Electromagnetic Warfare Research Team
Advancing Army electromagnetic warfare capabilities through applied research, spectrum data processing, governance, artificial intelligence, and hands-on RF experimentation.
Our vision is to be the nation's premier academic capability for data-driven EW experimentation, evaluation, and understanding. We do this by generating data, producing insight, and developing talent to understand and shape the future of the electromagnetic fight.
Research Areas
RF Observatory
Build a world-class RF collection, analysis, and synthesis capability.
- Distributed RF sensing across West Point and partner sites
- Real-world and synthetic IQ dataset generation
- RF signal processing, geolocation, and characterization
- Edge-to-cloud processing architectures
- AI-enabled and traditional RF analytics
EW Benchmarking
Establish rigorous evaluation of AI-enabled and data-driven EW systems.
- Measure complete system performance - go beyond model accuracy
- Compare AI and traditional algorithmic approaches
- Develop representative datasets and test scenarios
- Assess performance across realistic operational conditions
- Inform Army requirements and investment decisions
RF Village
Create a premier platform for EW education, experimentation, and human-centered innovation.
- Hands-on EW and RF training environments
- AI-assisted learning and instruction
- RF visualization and spectrum awareness tools
- Human-machine interaction research
- Low-cost, deployable training packages
Current Primary Projects
RF OBSERVATORY
RF Observatory
The RF Observatory is our primary effort to establish a distributed architecture for collecting, transporting, processing, analyzing, and visualizing RF data. The effort includes remote sensing infrastructure, data pipelines, processing environments, and experimentation capabilities that support future EW research, benchmarking, and operational concepts. Much of the team's technical work is built on top of this foundation.
RF OBSERVATORY
Training Area WAN
This effort establishes networking infrastructure linking RF sensors, data collection sites, and processing environments across training areas. The purpose is to enable distributed RF experimentation, remote sensor control, data transport, and future field experimentation efforts. It serves as enabling infrastructure for broader RF Observatory objectives.
RF OBSERVATORY / EW BENCHMARKING
Quicksilver Signal Compression
Quicksilver explores methods to reduce storage and bandwidth requirements associated with RF IQ data while preserving analytical value. The goal is to make distributed RF sensing, long-term storage, and sensor-to-cloud architectures more practical and scalable while supporting future benchmarking and experimentation activities.
Additional Research & Initiatives
EW BENCHMARKING
Signal Classification Optimization
This effort evaluates machine-learning and non-machine-learning approaches to RF signal classification. Current work examines model performance, computational requirements, training approaches, and operational tradeoffs to help identify effective approaches for future Army EW systems and RF processing architectures.
RF OBSERVATORY / EW BENCHMARKING
Gold RF Datasets
This effort seeks to define what constitutes a representative, high-quality RF dataset and establish methodologies for generating and maintaining those datasets. The work supports AI model development, system testing, evaluation, and future EW capability development.
RF OBSERVATORY / EW BENCHMARKING
AI-Enabled Edge RF Processing Architecture
This effort investigates lightweight AI architectures capable of operating on resource-constrained sensors and edge devices. The goal is to determine how classification and decision-support functions can be pushed forward into low-power sensing environments while balancing computational cost, storage requirements, and operational effectiveness.
RF VILLAGE
RF Village
RF Village provides a low-cost, deployable RF and EW experimentation and education environment. The effort supports hands-on experimentation, AI-assisted instruction, RF visualization, and spectrum-awareness activities while generating insights into workforce development, operator performance, and human-machine teaming.
Researchers
LTC Josh Groen
Division Chief
LTC Ash Holzmann
Jack Voltaic
CW4 James Turner
EW Researcher
MAJ Caleb Hill
EW Researcher
MAJ Dan Burrow
EW Researcher
CPT Brady Hannula
EW Researcher
Dr. Ravi Starzl
External Research Partner