Archived snapshot from the 00Z Fri 9 Oct 2026 model cycle. Forecasts have changed since. See the latest analysis.
NHC model cycle 00Z Fri 9 Oct 2026 · central Gulf of Mexico
Physics-based, statistical and AI models are all forecasting the same Gulf hurricane. This page shows where they agree, where they split, and whether the split is unusual. It uses NOAA's public model file and three seasons of verification.
Nearly every model agrees on the shape. Isaias strengthens for about 12 hours, then weakens fast after +24 h as NHC's track takes the center inland over the north-central Gulf coast. NHC's track is just offshore at +24 h and inland by +36 h. The models disagree on two numbers: how strong the storm is at the coast, and how fast it falls apart over land.
This cycle the early aids and NHC's official forecast all start from the same 85 kt at 00Z, so Fig. 1 has no starting offset to correct for. NHC's peak of 100 kt at +12 h is just above every aid at that time, the highest being HAFS-A at 99 kt. NHC's 03Z advisory raised the intensity to 90 kt, citing Hurricane Hunter Doppler radar winds.
Isaias sat nearly stationary in the Bay of Campeche for about two days, first as a weak disturbance and then as a depression. It then turned east-northeast and intensified rapidly, from 35 kt at 06Z Wednesday to 70 kt at 06Z Thursday. That is 35 kt in 24 hours. It reached 85 kt by 18Z Thursday in NHC's operational best track and held there at 00Z Friday. NHC has since revised the 12Z Thursday intensity from 70 to 75 kt; the scores below use the revised best track. Early on, the models disagreed about both the turn and the intensification. Some moved the system east quickly and strengthened it. Others kept it slow, weak and farther south. Those forecasts can now be checked against NHC's best track.
The 00Z Wednesday runs, made 48 h before Friday's 00Z position, show who handled the turn. DeepMind's raw run placed the center 18 nmi from where it was. That is the closest of any aid with its own track, for the third run in a row: the 12Z and 18Z Tuesday runs were 6 and 19 nmi off. NHC's official forecast from 00Z Wednesday was 58 nmi off. The raw HAFS-A and HAFS-B runs missed by 120 and 112 nmi. Single runs vary, which is why the averages below matter more. Over every forecast so far that all the aids below share, the interpolated DeepMind aid has the smallest average track error, 18 nmi, and NHC is next at 20 nmi.
The same raw 00Z Wednesday DeepMind run forecast 86 kt for 00Z Friday, against 85 kt in the best track. The raw HAFS-A run was next closest, at 83 kt. The raw HAFS-B run had 96 kt and the Navy's COAMPS-TC 104 kt. Across the shared forecasts, the smallest intensity errors belong to the corrected consensus (HCCA), COAMPS-TC, DeepMind, NHC and the neural-network consensus (NNIC), all between 4 and 6 kt.
Nearly every aid was too slow to intensify Isaias. Every aid in the table except COAMPS-TC has a low bias. The global models ran the lowest, as expected at their resolution, and the statistical LGEM was 16 kt low. Two days out, the raw GFS and its ensemble mean put the center 93 and 151 nmi from where it was. COAMPS-TC, the best interpolated physics model on intensity, had the largest track error of the regional models.
| Aid | Type | Intensity error | Intensity bias | Track error |
|---|---|---|---|---|
| HCCA | Consensus | 4.3 kt | −3.9 | 30 nmi |
| CTCI | Regional physics | 5.2 kt | +4.1 | 91 nmi |
| GDMI | AI (DeepMind) | 5.6 kt | −4.6 | 18 nmi |
| OFCL | NHC official | 5.8 kt | −5.2 | 20 nmi |
| NNIC | Machine learning | 6.0 kt | −5.8 | — |
| HWFI | Regional physics | 8.6 kt | −8.6 | 47 nmi |
| HMNI | Regional physics | 9.3 kt | −8.5 | 61 nmi |
| SHIP / DSHP | Statistical | 9.4 kt | −9.2 | — |
| HFBI | Regional physics | 10.8 kt | −9.2 | 56 nmi |
| HFAI | Regional physics | 10.9 kt | −10.8 | 58 nmi |
| AVNI | Global physics | 14.8 kt | −14.8 | 51 nmi |
| LGEM | Statistical | 15.7 kt | −15.6 | — |
| AEMI | Global physics | 23.8 kt | −23.8 | 73 nmi |
Mean absolute errors at +12 to +48 h, over the 20 forecast cycle and lead time pairs that every listed aid shares (a homogeneous sample), scored against NHC's operational best track through 00Z Friday. Statistical and ML aids borrow another model's track, so their track errors are not listed. This covers two to three days of one storm against a preliminary best track. It shows which models handled this storm's genesis and rapid intensification, not which models are better overall.
At +12 h, near the forecast peak, the regional physics models span 93–99 kt, with HAFS-A highest. The global physics models sit between 79 and 89 kt. Regional hurricane models follow the storm with nested grids (about 2 km for HAFS) that can resolve the eyewall. Global models, with grid spacings of about 10 km or more, cannot, and they usually run weak at the peak.
By +24 h, with NHC's center just offshore, the regional models have weakened to 74–84 kt. The statistical aids (85–88 kt) and the Canadian ensemble mean (87 kt) are now the highest, and the interpolated DeepMind aid the lowest, at 69 kt. NHC's 85 kt is at the upper end. NHC's discussion expects shear to "increase considerably on Friday and cause some weakening before landfall."
At +36 h the DeepMind aid (GDMI) is at 25 kt, its last forecast point, and the regional physics models are at 37–45 kt. The GFS is at 44 kt. The UK global model and the Canadian ensemble mean are still at 58 and 70 kt, and the deterministic Canadian run (CMC2, not plotted) is at 71 kt. SHIPS, a statistical model with no land in it by design, holds 67 kt. Its land-aware version, Decay-SHIPS, drops to 48 kt. The 19 kt between those two is the land effect as that statistical scheme models it, which makes the pair a useful control.
Some of the intensity spread is really track spread. A model that brings the center ashore earlier, or moves it farther inland, also weakens it earlier. At +36 h HAFS-A puts the center at 31.9°N 88.8°W and the DeepMind aid at 31.9°N 87.0°W, about 170 km apart. HAFS-A is at 41 kt there and the DeepMind aid at 25 kt (Fig. 4).
The DeepMind line on most spaghetti plots is GDMI, an interpolated aid. The raw model output (GDMN) arrives too late for the forecast cycle it would serve. NHC therefore takes the previous run and adjusts it to the storm's intensity at the start time.
For Isaias, the raw 18Z DeepMind run went from its 76 kt starting value to 98 kt at 00Z, six hours later. The best-track intensity at 00Z is 85 kt, and the aids were adjusted to that 85 kt. After the adjustment, the 00Z aid runs 8–13 kt below the raw run at 0, +12 and +24 h, and 3 kt below it at +36 h, where both end. The raw run peaks at 99 kt at +12 h, close to NHC's 100 kt. The raw run started high in each of the last three cycles: 82 kt against 75 kt in the revised best track (12Z), 106 kt against 85 kt (18Z) and now 98 kt against 85 kt. In each, the interpolated aid sits below the raw model.
"AI is less aggressive" is partly an artifact of this adjustment. Compare raw and interpolated output before drawing conclusions about any model class.
Intensity forecasts over land depend on when and where the center crosses the coast. The tracks below cluster tightly toward the Alabama and western Florida Panhandle coast. At +36 h every plotted aid has the center inland, between 31.9°N and 32.6°N and between 87.0°W and 88.8°W. NHC's discussion says its track lies "closer to the right side of the guidance envelope, very near the latest corrected consensus (HCCA)." Their small east–west and timing differences explain part of the +36 to +48 h intensity spread.
Not among the core models. The split comes from the models outside that core.
We took eight aids that ran in every season from 2023 to 2025: HAFS-A, HAFS-B, HWRF, HMON, COAMPS-TC, GFS, Decay-SHIPS and LGEM. For every Atlantic forecast cycle that started at hurricane strength, we computed their spread, the standard deviation across models. By that measure, Isaias's disagreement is ordinary at +24, +48 and +72 h (31st, 34th and 43rd percentiles).
Isaias stands out once the other models come back in. Adding the UK global model, the Canadian ensemble mean and SHIPS raises the +48 h spread from 7.1 kt to 13.2 kt. (The DeepMind aid is normally in this comparison too, but it has no +48 h value this cycle.) That figure uses a different set of models, so it can't be compared to the histograms. It does show where the disagreement comes from: models that treat land very differently.
NOAA's global ensemble (GEFS) runs 31 versions of the GFS, each with slightly perturbed starting conditions and model physics. At this resolution its intensities are much too weak. At 18Z the members started between 60 and 85 kt against an observed 85 kt, so read the plume for timing, not strength. On the 00Z clock, 19 of the 31 members weaken fastest between +24 and +36 h, and all 31 lose at least 15 kt in that window. It spans 00Z to 12Z Saturday (7 PM Friday to 7 AM Saturday CDT), consistent with NHC's forecast landfall late Friday or early Saturday. That is independent evidence that the timing of the move inland is fairly well constrained.
The European (ECMWF) model and ensemble are not in NOAA's public model file, so they are not shown. Google's model is itself an ensemble, but the public file carries one forecast per cycle.
Each version of this page, one per NHC model cycle, is committed to a public repository before landfall, and the commit history timestamps it. After the storm, each aid will be scored against NHC's best track from +12 to +72 h, on the questions this storm raises:
One storm can't settle which model is better. NHC's annual verification reports are where models get judged. This page is a worked example of reading the guidance.
This page is updated as new NHC model cycles arrive. Each earlier version is preserved unchanged.