Data · 1 to 14 Nov 2026 · 8 min read

What two weeks of pilot reports look like

Two weeks of pilot reports, each logged against our forecast for the same spot.

  1. 01The question
  2. 02Volume
  3. 03Where
  4. 04What pilots said
  5. 05Altitude
  6. 06Aircraft
  7. 07Time of day
  8. 08Lead time
  9. 09Forecast vs. reports
  10. 10One record
  11. 11What it supports
  12. 12Gaps in the data
← Bumpy Blog
Topic
Data, machine learning
Data
Reading time
8 min
Companion post
Learning to forecast turbulence from pilot reports
Pilot reports logged per day, 1 to 14 November 2026. The darker top of each column is a report of bumps; the pale base of each column is pilots saying the air was smooth. The last day is partial.

01Is two weeks of pilot reports enough to learn from?

Since 1 November we've logged every pilot turbulence report we can get against the forecast we had for that place, height and time. Before training anything on that log, we looked at what's actually in it.

pilot reports
report-vs-forecast rows
reports a day, on average
say the air was smooth

The short version. There is enough data to check and correct today's forecast over North America, but not enough to train a model of our own.

02About one report a minute

We rebuild the forecast grid every hour. Each build is a , and we keep the newest three.

Every new report is logged once against each of those runs, so one report becomes three rows.

Logging began on 1 November at about 06:00 UTC. Daily volume swings between about 1,500 and 3,100 reports, depending on the weather and on weekday traffic. 14 November is a partial day.

Reports logged per day

bumpssmooth
Tap a day for its numbers.

03Where the reports come from

97.6% of reports are over North America. That's the source, not a filter of ours. The data comes from aviationweather.gov, and most of it is US (pilot reports): a pilot radios in how the ride feels.

The rest of the world shows up only through , automated position reports from an airline's aircraft that sometimes carry a turbulence note. 97% of them come from one airline, United, over the Pacific and Atlantic.

The dense lines on the map are the busy US routes.

smoothlightlight–moderatemoderatemoderate–severesevere or extreme
Region (rough boxes)ReportsShare

04What pilots said

Pilot reports are words, not measurements. The pilot picks a category for how the ride felt in their own aircraft.

To compare words with a forecast, we turn each category into a rough for a medium jet, from 0.15 for light to 0.60 for extreme. EDR is eddy dissipation rate, the standard measure of turbulence strength, and higher is bumpier. On the forecast side we call 0.10 light, 0.22 moderate and 0.34 severe.

Smooth reports are logged too, and they make up 27% of the total. A model needs them as much as the bumps. Without them it only ever sees places where something happened.

Reports by what the pilot said

Severe and extreme together are 86 reports, 0.3% of the total. With moderate-to-severe added it is 192. They often come several at a time from one patch of sky, so there are fewer separate events than the count suggests.

05Altitude: about half are at cruise

A (FL) is altitude in hundreds of feet, so FL350 is about 35,000 ft.

About half of all reports sit between FL300 and FL400, where airliners cruise. The low levels are busy too, with climbs, descents and small aircraft, and that's where smooth reports are far more common. Switch to “Share smooth” to see it.

Reports by flight level

Bands of 20 flight levels. Rust is bumps, grey is smooth. Many reports below FL100 have no forecast to compare with, because the grid's lowest level is above them. That explains most of the 4,164 rows with an empty forecast.

06Aircraft: mostly 737s and A320s

PIREPs record the aircraft's type code, such as B738 for a 737-800. AIREPs record the flight number instead (UAL58, say), so we don't know what they were flying.

We sort the type codes into five size classes, using the same rules the forecast uses to score flights. Anything the rules don't recognise counts as medium.

Reports by aircraft size, split by what was reported

Tap a class to see its types
Heavies report moderate or worse more often (32%) than mediums (22%). They fly the long, windy oceanic routes, and their crews may also report differently. Two weeks of data can't tell those apart. The A380 has only 14 reports.

Pilots don't always write proper ICAO codes (the international standard for aircraft types). About 140 reports use family codes such as B777, B767, B747 and B787, and the scoring rules count those as medium, not heavy. A few small aircraft codes, such as C402, BE30 and PA32, also fall through to medium. The chart shows the rules exactly as they are.

07Time of day

Reports follow US daytime traffic. “Local solar time” shifts each report's UTC time by its longitude, so the chart shows the time of day where the aircraft was.

The overnight hours are thin, so a model will be least sure about overnight flights.

Reports per hour

08Lead time: two hours either way, no more

Lead time is how long before the report the forecast was made. We compare each report with the three runs on disk when it's logged, and those range from about two hours older than the report to two hours newer.

A negative lead means the run came after the pilot reported, so it isn't a fair test.

The app shows forecasts for flights hours or days away. The log can't say yet how good a 6-hour or 24-hour forecast is, and that is the number a nervous flyer cares about.

Rows by lead time, in minutes

run made after the reportrun made before (fair test)
The app needs this axis to reach +1,440 minutes (a day) and beyond. Only the newest three runs are kept, so only the values sampled into this log survive.

09How the forecast compares with what pilots felt

Over North America the forecast comes from (Graphical Turbulence Guidance), the turbulence forecast from , the US weather agency. Everywhere else it's a rougher estimate that we work out from (the Global Forecast System), NOAA's global weather model.

For each report we take the newest run made before it. That gives 28,501 fair pairs, with a median lead of 29 minutes.

The chart shows how forecast EDR is spread for each kind of report. Drag the slider to move the cut-off and see what it would have caught.

smoothlight, light–moderatemoderate or worse
of moderate-or-worse reports caught
of smooth reports wrongly called moderate
pairs: moderate+ / smooth / light
Horizontal axis: forecast EDR at the report. Each curve is scaled to its own total. “Inside” is a box from 20–55°N and 130–60°W, roughly GTG's coverage. Outside that box every forecast is the GFS estimate (see Gaps in the data).

It ranks well

Pick a random moderate-or-worse report and a random smooth one. Inside the GTG area, the bumpy one has the higher forecast 79% of the time. That's an (area under the ROC curve) of 0.79. Outside, it's 77%.

So the forecast does know where the air is rougher.

It reads low

At our 0.22 moderate cut-off, only 9% of moderate-or-worse reports inside the GTG area get a moderate forecast. The median forecast at those reports is 0.137.

This is the clearest finding so far, and a recalibration could fix it now. It holds for every size class: the median is 0.137 for mediums and 0.150 for heavies.

One possible cause, not yet tested, is that averaging fine GTG cells into the coarser grid flattens the peaks.

ReportedAreaPairs10th pctMedian90th pctNearby maxForecast moderate+

Values are forecast EDR. “Nearby max” is the median of the highest forecast within about 55 km and 20 flight levels of the report. It shows whether the forecast had the bump, just a few miles off.

10What one record looks like

Each record pairs one report with one forecast run. This one is real: a pilot report of moderate turbulence. The raw field is the text the pilot or airline system sent.


11What this sample can and can't support

What it can do now

The sample can recalibrate how forecast EDR maps to smooth, light, moderate and severe, over North America and at short lead. There are about 6,600 moderate-or-worse and 7,400 smooth fair pairs. That's plenty for a simple correction, and it would be the first real test of what the app's words mean.

What it can't do yet

A trained model starts to make sense after about a year of logging that includes 6–24-hour leads. At today's rate that's about 790,000 reports, about 5,000 of them moderate-to-severe or worse.

12Gaps in the data

  1. No global turbulence forecast. (the World Area Forecast System), the global turbulence product, has never loaded. NOAA's public server refused or dropped our requests, and the product has since left that server. So outside the GTG area, every forecast in this log is the GFS estimate.
  2. Lead time stops at two hours. Checking a day-ahead forecast means sampling each run against reports that arrive hours and days later. A full run is about 570 MB, so the plan is to keep a thinned copy of older runs.
  3. AIREPs have flight numbers, not aircraft types. That affects 2,170 reports. The plan is to look up the type from the flight number when the report is logged.