Hurricane tracks

Tropical Depression Cristina Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 8:00 PM ET Wed, Jun 10.

Tropical Depression Cristina has 18 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 3 forecasts. At 48 hours, the official wind forecast averaged 50 mph and where the storm actually went averaged 36 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.

EP032026 · 2026 · Jun 6-11, 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 1 1
2 GEFS mean 3.5 5 2
3 HMON 4.5 2 7
3 NHC official 4.5 3 6
5 HWRF 5.5 7 4
6 HAFS-A 6 9 3
7 UKMET 6.5 4 9
8 Canadian GEM 7 6 8
9 HAFS-B 7.5 10 5
10 GFS 9.5 8 11
11 NAVGEM 10.5 11 10
— WeatherNext 3 Not enough forecasts yet — —

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 5 12 mi Beats the official forecast by 46% 3 mph Beats the official forecast by 40%
1 Google DeepMind 24 h 3 43 mi Behind the official forecast by 70% 2 mph Beats the official forecast by 76%
1 Google DeepMind 36 h 1 40 mi Behind the official forecast by 44% 3 mph Beats the official forecast by 70%
2 GEFS mean 12 h 17 30 mi Behind the official forecast by 77% 7 mph Behind the official forecast by 23%
2 GEFS mean 24 h 15 52 mi Behind the official forecast by 62% 7 mph Beats the official forecast by 38%
2 GEFS mean 36 h 13 82 mi Behind the official forecast by 36% 4 mph Beats the official forecast by 71%
2 GEFS mean 48 h 11 104 mi Behind the official forecast by 17% 7 mph Beats the official forecast by 43%
2 GEFS mean 60 h 9 132 mi Behind the official forecast by 33% 9 mph Beats the official forecast by 80%
2 GEFS mean 72 h 7 168 mi — 12 mph —
2 GEFS mean 96 h 3 250 mi — 17 mph —
3 HMON 12 h 17 55 mi Behind the official forecast by 121% 12 mph Behind the official forecast by 123%
3 HMON 24 h 15 83 mi Behind the official forecast by 142% 13 mph Behind the official forecast by 40%
3 HMON 36 h 13 125 mi Behind the official forecast by 154% 9 mph Beats the official forecast by 3%
3 HMON 48 h 8 171 mi Beats the official forecast by 80% 11 mph —
3 HMON 60 h 4 358 mi — 4 mph —
3 HMON 72 h 4 520 mi — 4 mph —
3 NHC official 12 h 9 21 mi — 4 mph —
3 NHC official 24 h 7 32 mi — 8 mph —
3 NHC official 36 h 5 42 mi — 8 mph —
3 NHC official 48 h 3 62 mi — 13 mph —
3 NHC official 60 h 1 51 mi — 23 mph —
5 HWRF 12 h 17 47 mi Behind the official forecast by 121% 12 mph Behind the official forecast by 71%
5 HWRF 24 h 15 78 mi Behind the official forecast by 81% 14 mph Beats the official forecast by 10%
5 HWRF 36 h 13 130 mi Behind the official forecast by 117% 16 mph Behind the official forecast by 26%
5 HWRF 48 h 11 182 mi Behind the official forecast by 116% 12 mph Beats the official forecast by 29%
5 HWRF 60 h 9 215 mi Behind the official forecast by 228% 13 mph Beats the official forecast by 90%
5 HWRF 72 h 7 272 mi — 19 mph —
5 HWRF 96 h 3 312 mi — 14 mph —
6 HAFS-A 12 h 17 58 mi Behind the official forecast by 146% 11 mph Behind the official forecast by 20%
6 HAFS-A 24 h 15 91 mi Behind the official forecast by 170% 9 mph Behind the official forecast by 6%
6 HAFS-A 36 h 12 111 mi Behind the official forecast by 193% 8 mph Beats the official forecast by 43%
6 HAFS-A 48 h 10 145 mi Behind the official forecast by 192% 9 mph Beats the official forecast by 54%
6 HAFS-A 60 h 8 175 mi Behind the official forecast by 332% 15 mph Beats the official forecast by 50%
6 HAFS-A 72 h 7 241 mi — 15 mph —
6 HAFS-A 96 h 3 447 mi — 9 mph —
7 UKMET 12 h 9 43 mi Behind the official forecast by 122% 12 mph Behind the official forecast by 285%
7 UKMET 24 h 8 62 mi Behind the official forecast by 105% 10 mph Behind the official forecast by 112%
7 UKMET 36 h 7 82 mi Behind the official forecast by 90% 10 mph Behind the official forecast by 127%
7 UKMET 48 h 6 93 mi Beats the official forecast by 12% 10 mph Behind the official forecast by 33%
7 UKMET 60 h 5 93 mi Beats the official forecast by 44% 11 mph Beats the official forecast by 55%
7 UKMET 72 h 4 115 mi — 7 mph —
7 UKMET 96 h 2 69 mi — 7 mph —
8 Canadian GEM 12 h 9 50 mi Behind the official forecast by 155% 14 mph Behind the official forecast by 270%
8 Canadian GEM 24 h 8 52 mi Behind the official forecast by 49% 13 mph Behind the official forecast by 132%
8 Canadian GEM 36 h 5 86 mi Behind the official forecast by 164% 8 mph Beats the official forecast by 10%
8 Canadian GEM 48 h 5 130 mi Behind the official forecast by 190% 5 mph Beats the official forecast by 53%
8 Canadian GEM 60 h 5 151 mi Behind the official forecast by 178% 9 mph Beats the official forecast by 60%
8 Canadian GEM 72 h 4 146 mi — 8 mph —
8 Canadian GEM 96 h 2 103 mi — 11 mph —
9 HAFS-B 12 h 17 63 mi Behind the official forecast by 189% 13 mph Behind the official forecast by 60%
9 HAFS-B 24 h 15 84 mi Behind the official forecast by 204% 13 mph Ties the official forecast
9 HAFS-B 36 h 13 97 mi Behind the official forecast by 153% 12 mph Behind the official forecast by 20%
9 HAFS-B 48 h 11 143 mi Behind the official forecast by 232% 9 mph Beats the official forecast by 23%
9 HAFS-B 60 h 9 179 mi Behind the official forecast by 365% 9 mph Beats the official forecast by 30%
9 HAFS-B 72 h 7 250 mi — 3 mph —
9 HAFS-B 96 h 3 452 mi — 13 mph —
10 GFS 12 h 17 48 mi Behind the official forecast by 133% 12 mph Behind the official forecast by 160%
10 GFS 24 h 15 83 mi Behind the official forecast by 114% 12 mph Behind the official forecast by 68%
10 GFS 36 h 13 108 mi Behind the official forecast by 111% 16 mph Behind the official forecast by 243%
10 GFS 48 h 11 139 mi Behind the official forecast by 105% 17 mph Behind the official forecast by 126%
10 GFS 60 h 9 136 mi Behind the official forecast by 116% 18 mph Behind the official forecast by 35%
10 GFS 72 h 7 167 mi — 25 mph —
10 GFS 96 h 3 201 mi — 43 mph —
11 NAVGEM 12 h 14 111 mi Behind the official forecast by 620% 11 mph Behind the official forecast by 513%
11 NAVGEM 24 h 12 153 mi Behind the official forecast by 538% 9 mph Behind the official forecast by 160%
11 NAVGEM 36 h 12 197 mi Behind the official forecast by 547% 9 mph Behind the official forecast by 15%
11 NAVGEM 48 h 10 221 mi Behind the official forecast by 406% 17 mph Behind the official forecast by 40%
11 NAVGEM 60 h 9 234 mi Behind the official forecast by 385% 28 mph Behind the official forecast by 45%
11 NAVGEM 72 h 7 215 mi — 33 mph —
11 NAVGEM 96 h 3 125 mi — 52 mph —
— WeatherNext 3 12 h 3 7 mi Beats the official forecast by 72% 2 mph Beats the official forecast by 80%
— WeatherNext 3 24 h 2 42 mi Behind the official forecast by 37% 3 mph Beats the official forecast by 70%
— WeatherNext 3 36 h 1 56 mi Behind the official forecast by 100% 3 mph Beats the official forecast by 70%

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 15°N 24°N 32°N 103°W 96°W 90°W 84°W
Map of Tropical Depression Cristina. The best track, where the storm actually went, has 18 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 (18 positions)
  • NHC official Jun 8, 12:00 UTC
  • NHC official Jun 9, 00:00 UTC
  • NHC official Jun 9, 12:00 UTC
  • NHC official Jun 10, 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

21 mi 12 h 32 mi 24 h 42 mi 36 h 62 mi 48 h 51 mi 60 h
Average official track miss in miles by how far ahead. 12 hours 21 miles over 9 forecasts. 24 hours 32 miles over 7 forecasts. 36 hours 42 miles over 5 forecasts. 48 hours 62 miles over 3 forecasts. 60 hours 51 miles over 1 forecast.
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 9 21 mi 4 mph 44 mph 40 mph
24 h 7 32 mi 8 mph 45 mph 39 mph
36 h 5 42 mi 8 mph 44 mph 38 mph
48 h 3 62 mi 13 mph 50 mph 36 mph
60 h 1 51 mi 23 mph 58 mph 35 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.

Top wind

12 h 24 h 36 h 48 h 60 h
Top wind, official forecast versus where the storm went. At 12 hours the forecast averaged 44 mph and where the storm actually went averaged 40 mph. At 24 hours the forecast averaged 45 mph and where the storm actually went averaged 39 mph. At 36 hours the forecast averaged 44 mph and where the storm actually went averaged 38 mph. At 48 hours the forecast averaged 50 mph and where the storm actually went averaged 36 mph. At 60 hours the forecast averaged 58 mph and where the storm actually went averaged 35 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.