Verification

Envelope’s hurricane forecasts, run as a hindcast and scored against the 2014–2025 archive.

Storms verified
65
Seasons
2014–2025
Forecasts
1,676
Point evaluations
290,699,581
Truth sources
URMA 10-m analysis · NHC best track
Layer 1

Track

Each forecast generates 1,000 storm scenarios. At each lead time, the observed storm center is ranked within the scenario spread, along the direction of motion and across it; a centered spread ranks the observed center at 0.50 on average. Measured ranks are 0.47–0.50 at every lead, on both axes, illustrating that Envelope’s ensemble is spatially well-calibrated.

Lead timeAlong trackCross trackForecasts
24 h0.500.501,548
48 h0.470.481,379
72 h0.470.481,196
96 h0.470.501,008
120 h0.470.50835
Layer 2

Intensity

The same rank test, applied to intensity. In a calibrated spread, the observed intensity falls in the weakest 10% of scenarios 10% of the time, and in the strongest 10% of scenarios 10% of the time. Envelope’s stated 10th percentile verifies at 9th–10th percentile; Envelope’s stated 90th percentile verifies at 88th–90th percentile.

Lead timeIn weakest 10%In strongest 10%
24 h9.7%12.2%
48 h9.0%12.4%
72 h10.2%11.0%
96 h9.5%10.2%
120 h9.5%10.8%
Layer 3

Storm lifetime

A major part of modeling tropical cyclones is modeling the probability that the event dissipates. Envelope probabilities of dissipation are calibrated within 2–4 percentage points.

Lead timeScenarios dissipatedObserved
24 h12%8%
48 h22%18%
72 h33%29%
96 h43%41%
120 h53%51%
Layer 4

Wind field, given the track

For actual storms, we compare what Envelope’s wind field model would have said conditional on the post-event best track to our best estimate of the actual wind field. The model is well-calibrated, with some conservative over-forecasting of winds at the high-end where our error bars around the true wind speed are highest.

Model saidModel averageAnalysis averageRatioLocation-hours
40–50 mph44 mph40 mph0.902,348,671
50–60 mph54 mph53 mph0.97688,276
60–70 mph64 mph63 mph0.98213,835
70–80 mph74 mph73 mph0.9993,909
80–90 mph85 mph82 mph0.9750,390
90–100 mph95 mph89 mph0.9437,277
100–110 mph104 mph94 mph0.9019,888
110+ mph130 mph110 mph0.8422,137
Layer 5

End to end

We compiled every probabilistic forecast Envelope would have made in the historical record, binned them by probability band, and compared the forecast probabilities to the realized probabilities, demonstrating forecast reliability.

60 mph gust threshold
0.00.00.20.20.40.40.60.60.80.81.01.0Forecast probabilityObserved frequency
74 mph gust threshold
0.00.00.20.20.40.40.60.60.80.81.01.0Forecast probabilityObserved frequency

Methodology and assumptions

Our working source of wind field truth is NOAA’s URMA 10-m gust analysis, enhanced with tropical cyclone core winds estimated from National Hurricane Center best track position, intensity, and size (an enhancement that gap-fills wind underestimation in hurricane inner cores due to instrument sparsity). Track, intensity, and lifetime are verified against the National Hurricane Center’s post-season best track. All wind verification is over land, 2014–2025.