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.