Sustainability
Stratus
Live operations dashboard for airport ground vehicle decarbonization — replays 1,422 real ATL flights and optimizes Delta's $65M electrification budget.
80%
charging cost reduction
01 — Problem
Hartsfield-Jackson runs nearly 1,000 Delta flights a day, each triggering a swarm of diesel baggage tugs, belt loaders, GPUs, and pushback tractors. Delta has committed to 100% GSE electrification by 2035 and spends $65M a year to get there, but no tool existed to decide which vehicles to electrify first, when to charge them, or what the financial case looks like.
02 — Approach
- 01
Python/FastAPI backend runs an in-memory simulation — every 100ms it advances a clock, dispatches ground vehicles to arriving flights based on aircraft-specific recipes, and moves them along a precomputed Dijkstra-routed taxiway graph built from OpenStreetMap data.
- 02
Next.js frontend with Mapbox GL JS renders the live map; Zustand manages state; Recharts powers the roadmap dashboard. Aircraft motion is computed entirely client-side from the flight schedule.
- 03
Ranks every diesel vehicle class by cost per tonne of CO₂ avoided. Schedules EV charging against real Georgia Power TOU-GSD rates on Mercedes-Benz Fleet Depot Charging infrastructure.
- 04
Models depot-side capital projects (solar, battery storage, civil works) with full NPV analysis at Delta's 7% cost of capital, including IRA tax credit stacking and Delta's $50/tonne internal carbon price.
- 05
Every number is defensible — emission factors from ACRP Report 78, electricity rates from the Georgia Power tariff PDF, flight data from 1,422 real OpenSky Network turns.
03 — Results
80%
charging cost reduction vs. naive scheduling
1,422
real flights simulated
402
depot-to-gate Dijkstra routes precomputed
Stack
Next
RePlot→
Interactive tool that identifies underutilized urban land for infill development, scoring parcels on a 100-point algorithm across ROI, regulation, and environmental impact.