Forecast Scoreboard Forecast
Scoreboard

Days 1–5. Compared with the National Weather Service forecast from the same hour. No one pays for a rank.

Hurricane tracks

Tropical Disturbance Edouard Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 2:00 AM ET Thu, Sep 3.

Tropical Disturbance Edouard has 23 positions on the best track, which is where the storm actually went, from the operational NHC file. 2 official forecast tracks are drawn. At 48 hours, the average track miss is 51 miles across 2 forecasts. At 48 hours, the official wind forecast averaged 26 mph and where the storm actually went averaged 29 mph. Stored model tracks on these forecast tracks: GFS, GEFS mean, Canadian GEM, UKMET, HAFS-A, HAFS-B, HWRF, HMON, NAVGEM, Google DeepMind, WeatherNext 3.

AL052026 · 2026 · Aug 28–Sep 3, 2026. Score table. Damage reports.

How to read this. The solid line is where the storm went. A dashed line is where the official forecast said it would go. A smaller path miss is closer. Distances are statute miles. Wind speeds are miles per hour.

The technical details

Path miss on this page is the great-circle distance in statute miles, the same miles as the home card and the score table. The Earth radius is 3,958.7613 miles. The file also keeps that distance in nautical miles. One nautical mile is 1,852 meters, about 1.15 statute miles. A case counts when that forecast and the best track (BEST, lead 0) share the same valid time. Positions are not interpolated. A model track counts even when that cycle has no official forecast yet. Skill against the official forecast (OFCL) still requires the official forecast from the same issue time and lead.

Shown leads are 12, 24, 36, 48, 60, 72, 96, and 120 hours, once a paired fix exists. Sample size is the number of paired cases at that lead. Overall rank still uses 24, 48, 72, and 120 hours. The 96-hour lead is drawn when the deck has a paired fix, and it is not in that rank.

Wind on this page is miles per hour. The file stores maximum wind in knots. One knot is about 1.15 miles per hour. An advisory wind is rounded to the nearest 5 mph. A mean on this page is rounded to the nearest mile per hour. Wind miss is the absolute difference on the paired cases. There is no confidence interval on this map. The daily board’s interval is a 95% percentile bootstrap.

Overall rank is the average of the path rank and the wind rank on this storm. Each rank uses the graded leads at 24, 48, 72, and 120 hours, and each of those leads counts once, however many forecasts it holds. A lower miss is the better rank. A tie shares the average of the places those forecasts occupy. A source is ranked only with at least 3 graded forecasts for path and 3 for wind. Fewer than that says Not enough forecasts yet. A source with no graded path, or no graded wind, is left out of both ranks, and overall shows —.

The best track is the operational NHC b-deck. It is preliminary and revised after the season. HURDAT2 is not loaded. Model lines come from the public a-deck for the same forecast tracks, and only when that file stores them. Google DeepMind is the Weather Lab operational ensemble mean. WeatherNext 3 is that model’s ensemble mean from the same download. ECMWF AIFS, ECMWF HRES, and the ECMWF ENS mean are tropical-cyclone tracks from ECMWF open data. The ECMWF ENS mean is the average of the member centers in the IFS ensemble track file. AI GFS is NOAA’s AIGFS tracker when that file is still posted. The methodology page names the aids that are scored.

The methodology page is the full reference. How we grade says the same rules in plain English.

The best track is the operational NHC b-deck. It is preliminary and is revised after the season. The post-season HURDAT2 track is not loaded.

ECMWF AIFS, ECMWF HRES, ECMWF ENS mean, AI GFS: No graded forecasts yet.

Overall rank

Overall averages each forecast's rank on path and on wind strength. See the separate scores below.

Place on this list. 1 was closest to the weather that happened. A tie shares this number, and the next place skips ahead. Early read until the longer day count, then proven. The forecast source this row scores. Path and wind ranksOverall averages each forecast's rank on path and on wind strength. See the separate scores below. Track rankPlace on path miss. 1 was closest. On one storm this is that place. Across storms it is the average of those places. Each graded lead counts once. A tie shares the average place. Intensity rankPlace on wind miss. 1 was closest. On one storm this is that place. Across storms it is the average of those places. Each graded lead counts once. A tie shares the average place.
1 Google DeepMind 1.5 1 2
1 NHC official 1.5 2 1
3 WeatherNext 3 3 3 3
4 HAFS-B 6 7 5
5 HAFS-A 6.5 9 4
6 HMON 7 6 8
7 HWRF 7.5 8 7
7 UKMET 7.5 4 11
9 GFS 8.5 11 6
9 Canadian GEM 8.5 5 12
11 NAVGEM 10 10 10
12 GEFS mean 10.5 12 9

How we grade

Track and intensity by model

Each row is one source at one lead that has already verified, including 12, 24, 36, and 48 hours. The count is how many forecasts shared a time with where the storm went. Path miss is statute miles. Wind miss is miles per hour. The rank number is that source's place in the table above, and it still uses 24, 48, 72, and 120 hours.

Place on this list. 1 was closest to the weather that happened. A tie shares this number, and the next place skips ahead. Early read until the longer day count, then proven. The forecast source this row scores. LeadHow many hours ahead this forecast was made. Scored leads are 24, 48, 72, and 120. The technical name is lead. CasesHow many past forecasts went into this average. A forecast counts only when the best track has a fix at that exact time. The technical name is cases. Track errorAverage how far the predicted storm path was from where it actually went, in miles. Lower is better. The technical name is track error. Track skillHow that path miss compares with the official hurricane forecast. Positive means better than the official forecast. Negative means worse. The technical name is track skill. Intensity errorAverage how far off the predicted wind speed was, in miles per hour. The file stores knots. Lower is better. The technical name is intensity error. Intensity skillHow that wind miss compares with the official hurricane forecast. Positive means better. Negative means worse. The technical name is intensity skill.
1 Google DeepMind 12 h 10 13 mi Beats the official forecast by 23% 5 mph Behind the official forecast by 15%
1 Google DeepMind 24 h 7 17 mi Beats the official forecast by 16% 5 mph Behind the official forecast by 190%
1 Google DeepMind 36 h 5 19 mi Beats the official forecast by 37% 1 mph Behind the official forecast by 20%
1 Google DeepMind 48 h 2 30 mi Beats the official forecast by 41% 3 mph Ties the official forecast
1 NHC official 12 h 10 17 mi — 5 mph —
1 NHC official 24 h 8 19 mi — 1 mph —
1 NHC official 36 h 4 32 mi — 1 mph —
1 NHC official 48 h 2 51 mi — 3 mph —
3 WeatherNext 3 12 h 10 15 mi Beats the official forecast by 12% 6 mph Behind the official forecast by 40%
3 WeatherNext 3 24 h 8 22 mi Behind the official forecast by 19% 5 mph Behind the official forecast by 220%
3 WeatherNext 3 36 h 5 30 mi Behind the official forecast by 3% 3 mph Behind the official forecast by 180%
3 WeatherNext 3 48 h 3 47 mi Behind the official forecast by 8% 4 mph Behind the official forecast by 60%
3 WeatherNext 3 60 h 1 47 mi — 5 mph —
4 HAFS-B 12 h 12 38 mi Behind the official forecast by 199% 9 mph Behind the official forecast by 85%
4 HAFS-B 24 h 12 65 mi Behind the official forecast by 212% 8 mph Behind the official forecast by 860%
4 HAFS-B 36 h 12 82 mi Behind the official forecast by 126% 12 mph Behind the official forecast by 720%
4 HAFS-B 48 h 10 95 mi Behind the official forecast by 53% 11 mph Behind the official forecast by 40%
4 HAFS-B 60 h 8 84 mi — 18 mph —
4 HAFS-B 72 h 5 94 mi — 9 mph —
5 HAFS-A 12 h 12 37 mi Behind the official forecast by 223% 10 mph Behind the official forecast by 175%
5 HAFS-A 24 h 12 67 mi Behind the official forecast by 251% 8 mph Behind the official forecast by 500%
5 HAFS-A 36 h 12 85 mi Behind the official forecast by 147% 12 mph Behind the official forecast by 560%
5 HAFS-A 48 h 11 100 mi Behind the official forecast by 60% 11 mph Behind the official forecast by 40%
5 HAFS-A 60 h 9 108 mi — 16 mph —
5 HAFS-A 72 h 5 117 mi — 9 mph —
6 HMON 12 h 8 31 mi Behind the official forecast by 253% 13 mph Behind the official forecast by 290%
6 HMON 24 h 8 39 mi Behind the official forecast by 184% 14 mph Behind the official forecast by 1560%
6 HMON 36 h 7 55 mi Behind the official forecast by 79% 12 mph Behind the official forecast by 460%
6 HMON 48 h 6 75 mi Behind the official forecast by 54% 13 mph Behind the official forecast by 120%
6 HMON 60 h 5 79 mi — 7 mph —
6 HMON 72 h 2 94 mi — 5 mph —
7 UKMET 12 h 8 27 mi Beats the official forecast by 14% 15 mph Behind the official forecast by 300%
7 UKMET 24 h 7 36 mi Behind the official forecast by 18% 16 mph Behind the official forecast by 1260%
7 UKMET 36 h 6 46 mi Behind the official forecast by 48% 18 mph Behind the official forecast by 680%
7 UKMET 48 h 5 41 mi Behind the official forecast by 42% 19 mph Behind the official forecast by 180%
7 UKMET 60 h 3 52 mi — 22 mph —
7 UKMET 72 h 2 50 mi — 25 mph —
7 HWRF 12 h 8 32 mi Behind the official forecast by 122% 5 mph Behind the official forecast by 30%
7 HWRF 24 h 8 44 mi Behind the official forecast by 136% 9 mph Behind the official forecast by 820%
7 HWRF 36 h 8 71 mi Behind the official forecast by 99% 11 mph Behind the official forecast by 160%
7 HWRF 48 h 7 104 mi Behind the official forecast by 82% 9 mph Behind the official forecast by 100%
7 HWRF 60 h 5 141 mi — 5 mph —
7 HWRF 72 h 3 230 mi — 0 mph —
9 GFS 12 h 17 28 mi Behind the official forecast by 35% 8 mph Behind the official forecast by 88%
9 GFS 24 h 15 53 mi Behind the official forecast by 113% 10 mph Behind the official forecast by 590%
9 GFS 36 h 13 77 mi Behind the official forecast by 115% 11 mph Behind the official forecast by 660%
9 GFS 48 h 11 101 mi Behind the official forecast by 93% 16 mph Behind the official forecast by 120%
9 GFS 60 h 8 124 mi — 17 mph —
9 GFS 72 h 5 165 mi — 9 mph —
9 GFS 96 h 1 88 mi — 3 mph —
9 Canadian GEM 12 h 8 21 mi Behind the official forecast by 3% 14 mph Behind the official forecast by 300%
9 Canadian GEM 24 h 7 33 mi Behind the official forecast by 78% 16 mph Behind the official forecast by 1240%
9 Canadian GEM 36 h 6 43 mi Behind the official forecast by 79% 17 mph Behind the official forecast by 680%
9 Canadian GEM 48 h 5 42 mi Behind the official forecast by 31% 18 mph Behind the official forecast by 260%
9 Canadian GEM 60 h 4 50 mi — 16 mph —
9 Canadian GEM 72 h 3 60 mi — 12 mph —
9 Canadian GEM 96 h 1 90 mi — 5 mph —
11 NAVGEM 12 h 12 32 mi Behind the official forecast by 164% 13 mph Behind the official forecast by 312%
11 NAVGEM 24 h 12 37 mi Behind the official forecast by 151% 16 mph Behind the official forecast by 2060%
11 NAVGEM 36 h 10 46 mi Behind the official forecast by 173% 19 mph Behind the official forecast by 760%
11 NAVGEM 48 h 9 56 mi Behind the official forecast by 72% 17 mph Behind the official forecast by 160%
11 NAVGEM 60 h 8 92 mi — 19 mph —
11 NAVGEM 72 h 6 111 mi — 21 mph —
12 GEFS mean 12 h 17 27 mi Behind the official forecast by 43% 11 mph Behind the official forecast by 208%
12 GEFS mean 24 h 15 54 mi Behind the official forecast by 137% 14 mph Behind the official forecast by 1000%
12 GEFS mean 36 h 13 78 mi Behind the official forecast by 128% 17 mph Behind the official forecast by 1020%
12 GEFS mean 48 h 11 97 mi Behind the official forecast by 116% 19 mph Behind the official forecast by 320%
12 GEFS mean 60 h 8 96 mi — 19 mph —
12 GEFS mean 72 h 5 102 mi — 10 mph —

How we grade

ECMWF AIFS, ECMWF HRES, ECMWF ENS mean, AI GFS: No graded forecasts yet.

Track map

The solid line is the best track. Dashed lines are official forecast tracks from a few advisories, from the issue position out through the leads stored in that advisory. Thinner lines are model tracks from NHC’s public a-deck for those same advisories, and only when that file actually contains them. Google DeepMind and WeatherNext 3 are ensemble-mean tracks from Weather Lab, drawn on those same advisories. ECMWF AIFS, ECMWF HRES, and the ECMWF ENS mean are open-data cyclone tracks, drawn the same way. AI GFS is NOAA’s AIGFS tracker, drawn when that file is still posted.

26°N 30°N 34°N 38°N 102°W 96°W 91°W 86°W
Map of Tropical Disturbance Edouard. The best track, where the storm actually went, has 23 positions. 2 official forecast tracks are drawn. Model lines: GFS, GEFS mean, Canadian GEM, UKMET, HAFS-A, HAFS-B, HWRF, HMON, NAVGEM, Google DeepMind, WeatherNext 3. Latitude and longitude, scaled by the cosine of the mid-latitude so a degree of longitude is not stretched.
  • Actual track (23 positions)
  • NHC official Aug 31, 12:00 UTC
  • NHC official Aug 31, 18:00 UTC
  • GFS
  • GEFS mean
  • Canadian GEM
  • UKMET
  • HAFS-A
  • HAFS-B
  • HWRF
  • HMON
  • NAVGEM
  • Google DeepMind
  • WeatherNext 3

The chart measures how far the track was off in statute miles, the same miles as the home card. It includes 12, 24, 36, 48, 60, 72, 96, and 120 hours when a paired fix exists. The overall rank uses 24, 48, 72, and 120 hours. Positions are not interpolated.

How far the track was off

17 mi 12 h 19 mi 24 h 32 mi 36 h 51 mi 48 h
Average official track miss in miles by how far ahead. 12 hours 17 miles over 10 forecasts. 24 hours 19 miles over 8 forecasts. 36 hours 32 miles over 4 forecasts. 48 hours 51 miles over 2 forecasts.
LeadHow many hours ahead this forecast was made. This map shows 12, 24, 36, 48, 60, 72, 96, and 120 when a paired fix exists. Overall rank uses 24, 48, 72, and 120. The technical name is lead. CasesHow many past forecasts went into this average. A forecast counts only when the best track has a fix at that exact time. The technical name is cases. Track errorAverage how far the predicted storm path was from where it actually went, in statute miles. Lower is better. The technical name is track error. Intensity errorAverage how far off the predicted wind speed was, in miles per hour, on this page. Lower is better. The file stores knots. The technical name is intensity error. Forecast max windAverage top wind in the official forecast, in miles per hour, on the paired cases. The file stores knots. The technical name is forecast maximum wind. Best-track windAverage top wind where the storm actually went, in miles per hour, at the same times. The file stores knots. The technical name is best-track wind.
12 h 10 17 mi 5 mph 39 mph 37 mph
24 h 8 19 mi 1 mph 36 mph 36 mph
36 h 4 32 mi 1 mph 33 mph 35 mph
48 h 2 51 mi 3 mph 26 mph 29 mph

Miles are statute miles. Wind is miles per hour. The National Hurricane Center file stores wind in knots. One knot is about 1.15 miles per hour. Nautical miles are in the technical details.

How we grade

Top wind

12 h 24 h 36 h 48 h
Top wind, official forecast versus where the storm went. At 12 hours the forecast averaged 39 mph and where the storm actually went averaged 37 mph. At 24 hours the forecast averaged 36 mph and where the storm actually went averaged 36 mph. At 36 hours the forecast averaged 33 mph and where the storm actually went averaged 35 mph. At 48 hours the forecast averaged 26 mph and where the storm actually went averaged 29 mph.
  • Official forecast maximum wind
  • Best-track maximum wind

Source: National Hurricane Center / NOAA. The operational b-deck and the public a-deck are U.S. government works in the public domain. Google DeepMind and WeatherNext 3 ensemble means are experimental forecasts from Google DeepMind Weather Lab. Forecasts older than 48 hours are used under CC BY 4.0. ECMWF AIFS, ECMWF HRES, and ECMWF ENS tracks are ECMWF open data, used under CC BY 4.0. AI GFS tracks are a NOAA AIGFS product. Forecast Scoreboard is not affiliated with NHC, NOAA, Google, or ECMWF.