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

Remnant Low Lowell Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 8:00 PM ET Thu, Sep 10; Lowell is now a remnant low.

Remnant Low Lowell has 66 positions on the best track, which is where the storm actually went, from the operational NHC file. 4 official forecast tracks are drawn. At 48 hours, the average track miss is 62 miles across 50 forecasts. At 48 hours, the official wind forecast averaged 101 mph and where the storm actually went averaged 100 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.

EP122026 · 2026 · Aug 25–Sep 11, 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 2 1
2 WeatherNext 3 2 1 3
3 HAFS-A 4 6 2
4 HAFS-B 4.5 5 4
4 NHC official 4.5 4 5
6 HMON 6.5 7 6
7 UKMET 7 3 11
8 GFS 8 8 8
8 HWRF 8 9 7
10 GEFS mean 10 10 10
11 NAVGEM 10.5 12 9
12 Canadian GEM 11.5 11 12

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 56 11 mi Beats the official forecast by 40% 9 mph Behind the official forecast by 36%
1 Google DeepMind 24 h 54 20 mi Beats the official forecast by 36% 10 mph Beats the official forecast by 7%
1 Google DeepMind 36 h 52 30 mi Beats the official forecast by 35% 11 mph Beats the official forecast by 6%
1 Google DeepMind 48 h 50 42 mi Beats the official forecast by 33% 11 mph Beats the official forecast by 21%
1 Google DeepMind 60 h 48 53 mi Beats the official forecast by 37% 13 mph Beats the official forecast by 22%
1 Google DeepMind 72 h 46 66 mi Beats the official forecast by 36% 14 mph Beats the official forecast by 25%
1 Google DeepMind 96 h 42 84 mi Beats the official forecast by 40% 17 mph Beats the official forecast by 20%
1 Google DeepMind 120 h 38 95 mi Beats the official forecast by 45% 17 mph Beats the official forecast by 27%
2 WeatherNext 3 12 h 56 9 mi Beats the official forecast by 52% 9 mph Behind the official forecast by 50%
2 WeatherNext 3 24 h 54 15 mi Beats the official forecast by 53% 11 mph Behind the official forecast by 5%
2 WeatherNext 3 36 h 52 24 mi Beats the official forecast by 48% 11 mph Beats the official forecast by 3%
2 WeatherNext 3 48 h 50 34 mi Beats the official forecast by 45% 12 mph Beats the official forecast by 13%
2 WeatherNext 3 60 h 48 46 mi Beats the official forecast by 45% 13 mph Beats the official forecast by 21%
2 WeatherNext 3 72 h 46 61 mi Beats the official forecast by 42% 14 mph Beats the official forecast by 23%
2 WeatherNext 3 96 h 42 81 mi Beats the official forecast by 42% 16 mph Beats the official forecast by 24%
2 WeatherNext 3 120 h 38 98 mi Beats the official forecast by 43% 20 mph Beats the official forecast by 18%
3 HAFS-A 12 h 60 29 mi Behind the official forecast by 53% 9 mph Behind the official forecast by 47%
3 HAFS-A 24 h 58 48 mi Behind the official forecast by 51% 11 mph Behind the official forecast by 6%
3 HAFS-A 36 h 56 67 mi Behind the official forecast by 40% 11 mph Beats the official forecast by 2%
3 HAFS-A 48 h 54 95 mi Behind the official forecast by 42% 11 mph Beats the official forecast by 17%
3 HAFS-A 60 h 52 121 mi Behind the official forecast by 32% 13 mph Beats the official forecast by 22%
3 HAFS-A 72 h 50 146 mi Behind the official forecast by 27% 11 mph Beats the official forecast by 38%
3 HAFS-A 96 h 46 204 mi Behind the official forecast by 28% 13 mph Beats the official forecast by 38%
3 HAFS-A 120 h 42 270 mi Behind the official forecast by 33% 19 mph Beats the official forecast by 16%
4 HAFS-B 12 h 60 29 mi Behind the official forecast by 42% 13 mph Behind the official forecast by 116%
4 HAFS-B 24 h 58 46 mi Behind the official forecast by 44% 11 mph Behind the official forecast by 8%
4 HAFS-B 36 h 56 65 mi Behind the official forecast by 35% 11 mph Beats the official forecast by 3%
4 HAFS-B 48 h 54 93 mi Behind the official forecast by 34% 13 mph Beats the official forecast by 9%
4 HAFS-B 60 h 52 122 mi Behind the official forecast by 29% 16 mph Ties the official forecast
4 HAFS-B 72 h 50 150 mi Behind the official forecast by 26% 18 mph Beats the official forecast by 3%
4 HAFS-B 96 h 46 205 mi Behind the official forecast by 25% 16 mph Beats the official forecast by 25%
4 HAFS-B 120 h 42 260 mi Behind the official forecast by 25% 19 mph Beats the official forecast by 20%
4 NHC official 12 h 56 18 mi — 6 mph —
4 NHC official 24 h 54 31 mi — 10 mph —
4 NHC official 36 h 52 46 mi — 12 mph —
4 NHC official 48 h 50 62 mi — 14 mph —
4 NHC official 60 h 48 84 mi — 17 mph —
4 NHC official 72 h 46 104 mi — 19 mph —
4 NHC official 96 h 42 140 mi — 21 mph —
4 NHC official 120 h 38 172 mi — 24 mph —
6 HMON 12 h 60 26 mi Behind the official forecast by 36% 8 mph Behind the official forecast by 39%
6 HMON 24 h 58 46 mi Behind the official forecast by 48% 11 mph Behind the official forecast by 16%
6 HMON 36 h 56 70 mi Behind the official forecast by 51% 14 mph Behind the official forecast by 24%
6 HMON 48 h 54 96 mi Behind the official forecast by 53% 16 mph Behind the official forecast by 14%
6 HMON 60 h 52 125 mi Behind the official forecast by 46% 18 mph Behind the official forecast by 12%
6 HMON 72 h 50 151 mi Behind the official forecast by 43% 19 mph Behind the official forecast by 9%
6 HMON 96 h 46 190 mi Behind the official forecast by 28% 19 mph Beats the official forecast by 2%
6 HMON 120 h 42 250 mi Behind the official forecast by 35% 21 mph Beats the official forecast by 8%
7 UKMET 12 h 30 24 mi Behind the official forecast by 19% 33 mph Behind the official forecast by 470%
7 UKMET 24 h 29 35 mi Behind the official forecast by 11% 36 mph Behind the official forecast by 261%
7 UKMET 36 h 28 52 mi Behind the official forecast by 6% 38 mph Behind the official forecast by 234%
7 UKMET 48 h 27 62 mi Beats the official forecast by 3% 39 mph Behind the official forecast by 184%
7 UKMET 60 h 26 78 mi Beats the official forecast by 8% 40 mph Behind the official forecast by 153%
7 UKMET 72 h 25 95 mi Beats the official forecast by 10% 42 mph Behind the official forecast by 139%
7 UKMET 96 h 23 134 mi Beats the official forecast by 2% 46 mph Behind the official forecast by 134%
7 UKMET 120 h 21 183 mi Behind the official forecast by 4% 52 mph Behind the official forecast by 132%
8 GFS 12 h 60 27 mi Behind the official forecast by 42% 21 mph Behind the official forecast by 260%
8 GFS 24 h 58 48 mi Behind the official forecast by 53% 23 mph Behind the official forecast by 142%
8 GFS 36 h 56 70 mi Behind the official forecast by 47% 23 mph Behind the official forecast by 108%
8 GFS 48 h 54 95 mi Behind the official forecast by 47% 23 mph Behind the official forecast by 73%
8 GFS 60 h 52 121 mi Behind the official forecast by 36% 24 mph Behind the official forecast by 51%
8 GFS 72 h 50 149 mi Behind the official forecast by 36% 24 mph Behind the official forecast by 34%
8 GFS 96 h 46 212 mi Behind the official forecast by 41% 29 mph Behind the official forecast by 42%
8 GFS 120 h 42 281 mi Behind the official forecast by 47% 33 mph Behind the official forecast by 48%
8 HWRF 12 h 60 25 mi Behind the official forecast by 32% 9 mph Behind the official forecast by 54%
8 HWRF 24 h 58 48 mi Behind the official forecast by 54% 12 mph Behind the official forecast by 20%
8 HWRF 36 h 56 70 mi Behind the official forecast by 51% 13 mph Behind the official forecast by 19%
8 HWRF 48 h 54 93 mi Behind the official forecast by 50% 15 mph Behind the official forecast by 9%
8 HWRF 60 h 52 122 mi Behind the official forecast by 44% 16 mph Behind the official forecast by 2%
8 HWRF 72 h 50 153 mi Behind the official forecast by 46% 18 mph Ties the official forecast
8 HWRF 96 h 46 209 mi Behind the official forecast by 48% 21 mph Behind the official forecast by 5%
8 HWRF 120 h 42 278 mi Behind the official forecast by 59% 27 mph Behind the official forecast by 14%
10 GEFS mean 12 h 60 26 mi Behind the official forecast by 37% 32 mph Behind the official forecast by 438%
10 GEFS mean 24 h 58 49 mi Behind the official forecast by 63% 33 mph Behind the official forecast by 245%
10 GEFS mean 36 h 56 78 mi Behind the official forecast by 66% 35 mph Behind the official forecast by 218%
10 GEFS mean 48 h 54 108 mi Behind the official forecast by 68% 36 mph Behind the official forecast by 172%
10 GEFS mean 60 h 52 142 mi Behind the official forecast by 62% 38 mph Behind the official forecast by 140%
10 GEFS mean 72 h 50 178 mi Behind the official forecast by 62% 39 mph Behind the official forecast by 121%
10 GEFS mean 96 h 46 250 mi Behind the official forecast by 65% 44 mph Behind the official forecast by 118%
10 GEFS mean 120 h 42 316 mi Behind the official forecast by 65% 50 mph Behind the official forecast by 124%
11 NAVGEM 12 h 54 41 mi Behind the official forecast by 92% 39 mph Behind the official forecast by 550%
11 NAVGEM 24 h 52 63 mi Behind the official forecast by 70% 34 mph Behind the official forecast by 245%
11 NAVGEM 36 h 50 94 mi Behind the official forecast by 82% 32 mph Behind the official forecast by 183%
11 NAVGEM 48 h 50 131 mi Behind the official forecast by 94% 32 mph Behind the official forecast by 129%
11 NAVGEM 60 h 48 185 mi Behind the official forecast by 105% 32 mph Behind the official forecast by 93%
11 NAVGEM 72 h 46 242 mi Behind the official forecast by 118% 34 mph Behind the official forecast by 86%
11 NAVGEM 96 h 42 387 mi Behind the official forecast by 153% 37 mph Behind the official forecast by 83%
11 NAVGEM 120 h 37 540 mi Behind the official forecast by 190% 41 mph Behind the official forecast by 73%
12 Canadian GEM 12 h 30 29 mi Behind the official forecast by 47% 39 mph Behind the official forecast by 581%
12 Canadian GEM 24 h 29 60 mi Behind the official forecast by 81% 43 mph Behind the official forecast by 347%
12 Canadian GEM 36 h 28 90 mi Behind the official forecast by 79% 46 mph Behind the official forecast by 310%
12 Canadian GEM 48 h 27 130 mi Behind the official forecast by 97% 48 mph Behind the official forecast by 254%
12 Canadian GEM 60 h 26 174 mi Behind the official forecast by 96% 50 mph Behind the official forecast by 219%
12 Canadian GEM 72 h 25 217 mi Behind the official forecast by 98% 52 mph Behind the official forecast by 203%
12 Canadian GEM 96 h 23 318 mi Behind the official forecast by 126% 55 mph Behind the official forecast by 185%
12 Canadian GEM 120 h 21 424 mi Behind the official forecast by 146% 62 mph Behind the official forecast by 185%

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.

6°N 20°N 34°N 48°N 156°E 177°W 151°W 124°W
Map of Remnant Low Lowell. The best track, where the storm actually went, has 66 positions. 4 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 (66 positions)
  • NHC official Aug 27, 18:00 UTC
  • NHC official Sep 1, 12:00 UTC
  • NHC official Sep 6, 06:00 UTC
  • NHC official Sep 11, 00:00 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

18 mi 12 h 31 mi 24 h 46 mi 36 h 62 mi 48 h 84 mi 60 h 104 mi 72 h 140 mi 96 h 172 mi 120 h
Average official track miss in miles by how far ahead. 12 hours 18 miles over 56 forecasts. 24 hours 31 miles over 54 forecasts. 36 hours 46 miles over 52 forecasts. 48 hours 62 miles over 50 forecasts. 60 hours 84 miles over 48 forecasts. 72 hours 104 miles over 46 forecasts. 96 hours 140 miles over 42 forecasts. 120 hours 172 miles over 38 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 56 18 mi 6 mph 96 mph 94 mph
24 h 54 31 mi 10 mph 98 mph 96 mph
36 h 52 46 mi 12 mph 99 mph 98 mph
48 h 50 62 mi 14 mph 101 mph 100 mph
60 h 48 84 mi 17 mph 103 mph 102 mph
72 h 46 104 mi 19 mph 106 mph 104 mph
96 h 42 140 mi 21 mph 107 mph 109 mph
120 h 38 172 mi 24 mph 107 mph 113 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 60 h 72 h 96 h 120 h
Top wind, official forecast versus where the storm went. At 12 hours the forecast averaged 96 mph and where the storm actually went averaged 94 mph. At 24 hours the forecast averaged 98 mph and where the storm actually went averaged 96 mph. At 36 hours the forecast averaged 99 mph and where the storm actually went averaged 98 mph. At 48 hours the forecast averaged 101 mph and where the storm actually went averaged 100 mph. At 60 hours the forecast averaged 103 mph and where the storm actually went averaged 102 mph. At 72 hours the forecast averaged 106 mph and where the storm actually went averaged 104 mph. At 96 hours the forecast averaged 107 mph and where the storm actually went averaged 109 mph. At 120 hours the forecast averaged 107 mph and where the storm actually went averaged 113 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.