the Sediment Mobility Tool (SMT). The SMT-predicted sediment migration direction was compared to observations. Observations indicated that between 10/11/2016 and 11/15/2016 the centroid of the sediment above the pre-placement survey moved 17 m onshore. These observations agreed with SMT predictions — onshore migration under storm and typical wave conditions. CMS accurately reproduced the hydrodynamic features.

22 Apr 2020

PUBLICATION NOTICE: Nested Physics-Based Watershed Modeling at Seven Mile Creek: Minnesota River Integrated Watershed Study

ABSTRACT: The Minnesota River Basin (MRB) Integrated Study Team (IST) was tasked with assessing the condition of the MRB and recommending management options to reduce suspended sediments and improve the water quality in the basin. The Gridded Surface Subsurface Hydrologic Analysis (GSSHA) was chosen by the IST as the fine scale model for the Seven Mile Creek Watershed to help quantify the physical effects from best management practices within the MRB. The predominately agricultural Seven Mile Creek Watershed produces high total suspended solids and nutrients loads, contributing roughly 10% of the total load to the Minnesota River. GSSHA models were developed for a small experimental field research site called Red Top Farms, a Hydrologic Unit Code (HUC)-12 model for the entire Seven Mile Creek Watershed, a sub-basin of the Seven Mile Creek Watershed. After calibration, the resulting models were able to simulate measured tile drain flows, stream flow, suspended sediments, and to a lesser extent, nutrients. A selected suite of alternative land-use scenarios was simulated with the models to determine the watershed response to land-use changes at the small and medium scale and to test whether the type, size, and spatial distribution of land uses will influence the effectiveness of land management options.

22 Apr 2020

PUBLICATION NOTICE: Operation and Deployment Risk Assessment Report for the City of Cedar Rapids, Iowa: Alternative and Sequencing Optimization for Removable Flood Barriers

ABSTRACT: The City of Cedar Rapids, Iowa, partnered with engineering firms and the US Army Engineer District, Rock Island (MVR), to develop a Flood Control System (FCS). In 2011, the US Army Engineer Research and Development Center, Coastal and Hydraulics Laboratory (ERDC-CHL), was tasked with completing a risk assessment of removable floodwalls on the eastern side of the Cedar River. In 2016, ERDC-CHL was asked to include the temporary flood closure barriers on both sides of the Cedar River. Phase 1 of the study consisted of seven alternatives to be considered for the final FCS design, with a goal of a 90% confidence of successful deployment. Phase 2, initiated by MVR, targeted a 95% confidence level. The method used for evaluation was RiskyProject® software. The software used a Monte Carlo method of analysis to determine a range of durations, manpower, and labor costs based on logical sequencing. The results showed that the “Master Plan Minus 400 ft” alternative to be the most efficient for Phase 1. The most efficient alternative for Phase 2 was Task 5.4, which achieved a 95% confidence level of completion within 48 hours. The Phase 1 and the Phase 2 descriptions are detailed within this report.

22 Apr 2020

PUBLICATION NOTICE: A Practical Two-Phase Approach to Improve the Reliability and Efficiency of Markov Chain Monte Carlo Directed Hydrologic Model Calibration

ABSTRACT: Markov chain Monte Carlo (MCMC) methods are widely used in hydrology and other fields for posterior inference in a Bayesian framework. A properly constructed MCMC sampler is guaranteed to converge to the correct limiting distribution, but convergence can be very slow. While most research is focused on improving the proposal distribution used to generate trial moves in the Markov chain, this work instead focuses on efficiently finding an initial population for population-based MCMC samplers that will expedite convergence. Four case studies, including two hydrological models, are used to demonstrate that using multi-level single linkage implicit filtering stochastic global optimization to initialize the population both reduces the overall computational cost and significantly increases the chance of finding the correct limiting distribution within the constraint of a fixed computational budget.

20 Apr 2020

PUBLICATION NOTICE: Application of Chirp Acoustic Sub-Bottom Data in Riverine Environments: Identification of Underlying Rocky Hazards at Cape Girardeau, Missouri, and Thebes, Illinois

ABSTRACT: Shallow acoustic reflection (chirp) data have been utilized to map the elevation of underlying stratigraphy in a wide range of aqueous environments. Of particular concern in riverine regions is the elevation of near-surface underlying rock that, if exposed during normal migration of sedimentary bedforms, can cause grounding and damage to vessels transiting the region during periods of low water. Given the ephemeral nature of the rock’s exposure, traditional surveying methods are insufficient to map rock when it is covered by a thin veneer of sediment, increasing the potential hazard. Accordingly, the US Army Corps of Engineers, St. Louis District, (MVS) explored the use of chirp sub-bottom surveys to identify buried rock within the Mississippi River in the vicinity of Cape Girardeau, MO, and Thebes, IL. Hazard maps showing the distribution of buried rock were generated, and the base of the mobile sediment layer was identified where possible. These data will allow MVS to accurately identify potentially hazardous regions during periods of low water. Although the study did not result in the complete mapping of all near-surface geologic hazards, regions that warrant further study are identified, and modifications to the original survey plan are provided to improve the accuracy of future data collection efforts.

20 Apr 2020

PUBLICATION NOTICE: Bed-Load Transport Measurements on the Chippewa River Using the ISSDOTv2 Method

PURPOSE: This Regional Sediment Management (RSM) Technical Note (TN) provides information on bed-load measurements obtained on the Chippewa River, Wisconsin, in the spring of 2018. The ISSDOTv2 method was developed by the U.S. Army Corps of Engineers (USACE), Engineering Research and Development Center (ERDC), Coastal and Hydraulics Laboratory (CHL), River and Estuarine Engineering Branch. The method uses time-sequenced bathymetric data to determine a bed-load transport rate. When transport rates are obtained with concurrent flow-rate data, it is possible to develop bed-load rating curves. Such rating curves are extremely valuable in forecasting or hindcasting bed-load sediment delivery for the location at which the data were obtained. This is very important for river managers in developing sediment budgets and in the planning of dredging operations.  In the present study, the USACE Mississippi Valley Division (MVD), St. Paul District (MVP), had contracted with the U.S. Geological Survey (USGS) for real-time monitoring of suspended-sediment concentrations (suspended sand load and bed-load sediment) on the lower Chippewa River, a major source and contributor of sand-sized sediment to the Upper Mississippi River (UMR). The bed-load values obtained using ISSDOTv2 are presented in this RSM TN.