Skip to main content
Track Record

What the discipline has produced.

Twenty-four years of right-fidelity modeling across energy, environment, and public health — the same discipline now aimed at neurodegeneration.

← The Mission

By Michael Key · ORCID

Who built this, and what has the work produced.

Background

Twenty-four years at the intersection of math, simulation, and high-stakes decisions — from MITRE’s intelligence analysis center to major aerospace contractors to running an independent practice. The credentials and the arc that leads to this mission.

Read the background →

The method on other problems

Thirteen studies on real, high-stakes problems — energy grids, groundwater, public health, a longevity cohort, higher education — most showing that right-fidelity modeling with honest uncertainty holds up, and on the highest-stakes ones, changes the decision. The evidence that the discipline now aimed at Alzheimer’s and ALS carries weight.

Browse studies ↓

The method, proven on real problems.

None of these thirteen studies is about neurodegeneration — and that’s the point. Each is evidence that the discipline — calibrated, honestly-bounded modeling — holds up on real, high-stakes problems, and often changes the decision. The studies closest to the mission come first; the rest is the same method, applied across other domains.

Closest to the mission

Human-cohort & health studies

The method on real human-health data — the nearest neighbors to the Alzheimer’s and ALS work. New studies aimed closer to cognition and aging will join this group as they’re finished.

Health Cohort · NHANES + HRS

What predicts how long we live?

64,000 real people across the NHANES and HRS cohorts, 13 investigations. ML does better than domain knowledge on some questions; domain knowledge does better on others. The right method depends on the question — the same judgment the neurodegeneration work turns on.

Longevity study →
Environmental Health · 700K Cohort

California freight & ozone

57 chained investigations on a 700K-person cohort. Key finding: cutting NOx raises ozone in 99.95% of scenarios — complicating the common assumption that cutting NOx always lowers ozone.

RFAQ study →
The method on other domains — eleven studies · energy, water, environment, emergency response, education
Energy · PJM Grid

Can the grid absorb the data-center surge?

Can PJM’s grid absorb 40 GW of new data center load? 200-draw Monte Carlo, 4 chained questions. Validated against FERC/NERC filings.

PJM study →
Environmental · PFAS

Military base groundwater

Screening model says pump-and-treat is cheaper. Full physics analysis reverses the decision. Physics equations and Monte Carlo, not neural networks.

PFAS study →
Emergency · Wildfire

Evacuation & insurance

Four real wildfires, NASA FIRMS satellite data, USGS elevation, NIFC perimeters. Right model shifts evacuation triggers 1–7 hours earlier across 16 communities.

Wildfire study →
Water Resources · Colorado

Can the river keep its promises?

Legal over-allocation vs. physical supply. 12 investigations. Global sensitivity shows the delivery obligation drives just 7.3% of breach risk — inflow drives 92.9%.

Colorado River study →
Conservation · Ocean

Offshore wind & right whales

Pile-driving noise propagation vs. NARW critical habitat. 8 investigations, 3 sites, real SSP profiles. Coordinated scheduling cuts total whale takes 3.3× and creates 9 quiet hours/day — at zero added cost.

Ocean acoustics →
Energy · Texas Grid

Texas grid resilience

Five questions about the grid that failed in Winter Storm Uri. Physics-based dispatch, investment tradeoffs, location sensitivity.

Texas energy →
Energy · Data Centers

Where should a data center go?

Where should a large data center go when transmission is the binding constraint? Spatial optimization over grid physics and siting cost.

DC Siting →
Transportation · EV

Where do the charging gaps fall?

Where do the coverage gaps fall, and how big should each station be? Network planning under grid constraints, with battery-storage tradeoffs.

EV Charging →
Insurance · Wildfire Risk

How much fidelity does the decision need?

3 fires, 4 fidelity levels, 200 Monte Carlo draws. Four viability gates, 2 interactive tools. How fidelity affects the insurance decision.

Wildfire insurance →
Higher Education · College Closure

College closure risk

4,000+ institutions modeled with real College Scorecard and IPEDS data. Six investigations, three model tiers, three interactive tools. ML vs. rules-based risk scoring on a question where the real outcome is known.

College closure →
Higher Education · Program ROI

Is your degree worth it?

65,935 college programs analyzed with real IRS earnings data. 34% have negative lifetime ROI. Data analysis, not modeling — but the same question-first discipline applied to a hard, consequential question.

College ROI →