Context
FEMA's Coordinated Needs Management Strategy is a national geospatial program used to identify, validate, track, and prioritize flood hazard mapping needs. Because the program depends on large volumes of spatial information, documentation, and update signals, it presents a strong opportunity for targeted AI support.
Challenge
The challenge was not simply identifying AI methods that looked promising. The work required understanding where AI could improve CNMS workflows without disrupting the logic, quality controls, and decision structures that support national flood mapping priorities.
My Role
I led AI strategy support as part of AECOM's AI and machine learning working group. I helped define potential AI pilot projects, evaluate their technical fit, and frame how LLMs, computer vision, and remote sensing could support CNMS modernization.
Approach
I examined CNMS workflows through the lens of practical AI implementation. Potential pilots were organized around specific operational needs, including feature identification, update detection, data quality improvement, document interpretation, and mapping needs prioritization. Each concept was framed around measurable workflow value rather than generic AI capability.
Output
The work produced a set of recommended AI pilot directions for FEMA consideration. These concepts outlined how AI-enabled methods could support CNMS data quality, update detection, and flood hazard mapping needs assessment.
Impact
The project helped connect emerging AI capabilities to an established federal geospatial program. It provided a more disciplined way to evaluate where AI could add value to flood mapping modernization without treating AI as a broad, undefined automation layer.