18 Oct 2024

Automated Change Detection in Ground-Penetrating Radar using Machine Learning in R

Abstract: Ground-penetrating radar (GPR) is a useful technique for subsurface change detection but is limited by the need for a subject matter expert to process and interpret coincident profiles. Use of a machine learning model can automate this process to reduce the need for subject matter expert processing and interpretation. Several machine learning models were investigated for the purpose of comparing coincident GPR profiles. Based on our literature review, a Siamese Twin model using a twinned convolutional network was identified as the optimum choice. Two neural networks were tested for the internal twinned model, ResNet50 and MobileNetV2, with the former historically having higher accuracy and the latter historically having faster processing time. When trained and tested on experimentally obtained GPR profiles with synthetically added changes, ResNet50 had a higher accuracy. Thanks to this higher accuracy, less computational processing was needed, leading to ResNet50 needing only 107 s to make a prediction compared to MobileNetV2 needing 223 s. Results imply that twinned models with higher historical accuracies should be investigated further. It is also recommended to test Siamese Twin models further with experimentally produced changes to verify the changed detection model’s accuracy is not merely specific to synthetically produced changes.

26 Sep 2024

A Geospatial Model for Identifying Stream Infrastructure Locations

Abstract: Management of hydraulic infrastructure for flood control, hydropower, navigation, and water supply is a critical component of the Army Dams and Transportation Infrastructure Program (ADTIP). This project provides a tool to locate stream infrastructure using a one-dimensional approach supplemented with geospatial filtering that only needs digital elevation model (DEM) files as primary input. The regions in and around Forts Liberty, Sill, and Cavazos were selected as study areas, and stream networks with corresponding stream elevation profiles were created and searched for elevation changes that met vertical threshold and search window criteria. Recall, Fβ, and a ratio of under to overprediction were used to evaluate performance. The search algorithm generally overpredicts the number of stream infrastructure locations and especially so for large search windows (20 or 25 cells) and small vertical threshold values (5 or 10 m). Overall, it was found that midrange vertical threshold values (2 or 2.5 m with long search windows (20 or 25 cells) with the land cover classification (LCC) check applied yielded results that minimized false negatives and overpredictions. The significance of this tool is that it may reduce costly field investigations, or at least aid in the prioritization of site visits for hydraulic infrastructure managers.

25 Sep 2024

Comparing the Thermal Infrared Signatures of Shallow Buried Objects and Disturbed Soil

Abstract: The alteration of physical and thermal properties of native soil during object burial produces a signature that can be detected using thermal infrared (IR) imagery. This study explores the thermal signature of disturbed soil compared to buried objects of different compositions (e.g., metal and plastic) buried 5 cm below ground surface (bgs) to better understand the mechanisms by which soil disturbance can impact the performance of aided target detection and recognition (AiTD/R). IR imagery recorded every five minutes were coupled with meteorological data recorded on 15-minute intervals from 1 July to 31 October 2022 to compare the diurnal and long-term fluctuations in raw radiance within a 25 × 25 pixel area of interest (AOI) above each target. This study examined the diurnal pattern of the thermal signature under several varying environmental conditions. Results showed that surface effects from soil disturbance increased the raw radiance of the AOI, strengthening the contrast between the object and background soil for several weeks after object burial. Enhancement of the thermal signature may lead to expanded windows of object visibility. Target age was identified as an important element in the development of training data sets for machine learning (ML) classification algorithms.

25 Sep 2024

Thermography Conversion for Optimal Noise Reduction

Abstract: Computer vision applications in terms of raw thermal radiance are limited by byte size. Normalizing the raw imagery reduces functional complexities that could otherwise aide a computer processing algorithm. This work explores a method to normalize 16-bit signed integer (I16) into unsigned 8-bit (U8) while maintaining the integrity of the correlation coefficients between the raw data sets and the environmental parameters that affects thermal anomaly detectability.

24 Sep 2024

Validation of Sample Extraction and Analysis Techniques for Simultaneous Determination of Legacy and Insensitive Munitions (IM) Constituents

Abstract: Currently, no standardized method exists for the analysis of insensitive munitions (IM) in environmental matrices such as water, soils, and tis-sues. However, standardized methods, such as United States Environmental Protection Agency (EPA) 8330B, exist for legacy munitions for water and soil matrices. The lack of standardized methods for IM analysis leads researchers to use a wide variety of incomplete and overlapping analytical methodologies. The overall project’s first phase, Strategic Environmental Research and Development Program (SERDP) Environmental Restoration (ER)–2722, was to develop and optimize methods to address these methodological gaps by creating analytical methods for simultaneous analysis of IM and legacy munitions in water, soil, and tissue matrices. The main objective of the current project phase, Environmental Security Technology Certification Program (ESTCP) ER19-5078, is to build upon the previous work in phase one and to focus on the validation of the newly developed methods. Synergizing with the main objective of the overall project, the methods were validated and submitted to the EPA for inclusion as a possible addendum to EPA 8330B.

19 Sep 2024

The Arctic Deployable Resilient Installation Water Purification and Treatment System (DRIPS): Microgrid Integration with Geoenabled Water Production and Disinfection Systems for Installations

Abstract: The purpose of the Arctic Deployable Resilient Installation water Purification and treatment System (DRIPS) is to be a critical asset in disaster response and military operations by providing a reliable and effective means of producing potable water and disinfection in a challenging and unpredictable environment, such as in an extremely cold climate. The objective of this effort was to deliver, integrate, and demonstrate the Arctic DRIPS to show that it can provide drinkable water to users of the microgrid within polar climate zones. Its adaptability, mobility, and comprehensive water treatment capabilities make it an invaluable resource for addressing water-related emergencies and water disruptions and for sustaining critical missions. It also addresses a point of need by improving the ability to meet demands while reducing convoy requirements and the logistical foot-print and ensuring the well-being of affected installations during disaster responses, training operations, normal water disruptions, and emergency preparation. The DRIPS was delivered to Fort Wainwright, a sub-Arctic installation, to demonstrate the integration of a water treatment component within a microgrid structure and to help them be better prepared to meet their water and energy requirement goals. The microgrid integration requirements were met upon implementation of this project.

12 Sep 2024

Establishing a Selection of Dust Event Case Studies for Regions in the Global South

Abstract: Airborne dust is an essential component of climatological and biogeochemical processes. Blowing dust can adversely affect agriculture, transportation, air quality, sensor performance, and human health. Therefore, the accurate characterization and forecasting of dust events is a priority for air quality researchers and operational weather centers. While dust detection and prediction capabilities have evolved over the preceding decades, the weather modeling community must continue to improve the location and timing of individual dust event fore-casts, especially for extreme dust outbreaks. Accordingly, Researchers at the US Army Engineer Research and Development Center (ERDC) are establishing a series of reference case study events to enhance dust transport model development and evaluation. These case studies support ongoing research to increase the accuracy of simulated dust emissions, dust aerosol transport, and dust-induced hazardous air quality conditions. This report documents five new contributions to the reference inventory, including detailed assessments of dust storms from three regions with differing meteorological forcing regimes. Here, we examine two extreme dust episodes that affected India, a multiday berg wind event in southern Africa, a strong but short-lived dust plume from the Atacama Desert of Chile, and a narrow, isolated dust plume emanating from a dry lake bed in Patagonia.

6 Sep 2024

Snow Surface Roughness across Spatio-Temporal Scales

Abstract: The snow surface is at the interface between the atmosphere and Earth. The surface of the snowpack changes due to its interaction with precipitation, wind, humidity, short- and long-wave radiation, underlying terrain characteristics, and land cover. These connections create a dynamic snow surface that impacts the energy and mass balance of the snowpack, blowing snow potential, and other snowpack processes. Despite this, the snow surface is generally considered a constant parameter in many Earth system models. Data from the National Aeronautics and Space Administration (NASA) Cold Land Processes Experiment (CLPX) collected in 2002 and 2003 across northern Colorado were used to investigate the spatial and temporal variability of snow surface roughness. The random roughness (RR) and fractal dimension (D) metrics used in this investigation are well correlated. However, roughness is not correlated across scales, computed here from snow roughness boards at a millimeter resolution and airborne lidar at a meter resolution. Process scale differences were found based on land cover at each of the two measurement scales, as appraised through measurements in the forest and alpine.

30 Aug 2024

Particle Size Characteristics of Energetic Materials Distributed from Low-Order Functioning Mortar Munitions

Abstract: Particles of explosive filler distributed from low-order (LO) munition functioning are susceptible to dissolution and potential mobilization into groundwater and surface water. We command-initiated three mortar munitions as LO in triplicate using a fuze simulator and recovered particles from an ice surface to constrain LO particle characteristics. Total explosive mass recovery (19–55%) and spatial distribution (0->20 m) varied significantly both between munitions and between replicate LOs of the same munition. The median particle size (0.27–3.99 mm) varied with total mass recovery. In general, LO particles coarsened, and total mass deposition rates decreased logarithmically, with increasing distance from the initiation point.

28 Aug 2024

Validation of Daily Snow Water Equivalent for a Watershed Statistics Tool

Abstract: The Watershed Statistics tool is a tool currently being developed for the Remote Sensing and Geographic Information Systems Center of Expertise’s (RSGIS) Extreme Cold Weather web portal and will allow users to easily access and visualize snow water equivalent (SWE) data. The SWE data available on this tool are derived from passive microwave signals acquired by satellite through a technique known as enhanced passive microwave SWE. This analysis used available in situ SWE measurements from snow study sites in four watersheds across the United States and Canada to determine the accuracy of the data available on the tool at the watershed scale. In situ measurements of SWE were compared with the Watershed Statistics tool’s SWE data based on watershed, land cover, and elevation to determine causes if discrepancies between the satellite-based estimations on the tool and ground-based measurements. The extent to which the data available on the Watershed Statistics tool agreed with in situ measurements was highly variable. SWE data available on the Watershed Statistics tool agreed the least with ground-based measurements made at higher elevations and in areas with denser vegetation. The findings of this comparison are consistent with known limitations of the enhanced passive microwave SWE technique.