11 Jun 2026

Geofencing for Standardized Navigation Lock Cycle Time Analysis

Abstract: The purpose of this US Army Engineer Research and Development Center (ERDC) technical note (TN) is to describe the motivation for, and development of, a set of geospatial boundaries (geofences) at standard intervals around navigation lock structures owned or operated by the US Army Corps of Engineers (USACE). These geofences will be used for automated time-stamp generation in conjunction with Automatic Identification System (AIS) broadcasts from vessels.

10 Jun 2026

Multisource Knowledge Graph Architecture for Air-Gapped AI Systems: Design Patterns and a Geospatial Reference Implementation

Purpose: This technical note presents a reference architecture for constructing multisource knowledge graphs in air-gapped, domain-specific AI systems. The architecture addresses recurring problems in military, intelligence, and secure-enterprise environments: integrating heterogeneous authoritative data sources while preserving source schema fidelity, enabling deterministic semantic resolution, and operating without external network dependencies. While this is a geospatial implementation, the architectural principles in the core design are transferable. The implementation is organized around four separable layers—schema registry, domain ontology, reasoning patterns, and relationship vocabulary—and adopts a canonical-with-aliasing integration strategy that supports cross-schema reasoning without forcing premature schema con-vergence. These patterns are validated through a geospatial intelligence implementation supporting US Army operations and demonstrate how abstract design principles translate into an operationally relevant system. This knowledge graph is designed to serve as the semantic substrate for router-based AI systems. A companion technical note (Drouillard and Lewis 2026) describes the geospatial AI (GeoAI) agent stack, which is a router-based orchestration architecture that coordinates multiple retrieval backends and reasoning tools. Within that architecture, the knowledge graph functions as a specialized retrieval backend that runs alongside document retrieval and vector search, serving queries that require structured entity-relationship reasoning, provenance tracking, or deterministic semantic resolution. The router directs spatial relationship queries (e.g., “which roads cross this river”), multihop dependency queries (e.g., “what infrastructure depends on this power station”), and schema-resolution queries (e.g., “find all transportation features in Multinational Geospatial Co-production Program [MGCP] format”) to the knowledge graph while routing conceptual or analytical questions to document retrieval. This technical note focuses exclusively on the knowledge graph architecture; the broader orchestration patterns and routing logic are detailed in the companion paper. While the examples presented are geospatial, the architectural principles, validation strategies, and design tradeoffs documented here have broader applicability where deterministic semantic integration is required under air-gapped constraints. The geospatial instantiation serves as a concrete demonstration of abstract patterns that may inform future knowledge graph efforts in other US Army Engineer Research and Development Center (ERDC) research domains.

18 May 2026

Workflow to Build Space-Time Cubes in ArcGIS Pro with High-Resolution Elevation Data

Abstract: This Coastal and Hydraulics Engineering Technical Note (CHETN) presents a workflow to build space-time cubes (STCs) using high-resolution digital elevation models (DEMs). The workflow leverages ArcGIS Pro’s mosaic dataset architecture and multidimensional tools to analyze temporal changes across elevation datasets. This workflow is intended to (1) guide users who may not be familiar with STCs through a step-by-step workflow, (2) share a set of best practices, and (3) highlight considerations when using remotely sensed elevation datasets. This CHETN is a part of a larger effort to develop the next generation of volume change tools for application in the coastal environment.

13 May 2026

Processing and Optimization of Global Land Ice Measurements from Space (GLIMS) Glacier Polygon Shapefiles for Army Geospatial Data Model Integration

Abstract: This technical note documents the methodology used to prepare glacier polygon datasets from the Global Land Ice Measurements from Space (GLIMS) database for integration into Army geospatial workflows. The Army Geospatial Data Model contains a feature class within the GGDM (Ground-Warfighter Geospatial Data Model) for permanent snow, defined operationally as snow persisting on the ground for more than two years. However, in cryospheric science, snow that persists across multiple accumulation seasons transitions into firn and ultimately becomes glacial ice. Thus, most “permanent snow” surfaces are more accurately classified as permanent ice, and GGDM does not currently contain a dedicated feature class representing this land-surface category. The GLIMS database provides authoritative, globally maintained glacier and perennial ice extents, making it ideally suited to fill this structural gap in the GGDM schema. The purpose of this work is to (1) transform raw GLIMS glacier polygons into a clean, nonoverlapping, attribute-free dataset; (2) standardize the geometry for compatibility with GGDM; and (3) establish a US Army Engineer Research and Development Center (ERDC)–compliant workflow for maintaining a credible representation of global permanent ice surfaces.

13 May 2026

Geospatial AI (GeoAI) Agent Stack: Router-Based Orchestration and Design Rationale

Abstract: This report summarizes the current state of a router-based, multiagent Geospatial AI (GeoAI) system designed to reliably execute geospatial workflows while retaining the flexibility of large language model (LLM) reasoning. The architecture is intentionally both language-model agnostic and orchestration-framework agnostic to support organizational controls and mandates, and it is designed to operate in air-gapped environments. It uses a domain router to scope tools before the model is invoked; a microrouter to decide whether the system should execute tools, retrieve knowledge, or produce a direct response; and a bounded cycle of execution and validation that supports multistep tool use. The design emphasizes determinism after the model makes decisions, strict boundaries around what the model can “see,” and modularity that keeps core business logic largely independent from orchestration and tool-protocol frameworks. The remainder of this report describes the architecture as implemented today, explains the design rationale, and outlines anticipated future work.

12 May 2026

A Scalable Algorithm for Dynamic Vector Model Representation Utilizing Time-Series Reduction

Abstract: This document follows a technical report published by the US Army Engineer Research and Development Center–Geospatial Research Laboratory (ERDC-GRL), Time-Series Reduction for Dynamic Vector Model Attribute Representation in a Geographic Information System (ERDC/GRL TR-24-2, Drouillard and Lewis 2024). In that publication, we described the theoretical basis for extracting and modeling raster-format spatiotemporal phenomena for inclusion as a vector model attribute and provided a preliminary Python code example that was unsuitable for large-scale application. This report details the algorithm we subsequently developed to enable global-scale application of the time-series reduction method in service of the Intelligent Environmental Battlefield Awareness (IEBA) project.

20 Apr 2026

Multimethod Change-Detection Analysis Using Prithvi-EO-2.0: A Comparative Study of Traditional and Segmentation-Based Approaches for Vector Database Validation

Abstract: This technical note presents an evaluation of the performance of four change-detection methodologies, with a focus on validating and maintaining authoritative vector-feature databases using Earth observation data. In this study, we implemented traditional pixel-to-pixel change detection, feature-data-compliant segmentation, pixel-to-feature segmentation, and feature-to-pixel change detection, leveraging the Prithvi-EO-2.0 Vision Transformer model (Szwarcman et al. 2025), to analyze imagery from California’s Central Valley. The analysis of Sentinel-2 imagery from California’s Central Valley (in 2021–2023) demonstrated that there was a trade-off between sensitivity and reliability in the change-detection approaches: feature-to-feature methods achieved the highest sensitivity (0.637 average), while the feature-to-pixel approach provided the most reliable validation (0.280 average), exceeding the performance of traditional pixel-to-pixel methods (0.256 average).

19 Mar 2026

Arctic and Subarctic Zonal Characterization and Operational Thresholding (AZCOT)

Abstract: The US military develops and updates environmental parameters specified for the sustainment of operations throughout the world. These requirements are generally based on environmental data providing a baseline of temperature, wind, and precipitation expectations for each location. Observational data for Arctic regions is limited because of the remote and sparsely occupied geographical conditions. To address the need for updating these requirements, a 30-year analysis of meteorological conditions was conducted using a European Centre for Medium-Range Weather Forecasts (ECMWF) global reanalysis dataset over the Arctic and Subarctic region, defined by latitude 60°–90° North for this project. Raw hourly datasets were acquired, and the minimum temperatures, maximum wind speeds, maximum snow depths, and averages were determined over the period 1991–2020 between the months of October and March for each parameter. These were then visualized with geospatial analysis, producing a variety of maps designed to assist with the classification of parameters in Arctic zones of operation across a range of temporal resolutions. Finally, a review of operational limits for military equipment was conducted to match northern zones of operation with suitable capabilities dependent on environmental conditions.

16 Dec 2025

Procedures for Obtaining US Air Force Global Air-Land Weather Exploitation Model (GALWEM) Data for Hydrological Modeling Applications: An Overview of the GALWEM Acquisition System (GAS) v1.0 and v2.0

Abstract: The Global Air Land Weather Exploitation Model (GALWEM) Acquisition System (GAS) is a software platform that serves to automate and simplify the procurement of numerical weather prediction model data from the 557th Weather Squadron. GAS allows for the download of meteorological and other environmental parameters from the GALWEM, an operational Numerical Weather Prediction capability operated by the 557th Weather Squadron for use by both Air Force and Army interests. GAS provides the ability to archive GALWEM data so that it may be used by the US Army Engineer Research and Development Center (ERDC) and other researchers. The report describes multiple methodologies for data access as well as suggestions for future work to improve computational efficiency and customer access.

10 Oct 2025

Development and Management of Arctic Zonal Characterization Products: Geospatial Database

Abstract: Environmental parameters for operational planning in extreme conditions require accurate knowledge of prevailing meteorological conditions. However, the Arctic region presents unique challenges due to limited observational data and unique geographical conditions. To address the need for such knowledge, this study presents an analysis of Arctic prevailing-conditions using European Center for Medium-Range Weather Forecasting (ECMWF) Reanalysis v5 (ERA5) Data from 1991 to 2020. A custom Python-based framework was developed to process and analyze hourly datasets, identifying zones of extreme events and their frequency across multiple temporal scales. The framework uses ArcPy to automate the generation of nearly 40,000 mapped classifications for land masses 60°N and above. This automated pipeline enables both static and dynamic map generation capabilities for operational planning now and in the future. The resulting dataset provides critical spatial and temporal resolution of Arctic prevailing-conditions, enabling more refined characterization of extreme prevailing-conditions across the circumpolar region.