6 Feb 2023

Three-Dimensional Geospatial Product Generation from Tactical Sources, Co-Registration Assessment, and Considerations

Abstract: According to Army Multi-Domain Operations (MDO) doctrine, generating timely, accurate, and exploitable geospatial products from tactical platforms is a critical capability to meet threats. The US Army Corps of Engineers, Engineer Research and Development Center, Geospatial Research Laboratory (ERDC-GRL) is carrying out 6.2 research to facilitate the creation of three-dimensional (3D) products from tactical sensors to include full-motion video, framing cameras, and sensors integrated on small Unmanned Aerial Systems (sUAS). This report describes an ERDC-GRL processing pipeline comprising custom code, open-source software, and commercial off-the-shelf (COTS) tools to geospatially rectify tactical imagery to authoritative foundation sources. Four datasets from different sensors and locations were processed against National Geospatial-Intelligence Agency–supplied foundation data. Results showed that the co-registration of tactical drone data to reference foundation varied from 0.34 m to 0.75 m, exceeding the accuracy objective of 1 m described in briefings presented to Army Futures Command (AFC) and the Assistant Security of the Army for Acquisition, Logistics and Technology (ASA(ALT)). A discussion summarizes the results, describes steps to address processing gaps, and considers future efforts to optimize the pipeline for generation of geospatial data for specific end-user devices and tactical applications.

6 Feb 2023

Establishing a Series of Dust Event Case Studies for North Africa

Abstract: Dust aerosols often create hazardous air quality conditions that affect human health, visibility, agriculture, and communication in various parts of the world. While substantial progress has been made in dust-event simulation and hazard mitigation over the last several decades, accurately forecasting the spatial and temporal variability of dust emissions continues to be a challenge. This report documents an analysis of atmospheric conditions for a series of dust events in North Africa. The researchers highlight four analyzed events that occurred between January 2016 to present in the following locations: (1) the western Sahara Desert; (2) East Algeria and the Iberian Peninsula; (3) Chad-Bodélé Depression; (4) Algeria and Morocco. For each event, the researchers developed an overview of the general synoptic, mesoscale, and local environmental forcing conditions that controlled the event evolution and used a combination of available lidar data, surface weather observations, upper-air soundings, aerosol optical depth, and satellite imagery to characterize the dust conditions. These assessments will support downstream forecast model evaluation and sensitivity testing; however, the researchers also encourage broader use of these assessments as reference case studies for dust transport, air quality modeling, remote sensing, soil erosion, and land management research applications.

28 Nov 2022

The DEM Breakline and Differencing Analysis Tool—Step-by-Step Workflows and Procedures for Effective Gridded DEM Analysis

Abstract: The DEM Breakline and Differencing Analysis Tool is the result of a multi-year research effort in the analysis of digital elevation models (DEMs) and the extraction of features associated with breaklines identified on the DEM by numerical analysis. Developed in the ENVI/IDL image processing application, the tool is designed to serve as an aid to research in the investigation of DEMs by taking advantage of local variation in the height. A set of specific workflow exercises is described as applied to a diverse set of four sample DEMs. These workflows instruct the user in applying the tool to extract and analyze features associated with terrain, vegetative canopy, and built structures. Optimal processing parameter choices, subject to user modification, are provided along with sufficient explanation to train the user in elevation model analysis through the creation of customized output overlays.

28 Nov 2022

Cross Country Mobility (CCM) Modeling Using Triangulated Irregular Networks (TIN)

Abstract: Cross country mobility (CCM) models terrain that has insufficient or unavailable infrastructure for crossing. This historically has been done with either hand-drawn and estimated maps or with raster-based terrain analysis, both of which have their own strengths and weaknesses. In this report the authors explore the possibility of using triangulated irregular networks (TINs) as a means of representing terrain characteristics used in CCM and discuss the possibilities of using such networks for routing capabilities in lieu of a traditional road-based network. The factors used to calculate CCM are modified from previous methods to capture a more accurate measurement of terrain characteristics. Using a TIN to store and represent CCM information achieves comparable results to raster cost analysis with the additional benefits of an integrated network useful for visualization and routing and a reduction in the number of related files. Additionally, TINs can in some cases more accurately show the contours of the landscape and reveal feature details or impediments that may be lost within a raster, thus improving the quality of CCM overlays.

1 Nov 2022

Snow-Covered Region Improvements to a Support Vector Machine-Based Semi-Automated Land Cover Mapping Decision Support Tool

Abstract: This work builds on the original semi-automated land cover mapping algorithm and quantifies improvements to class accuracy, analyzes the results, and conducts a more in-depth accuracy assessment in conjunction with test sites and the National Land Cover Database (NLCD). This algorithm uses support vector machines trained on data collected across the continental United States to generate a pre-trained model for inclusion into a decision support tool within ArcGIS Pro. Version 2 includes an additional snow cover class and accounts for snow cover effects within the other land cover classes. Overall accuracy across the continental United States for Version 2 is 75% on snow-covered pixels and 69% on snow-free pixels, versus 16% and 66% for Version 1. However, combining the “crop” and “low vegetation” classes improves these values to 86% for snow and 83% for snow-free, compared to 19% and 83% for Version 1. This merging is justified by their spectral similarity, the difference between crop and low vegetation falling closer to land use than land cover. The Version 2 tool is built into a Python-based ArcGIS toolbox, allowing users to leverage the pre-trained model—along with image splitting and parallel processing techniques—for their land cover type map generation needs.

3 Oct 2022

Landform Identification in the Chihuahuan Desert for Dust Source Characterization Applications: Developing a Landform Reference Data Set

Abstract: ERDC-Geo is a surface erodibility parameterization developed to improve dust predictions in weather forecasting models. Geomorphic landform maps used in ERDC-Geo link surface dust emission potential to landform type. Using a previously generated southwest United States landform map as training data, a classification model based on machine learning (ML) was established to generate ERDC-Geo input data. To evaluate the ability of the ML model to accurately classify landforms, an independent reference landform data set was created for areas in the Chihuahuan Desert. The reference landform data set was generated using two separate map-ping methodologies: one based on in situ observations, and another based on the interpretation of satellite imagery. Existing geospatial data layers and recommendations from local rangeland experts guided site selections for both in situ and remote landform identification. A total of 18 landform types were mapped across 128 sites in New Mexico, Texas, and Mexico using the in situ (31 sites) and remote (97 sites) techniques. The final data set is critical for evaluating the ML-classification model and, ultimately, for improving dust forecasting models.

19 Sep 2022

Adapting Agile Philosophies and Tools for a Research Environment

Abstract: There exist myriad project management methodologies, but none is focused solely on scientific research. Research projects are unique compared to other types of projects, including software development, manufacturing, and drug trials; research projects inherently have unplanned risks. These risks provide a challenge to managing resources, developing schedules, and providing team ownership while still achieving project goals. To help mitigate the risks and the challenges associated with scientific research, a methodology to manage research projects needs to be developed.

16 Sep 2022

Analysis of Spectropolarimetric Responses in the Visible and Infrared for Differentiation between Similar Materials

Abstract: Spectropolarimetric research has focused on target detections of materials that have a high degree of contrast from background materials, such as identification of a manmade object embedded in a vegetative background. This study presents an approach using spectropolarimetric imagery in visible, shortwave infrared, and longwave infrared bands to differentiate between similar natural and manmade materials. The method employs Michelson contrast and Kruskal-Wallis one-way analysis of variance (ANOVA) H-test to determine if a distinction can be found in pairwise comparisons of similar and different materials using the Stokes parameters in the visible, shortwave infrared, and longwave infrared bands. Results showed that similar natural and manmade materials were differentiable in spectropolarimetric imagery using the Michelson contrast and ANOVA. This approach provides a way to use spectropolarimetric imagery to distinguish between materials that are similar to each other.

12 Aug 2022

User Guide: The DEM Breakline and Differencing Analysis Tool—Gridded Elevation Model Analysis with a Convenient Graphical User Interface

Abstract: Gridded elevation models of the earth’s surface derived from airborne lidar data or other sources can provide qualitative and quantitative information about the terrain and its surface features through analysis of the local spatial variation in elevation. The DEM Breakline and Differencing Analysis Tool was developed to extract and display micro-terrain features and vegetative cover based on the numerical modeling of elevation discontinuities or breaklines (breaks-in-slope), slope, terrain ruggedness, local surface optima, and the local elevation difference between first surface and bare earth input models. Using numerical algorithms developed in-house at the U.S. Army Engineer Research and Development Center, Geospatial Research Laboratory, various parameters are calculated for each cell in the model matrix in an initial processing phase. The results are combined and thresholded by the user in different ways for display and analysis. A graphical user interface provides control of input models, processing, and display as color-mapped overlays. Output displays can be saved as images, and the overlay data can be saved as raster layers for input into geographic information systems for further analysis.

29 Jun 2022

Adversarial Artificial Intelligence: Implications for Military Operations

Introduction: Artificial intelligence and machine learning algorithms are at the forefront of current research to help military analysts deal with triaging ever larger amounts of data from deployed sensors. These automated approaches will become increasingly embedded into the military decision making process, which makes it crucial to understand how these algorithms generate outputs and how sensitive they are to perturbations during training or classification. In other words, humans must have a ‘theory of mind’ for these sets of approaches in order to begin to trust them enough to make life or death decisions. Research in this area is known as adversarial examples for artificial intelligence / machine learning. Previous works in this domain focused on degrading classification performance with respect to added noise to new data. Some of these works achieved notable results on image data by subtly increasing noise, such that the image appeared unaltered to the human eye, but significantly impacted performance (Athalye et al. 2017). Povolny and Trivedi (2020) achieved similar results, but made a small visually obvious change to induce a degradation in performance. One notable work examined the effects of an increase in physical scale of the sensed environment (such as the large areas recorded for remote sensing platforms) on adversarial perturbations (Czaja et al. 2018). This technical note (TN) describes an initial foray into understanding how physical changes to the appearance of military vehicles resulted in performance degradation for a convolutional neural network (CNN). The military vehicles chosen were the M2 Bradley Infantry Fighting Vehicle and the M1064 Mortar Carrier. As stand-ins for the actual vehicle, plastic scale models were used, each a 1/35 scale replica. The results of this research have yielded a curated training and test data set of images related to the M2 and M1064, trained models based on a combined ResNet / Inception implementation from the Keras project, and adversarial examples mocked up using the scale models with images taken by a smartphone.