4 Dec 2024

Conway Lake Ecosystem Restoration: Soil Investigations to Support Engineering With Nature and Beneficial Use of Dredged Sediment

Purpose: The purpose of this Technical Note is to describe Conway Lake ecosystem restoration adaptive management investigations to evaluate forest planting and soil response to three depths of fine sediment placed over a sand base.

2 Dec 2024

Establishing a Workflow for Near-Seamless Digital Elevation Model Creation in the Great Lakes for ADCIRC Modeling

Abstract: This report introduces a workflow to create near-seamless, regional digital elevation models (DEMs) for use in coupled Advanced Circulation and Simulating Waves Nearshore modeling. The workflow is based in Esri ArcGIS Pro, leveraging the Mosaic Dataset architecture to organize and mosaic survey data sets into near-seamless DEMs. This workflow includes data collection and preprocessing, creation of source and derived mosaic data sets, manual editing of the data set seamlines, the creation of spatial metadata products, and quality assurance and control measures. These steps were implemented for each Great Lake to provide a high-resolution, near-seamless DEM product for modelers. The workflow may also have utility for other regional-scale investigations.

2 Dec 2024

Comparison of Run-Up Models with Field Data

Abstract: Run-up predictions are inherently uncertain, owing to ambiguities in phase-averaged models and inherent complexities of surf and swash-zone hydrodynamics. As a result, different approaches, ranging from simple algebraic expressions to computationally intensive phase-resolving models, have been used in attempt to capture the most relevant run-up processes. Studies quantifiably comparing these methods in terms of physical accuracy and computational speed are needed as new observation technologies and models become available. The current study tests the capability of the new swash formulation of the Coastal Modeling System (CMS) to predict 1D run-up statistics (R2%) collected during an energetic 3 week period on sandy dune-backed beach in Duck, North Carolina. The accuracy and speed of the debut CMS swash formulation is compared with one algebraic model and three other numerical models. Of the four tested numerical models, the CSHORE model computed the results fastest, and the CMS model results had the greatest accuracy. All four numerical models, including XBeach in surfbeat and nonhydrostatic modes, yielded half the error of the algebraic model tested. These findings present an encouraging advancement for phase-averaged coastal models, a critical step towards rapid prediction for near-time deterministic or long-term stochastic guidance.

2 Dec 2024

Adaptive Hydraulics 2D Shallow Water (AdH-SW2D) User’s Manual (Version 4.7.1): Guidelines for Solving 2D Shallow Water Problems with the Adaptive Hydraulics Modeling System

Abstract: Guidelines are presented for using the US Army Corps of Engineers Adaptive Hydraulics modeling software to model 2D shallow water problems. Constituent (nonsediment) transport is also included in this document. Sediment transport instructions are contained in a supplemental user’s guide.

19 Nov 2024

Deep Learning Approach for Accurate Segmentation of Sand Boils in Levee Systems

Abstract: Sand boils can contribute to the liquefaction of a portion of the levee, leading to levee failure. Accurately detecting and segmenting sand boils is crucial for effectively monitoring and maintaining levee systems. This paper presents SandBoilNet, a fully convolutional neural network with skip connections designed for accurate pixel-level classification or semantic segmentation of sand boils from images in levee systems. In this study, we explore the use of transfer learning for fast training and detecting sand boils through semantic segmentation. By utilizing a pretrained CNN model with ResNet50V2 architecture, our algorithm effectively leverages learned features for precise detection. We hypothesize that controlled feature extraction using a deeper pretrained CNN model can selectively generate the most relevant feature maps adapting to the domain, thereby improving performance. Experimental results demonstrate that SandBoilNet outperforms state-of-the-art semantic segmentation methods in accurately detecting sand boils, achieving a Balanced Accuracy (BA) of 85.52%, Macro F1-score (MaF1) of 73.12%, and an Intersection over Union (IoU) of 57.43% specifically for sand boils. This proposed approach represents a novel and effective solution for accurately detecting and segmenting sand boils from levee images toward automating the monitoring and maintenance of levee infrastructure.

19 Nov 2024

Widened Attention-Enhanced Atrous Convolutional Network for Efficient Embedded Vision Applications under Resource Constraints

Abstract: Onboard image analysis enables real-time autonomous capabilities for unmanned platforms including aerial, ground, and aquatic drones. Performing classification on embedded systems, rather than transmitting data, allows rapid perception and decision-making critical for time-sensitive applications such as search and rescue, hazardous environment exploration, and military operations. To fully capitalize on these systems’ potential, specialized deep learning solutions are needed that balance accuracy and computational efficiency for time-sensitive inference. This article introduces the widened attention-enhanced atrous convolution-based efficient network (WACEfNet), a new convolutional neural network designed specifically for real-time visual classification challenges using resource-constrained embedded devices. WACEfNet builds on EfficientNet and integrates innovative width-wise feature processing, atrous convolutions, and attention modules to improve representational power without excessive over-head. Extensive benchmarking confirms state-of-the-art performance from WACEfNet for aerial imaging applications while remaining suitable for embedded deployment. The improvements in accuracy and speed demonstrate the potential of customized deep learning advancements to unlock new capabilities for unmanned aerial vehicles and related embedded systems with tight size, weight, and power constraints. This research offers an optimized framework, combining widened residual learning and attention mechanisms, to meet the unique demands of high-fidelity real-time analytics across a variety of embedded perception paradigms.

19 Nov 2024

Finite Element Modeling of Aquatic Electrical Barriers—Voltage and Current Distributions: Brandon Road Lock and Dam Interbasin Project—Electric Fish Deterrent Design Recommendations

Abstract: Invasive carp (black, grass, silver, and bighead) are native to Asia and were imported into the US during the 1970s and 1980s to help fish farmers manage water quality and vegetation. Unfortunately, these carp became established in the Mississippi River and have led to a decline in native fish species. To prevent their spread from the Mississippi River Basin to the Great Lakes Basin via the Chicago Area Waterway System (CAWS), the US Army Corps of Engineers (USACE) operates a series of four electric dispersal barriers near Romeoville, Illinois in the Chicago Sanitary and Ship Canal (CSSC). To supplement these barriers, USACE was authorized to construct a series of aquatic nuisance species deterrents, including an electric deterrent, approximately 11 river miles downstream at Brandon Road Lock and Dam (BR). Throughout the BR electric deterrent design process, the dispersal barriers at the CSSC have served as the prototype systems used in the development of the concepts. Additionally, USACE has worked with the US Army Cold Regions Research Engineering Laboratory (CRREL) to develop a finite element numerical model (COMSOL) that predicts voltage and electric current distributions for a given electrode and waterway geometry.

15 Nov 2024

U.S. Army Corps of Engineers Civil Works Research, Development & Technology Strategy

Abstract: The Civil Works Research, Development, and Technology (RD&T) Strategy addresses the nation's pressing engineering challenges, including aging infrastructure, climate resilience, and environmental concerns. It emphasizes leveraging innovation to ensure the sustainability of the nation's infrastructure and water resources. Guided by six Strategic Focus Areas—Infrastructure, Water Modeling, Sediment Management, Ecosystems, Crisis Preparedness, and AI, Robotics, and Data—the strategy fosters collaboration with government, academia, and industry. This approach aims to transition technological innovations from development to practical application, enhancing national security, economic stability, and community preparedness.

14 Nov 2024

Application of Deep Learning for Segmenting Seepages in Levee Systems

Abstract: Seepage is a typical hydraulic factor that can initiate the breaching process in a levee system. If not identified and treated on time, seepages can be a severe problem for levees, weakening the levee structure and eventually leading to collapse. Therefore, it is essential always to be vigilant with regular monitoring procedures to identify seepages throughout these levee systems and perform adequate repairs to limit potential threats from unforeseen levee failures. This paper introduces a fully convolutional neural network to identify and segment seepage from the image in levee systems. To the best of our knowledge, this is the first work in this domain. Applying deep learning techniques for semantic segmentation tasks in real-world scenarios has its own challenges, especially the difficulty for models to effectively learn from complex backgrounds while focusing on simpler objects of interest. This challenge is particularly evident in the task of detecting seepages in levee systems, where the fault is relatively simple compared to the complex and varied background. We addressed this problem by introducing negative images and a controlled transfer learning approach for semantic segmentation for accurate seepage segmentation in levee systems.

6 Nov 2024

Time-Series Forecasting Methods: A Review

Abstract: Time-series forecasting techniques are of fundamental importance for predicting future values by analyzing past trends. The techniques assume that future trends will be similar to historical trends. Forecasting involves using models fit on historical data to predict future values. Time-series models have wide-ranging applications, from weather forecasting to sales forecasting, and are among the most effective methods of forecasting, especially when making decisions that involve uncertainty about the future. To evaluate forecast accuracy and to compare among models fitted to a time series, three performance measures were used in this study: mean absolute error (MAE), mean square error (MSE), and root-mean-square error (RMSE).