Physics-based AI smoke forecasts that warn communities before public data says the air is dangerous.
Trace AQ
venture active confidence: Medium status: Draft updated 2026-07-14
Summary
Trace AQ applies physics-based artificial intelligence to air-quality and wildfire-smoke forecasting. Better local forecasts can guide health and operations decisions, but the page shows neither wide deployment nor independently verified scale, so its demonstrated impact remains bounded.
Impact
Wildfire smoke is a fast-growing public health crisis across the western United States. Trace AQ markets improved forecast performance, but the earlier comparative percentage is not present in the captured official source.
Accurate advance warning can reduce outdoor exposure on dangerous days, potentially lowering respiratory hospitalizations, asthma attacks, and long-term lung disease burden. At scale, earlier warnings shift behavior from reactive (staying inside after air is already bad) to proactive (planning training, school recess, and clinical outreach around forecasted events).
What They Are Building
Trace AQ couples fluid dynamics, combustion chemistry, atmospheric chemistry, and local micrometeorology in physics-based models augmented with machine learning — running at finer resolution and faster update cycles than coarse-grid standard models. Per its official website, the product stack includes:
- Flow AQ — mobile app with up to four-day forecasts, real-time conditions, personalized alerts, and health insights (official website).
- Trace AQ | Aero — forecasting platform with plume-rise modeling, continuous source detection, timelapse visualizations, and dual API access for integration.
- ADAPT widget — embeddable live air-quality forecast for third-party websites.
- Whitepapers — science-driven publications on athletic training impacts and the Air Quality Analytics (AQA) forecast engine.
The hard engineering problems are nonlinear coupling of wind fields, emission factors by fuel type, secondary aerosol formation, and local micrometeorology — especially for wildfire plume rise and transport at actionable resolution.
What They Need Now
Hiring is software-heavy — machine-learning, front-end, full-stack, and data/cloud-infrastructure engineers, plus internships. That aligns with shipping Flow AQ / Aero as products while the underlying physics models stay core IP. Seed-stage capital still implies pressure to prove customer acquisition alongside forecast accuracy — healthcare and public-sector sales operators remain relevant even when not listed.
Who Could Help
Useful helpers include public health departments and hospital systems adopting air-quality alert integrations, athletic organizations and school districts with outdoor-activity scheduling needs, atmospheric-science advisors, Utah Venture Hub and Energy Accelerator connectors, and enterprise API customers in healthcare, insurance, and outdoor recreation.
Utah Context
Trace AQ is a University of Utah spinout founded by researchers Heather Holmes (Chemical Engineering), Derek Mallia (Atmospheric Sciences), and Taylor (Kai) Wilmot, with Victor Gill as founding CEO handling commercialization. The company worked with the U's Technology Licensing Office and Venture Hub Energy Accelerator. Salt Lake Valley's chronic air-quality challenges — inversion, dust, ozone, and wildfire smoke — make Utah both a natural testbed and mission-aligned market.
Evidence
- Official Website: Trace AQ · https://www.traceaq.com/
- U of U TLO: Flow AQ launch feature · https://technologylicensing.utah.edu/news-events/startups/u-of-u-startup-launches-new-air-quality-forecasting-app
- TechBuzz: $1.25M seed round · https://www.techbuzznews.com/trace-aq-raises-1-25-million-seed/
See Also
- Epitel — another U of U spinout translating research into health-facing products
- Culmination Bio — Utah health data infrastructure with population-scale clinical signal
Open Questions
- Forecast accuracy advantage versus large incumbents (The Weather Company, Tomorrow.io, AirNow) over multiple fire seasons is not independently benchmarked on this page.
- Commercial API licensing may cap impact relative to adoption by public health systems and government agencies — a harder but higher-leverage channel.
- Current financing and runway are not established by captured primary evidence.
- Moat durability (unique data, exclusive partnerships, regulatory adoption) is not yet established; accuracy gaps at large players may narrow over time.