ClimateClimate Foundation Models

Predict Air Quality and Tropical Cyclones with Aurora

How to use Aurora's specialized heads for air quality (PM2.5) forecasting and tropical cyclone tracking.

SciRouter Team
April 11, 2026
12 min read

Weather forecasting is the obvious application of Aurora, but it is not the only one. The Microsoft team explicitly framed Aurora as an atmospheric foundation model, meaning the same backbone is fine-tuned into multiple task-specific heads. Two of the most interesting heads are air quality prediction and tropical cyclone tracking. This post walks through what each one does and how to use them through SciRouter's climate lab.

Note
For background on Aurora's architecture and how the backbone is trained, see Aurora Explained.

Air quality prediction with Aurora

Air quality forecasting is a stack of hard problems. You need to know how winds are transporting air masses, how pollutants are being emitted from sources, how they are chemically transforming in the atmosphere, and how boundary-layer mixing is distributing them vertically. Traditional chemical transport models like GEOS-Chem solve all of this with physics and chemistry, and they are excellent — but they are slow.

Aurora's air quality head takes the shared atmospheric representation and maps it directly to pollutant concentrations. The model has learned the relationships between atmospheric dynamics and pollutant transport from training data, so it can produce a global air quality forecast in a fraction of the time.

What it predicts

  • Particulate matter (PM2.5, PM10). The pollutants that matter most for human health, on a global grid.
  • Nitrogen dioxide (NO2). A marker for combustion sources and a precursor for ozone and secondary particulate matter.
  • Sulfur dioxide (SO2). Important for industrial emission tracking and secondary aerosol formation.
  • Ozone (O3). The ground-level photochemical pollutant that matters for respiratory health.
  • Carbon monoxide (CO). A long-lived marker for combustion and long-range transport.

How to use it

You send a starting atmospheric state and the forecast horizon to the Aurora air quality endpoint through SciRouter. The response is the predicted concentrations of each pollutant on a global grid at the requested lead time. If you pass several horizons in one call, you get a time series.

Typical applications include real-time dashboards that show air quality trajectories for a city or region, what-if analysis of how wind-shift scenarios affect pollution transport, and rapid scoping for emergency-response planning. Aurora's speed is what makes all of these interactive.

Tropical cyclone tracking with Aurora

Tropical cyclones are one of the highest-leverage forecasting problems in the world. A better forecast of where a storm will go in the next 72 hours directly translates to better evacuation decisions and fewer deaths. The operational forecasts from agencies like NOAA and ECMWF are the gold standard, and they should stay the primary source for life-safety decisions.

Aurora's cyclone head adds something new: the ability to generate large ensembles of track forecasts in seconds. Because Aurora is fast, you can perturb the initial atmospheric state many ways and watch how the storm track spreads, giving you a probabilistic view that used to be available only to the largest forecasting centers.

What it predicts

  • Storm position. Predicted latitude and longitude of the storm center at future lead times.
  • Intensity indicators. Depending on the model variant, associated intensity measures such as minimum central pressure and maximum wind speed.
  • Uncertainty. When run as an ensemble, a cone of plausible tracks, not a single deterministic line.

How to use it

Send a recent atmospheric state that already contains an active cyclone. Aurora does not invent storms out of clear skies — it forecasts forward from the state you give it. If you want to track a specific storm, pull a fresh state from ERA5 or another source and feed it to the endpoint.

For ensemble tracking, run the same storm state multiple times with small perturbations in wind, temperature, or humidity. Aurora's speed means a 50-member ensemble takes less time than one physics-based forecast would.

Combining the two tasks

The interesting pattern is chaining the cyclone and air quality heads together. A landfalling storm redistributes air quality — wildfires push smoke around, industrial zones experience sudden changes in pollutant advection, and coastal communities see PM2.5 spikes or drops depending on wind direction. Aurora lets you reason about both in the same workflow.

  • Pull a current atmospheric state.
  • Call the cyclone head to forecast the storm track.
  • For each time step, call the air quality head to forecast pollutant fields.
  • Render both layers on the same map to see how storm motion and air quality interact.

This kind of composite forecast is exactly what foundation-model framing was designed for. One backbone, many heads, all sharing representation.

Warning
Neither the air quality head nor the cyclone head is intended to replace operational forecasts from official agencies. Use Aurora for research, exploration, and high-throughput analysis. Always defer to official warnings for life-safety decisions.

Limits to keep in mind

  • Out-of-distribution behavior. Aurora is trained on historical data. If atmospheric conditions are truly unprecedented, the model's confidence may be miscalibrated.
  • Local effects. A global model cannot resolve every city block. For hyperlocal air quality questions you still want urban-scale chemistry models.
  • Emissions changes. Sudden emission changes — say, a major industrial shutdown or a wildfire event — may not be captured if the initial state does not reflect them.
  • No attribution. Aurora tells you what it thinks will happen. It does not tell you why in the physical-mechanistic sense. For that you want a coupled chemistry-climate model.

Bottom line

Aurora's air quality and tropical cyclone heads are what make the foundation-model framing real. A single backbone trained on the atmosphere can now power forecasts that used to require entirely separate modeling stacks, at speeds that open new applications. Hooked up through SciRouter's climate lab, it is a practical tool for anyone building climate, health, or emergency-response products.

Open the Climate Lab →

Frequently Asked Questions

Why is air quality prediction hard?

Air quality depends on both atmospheric dynamics and chemistry. You have to track the transport of pollutants on winds, source emissions from human activity, chemical transformations between species like ozone and NOx, and boundary-layer mixing. Traditional chemical transport models are heavy to run globally. A data-driven model like Aurora can approximate the result dramatically faster.

What pollutants can Aurora forecast?

The Aurora air quality head targets the standard global pollutants: particulate matter (PM2.5 and PM10), nitrogen dioxide, sulfur dioxide, ozone, and carbon monoxide. Exact coverage depends on the version of the head you are calling. Check the SciRouter climate lab documentation for the current schema.

Can Aurora track a specific hurricane?

Yes. Aurora's cyclone head predicts tropical cyclone tracks from an atmospheric initial state. Given a current state that contains an active storm, Aurora forecasts the storm's position forward. It will not invent a storm that is not in the initial state, so you need a fresh input for real-time tracking.

How accurate are the cyclone track forecasts?

Aurora's published results are competitive with operational cyclone forecasting at short and medium lead times. That does not mean it replaces the operational centers that issue warnings. Use Aurora for research, exploration, and high-throughput scenario testing. Use the official forecasts for life-safety decisions.

Is this better than chemical transport models like GEOS-Chem?

Not better in a scientific sense — those models are physics-based and tell you why the air is the way it is. Aurora is faster, which lets you do things you could not do before: real-time querying, large ensembles, and interactive what-if analysis. The two approaches are complementary.

Can I run an ensemble of cyclone forecasts?

Yes, and this is one of the most compelling applications. Because Aurora is so fast, you can perturb the initial state many ways and generate an ensemble of forecasts in seconds. That gives you probabilistic track information that was previously too expensive to run outside major forecasting centers.

How do I chain Aurora with other climate tools?

Use the SciRouter MCP server. Aurora and the other climate tools are exposed as agent-callable tools with typed schemas. An agent can take a high-level question like 'what is the air quality risk for this region over the next 48 hours' and chain the relevant tool calls on its own.

Try this yourself

500 free credits. No credit card required.