Raw model output on the native 0.25° grid — no MOS, no bias correction, no post-processing. Scores understate operational forecast quality. Read the fairness statement →

CastCheck methodology v0.2 · data through 2026-08-30

Miami Intl · NCEP GFS · lead day 5

KMIA · gfs · lead 5

Target day = initialization date + 5 days. This page is a permanent link: the numbers change as history accumulates, the address and the methodology version do not.

Scores use the latest model version segment, gfs-0p25, starting 2026-08-01 — days before that ran a different version of the model and are excluded rather than silently pooled. Of the scored days, 2 carry a QC flag on the observation.

JSON for this page CSV of the daily errors Cite this page

Every number for this combination

All four windows × both initializations × both interpolations × both variables. Errors are computed in °C and shown in °F; CI is a 95 % moving-block bootstrap interval. MAE debiased and skill, debiased remove the constant offset of the window first, so a station that the model always reads a degree too warm is not scored as if it had no skill — compare the two skill columns to see how much of the error is a fixed offset. n QC next to n counts days whose observation carries a QC flag.

VariableInitMethod Windown MAE °F MAE debiased Bias °F RMSE °F ±1 °F±2 °F±3 °F Skill Skill, debiased Period
tmax00Zbilinear30d25 2 QC2.17 [1.40, 2.84]1.48-1.92 [-2.75, -0.75]2.84 [1.60, 3.86]24% [12%, 44%]52%80%-0.06+0.282026-08-06 → 2026-08-30
tmax00Zbilinear90d25 2 QC2.17 [1.16, 2.82]1.48-1.92 [-2.79, -0.31]2.84 [1.19, 3.79]24% [11%, 46%]52%80%-0.06+0.282026-08-06 → 2026-08-30
tmax00Zbilinear365d25 2 QC2.17 [1.15, 2.89]1.48-1.92 [-2.87, -0.23]2.84 [1.18, 3.96]24% [11%, 47%]52%80%-0.06+0.282026-08-06 → 2026-08-30
tmax00Zbilinearall25 2 QC2.17 [1.11, 2.87]1.48-1.92 [-2.84, -0.16]2.84 [1.15, 3.84]24% [11%, 55%]52%80%-0.06+0.282026-08-06 → 2026-08-30
tmax00Znearest30d25 2 QC3.75 [2.39, 4.70]1.60-3.75 [-4.70, -2.39]4.35 [2.92, 5.37]12% [0%, 35%]16%36%-0.84+0.222026-08-06 → 2026-08-30
tmax00Znearest90d25 2 QC3.75 [1.94, 4.74]1.60-3.75 [-4.74, -1.94]4.35 [2.38, 5.38]12% [0%, 44%]16%36%-0.84+0.222026-08-06 → 2026-08-30
tmax00Znearest365d25 2 QC3.75 [1.95, 4.83]1.60-3.75 [-4.83, -1.95]4.35 [2.37, 5.47]12% [0%, 44%]16%36%-0.84+0.222026-08-06 → 2026-08-30
tmax00Znearestall25 2 QC3.75 [1.76, 4.81]1.60-3.75 [-4.81, -1.76]4.35 [2.21, 5.43]12% [0%, 50%]16%36%-0.84+0.222026-08-06 → 2026-08-30
tmax12Zbilinear30d25 2 QC2.38 [1.67, 3.04]1.28-2.08 [-2.92, -1.01]2.78 [1.85, 3.52]16% [0%, 35%]44%84%-0.17+0.382026-08-06 → 2026-08-30
tmax12Zbilinear90d25 2 QC2.38 [1.56, 3.02]1.28-2.08 [-2.89, -0.63]2.78 [1.76, 3.45]16% [0%, 39%]44%84%-0.17+0.382026-08-06 → 2026-08-30
tmax12Zbilinear365d25 2 QC2.38 [1.44, 3.07]1.28-2.08 [-2.99, -0.61]2.78 [1.62, 3.57]16% [0%, 43%]44%84%-0.17+0.382026-08-06 → 2026-08-30
tmax12Zbilinearall25 2 QC2.38 [1.45, 3.07]1.28-2.08 [-2.96, -0.61]2.78 [1.68, 3.48]16% [0%, 43%]44%84%-0.17+0.382026-08-06 → 2026-08-30
tmax12Znearest30d25 2 QC4.00 [2.79, 4.92]1.37-3.96 [-4.92, -2.68]4.42 [3.17, 5.32]8% [0%, 22%]12%20%-0.96+0.332026-08-06 → 2026-08-30
tmax12Znearest90d25 2 QC4.00 [2.44, 4.91]1.37-3.96 [-4.90, -2.29]4.42 [2.80, 5.27]8% [0%, 27%]12%20%-0.96+0.332026-08-06 → 2026-08-30
tmax12Znearest365d25 2 QC4.00 [2.35, 5.05]1.37-3.96 [-5.05, -2.28]4.42 [2.82, 5.37]8% [0%, 25%]12%20%-0.96+0.332026-08-06 → 2026-08-30
tmax12Znearestall25 2 QC4.00 [2.30, 4.99]1.37-3.96 [-4.98, -2.19]4.42 [2.73, 5.31]8% [0%, 29%]12%20%-0.96+0.332026-08-06 → 2026-08-30
tmin00Zbilinear30d25 2 QC4.80 [3.78, 6.14]1.85+4.80 [3.78, 6.14]5.29 [4.30, 6.42]4% [0%, 12%]8%28%-0.82+0.312026-08-06 → 2026-08-30
tmin00Zbilinear90d25 2 QC4.80 [3.65, 6.44]1.85+4.80 [3.65, 6.44]5.29 [4.19, 6.74]4% [0%, 12%]8%28%-0.82+0.312026-08-06 → 2026-08-30
tmin00Zbilinear365d25 2 QC4.80 [3.64, 6.68]1.85+4.80 [3.64, 6.68]5.29 [4.16, 6.85]4% [0%, 12%]8%28%-0.82+0.312026-08-06 → 2026-08-30
tmin00Zbilinearall25 2 QC4.80 [3.59, 6.62]1.85+4.80 [3.59, 6.62]5.29 [4.16, 6.81]4% [0%, 13%]8%28%-0.82+0.312026-08-06 → 2026-08-30
tmin00Znearest30d25 2 QC5.05 [3.98, 6.40]1.89+5.05 [3.98, 6.40]5.55 [4.53, 6.69]4% [0%, 12%]8%24%-0.91+0.302026-08-06 → 2026-08-30
tmin00Znearest90d25 2 QC5.05 [3.85, 6.71]1.89+5.05 [3.85, 6.71]5.55 [4.42, 7.00]4% [0%, 12%]8%24%-0.91+0.302026-08-06 → 2026-08-30
tmin00Znearest365d25 2 QC5.05 [3.82, 6.93]1.89+5.05 [3.82, 6.93]5.55 [4.37, 7.10]4% [0%, 12%]8%24%-0.91+0.302026-08-06 → 2026-08-30
tmin00Znearestall25 2 QC5.05 [3.79, 6.84]1.89+5.05 [3.79, 6.84]5.55 [4.37, 7.04]4% [0%, 13%]8%24%-0.91+0.302026-08-06 → 2026-08-30
tmin12Zbilinear30d25 2 QC4.45 [3.49, 5.78]1.93+4.45 [3.49, 5.78]5.06 [4.09, 6.22]4% [0%, 12%]12%36%-0.69+0.292026-08-06 → 2026-08-30
tmin12Zbilinear90d25 2 QC4.45 [3.39, 6.19]1.93+4.45 [3.39, 6.19]5.06 [4.01, 6.47]4% [0%, 12%]12%36%-0.69+0.292026-08-06 → 2026-08-30
tmin12Zbilinear365d25 2 QC4.45 [3.36, 6.32]1.93+4.45 [3.36, 6.32]5.06 [3.95, 6.52]4% [0%, 12%]12%36%-0.69+0.292026-08-06 → 2026-08-30
tmin12Zbilinearall25 2 QC4.45 [3.36, 6.28]1.93+4.45 [3.36, 6.28]5.06 [3.96, 6.54]4% [0%, 13%]12%36%-0.69+0.292026-08-06 → 2026-08-30
tmin12Znearest30d25 2 QC4.64 [3.65, 5.94]1.94+4.64 [3.65, 5.94]5.23 [4.30, 6.36]4% [0%, 12%]12%32%-0.76+0.282026-08-06 → 2026-08-30
tmin12Znearest90d25 2 QC4.64 [3.57, 6.30]1.94+4.64 [3.57, 6.30]5.23 [4.24, 6.59]4% [0%, 12%]12%32%-0.76+0.282026-08-06 → 2026-08-30
tmin12Znearest365d25 2 QC4.64 [3.54, 6.44]1.94+4.64 [3.54, 6.44]5.23 [4.15, 6.65]4% [0%, 12%]12%32%-0.76+0.282026-08-06 → 2026-08-30
tmin12Znearestall25 2 QC4.64 [3.54, 6.43]1.94+4.64 [3.54, 6.43]5.23 [4.15, 6.65]4% [0%, 13%]12%32%-0.76+0.282026-08-06 → 2026-08-30

+ model too warm · − model too cold · bias interval includes zero · ★ lowest MAE · = not distinguishable from the leader · ▼ significantly worse · n < 30 greyed and unranked · CI is a 95 % moving-block bootstrap interval.

Daily error, last 90 days

Daily forecast minus observed error in °F for NCEP GFS at KMIA, lead day 5, 00Z bilinear tmax+10+50-5-102026-08-06: +0.9 °F2026-08-07: -0.83 °F2026-08-08: -1.61 °F2026-08-09: -2.18 °F2026-08-10: -2.64 °F2026-08-11: -3.09 °F2026-08-12: -2.69 °F2026-08-13: -2.68 °F2026-08-14: -4.3 °F2026-08-15: -2.57 °F2026-08-16: -2.22 °F2026-08-17: -0.26 °F2026-08-18: -9.44 °F2026-08-19: -1.31 °F2026-08-20: +0.08 °F2026-08-21: -3.01 °F2026-08-22: -2.99 °F2026-08-23: -3.73 °F2026-08-24: -0.39 °F2026-08-25: -1.19 °F2026-08-26: -1.48 °F2026-08-27: -1.24 °F2026-08-28: -1.22 °F2026-08-29: +1.34 °F2026-08-30: +0.84 °F2026-08-062026-08-30°F, forecast − observed
Forecast − observed, °F, 00Z bilinear daily maximum. The dashed line is zero; the thick line is a centred 7-day mean, drawn only where the whole window is present. Gaps are days with no score, never interpolation. Hover a point for its date and value.
The same series as a table (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30+0.84
2026-08-29+1.34
2026-08-28-1.22
2026-08-27-1.24
2026-08-26-1.48
2026-08-25-1.19
2026-08-24-0.39
2026-08-23-3.73
2026-08-22-2.99
2026-08-21-3.01
2026-08-20+0.08
2026-08-19-1.31
2026-08-18-9.44
2026-08-17-0.26
2026-08-16-2.22
2026-08-15-2.57
2026-08-14-4.30
2026-08-13-2.68
2026-08-12-2.69
2026-08-11-3.09
2026-08-10-2.64
2026-08-09-2.18
2026-08-08-1.61
2026-08-07-0.83
2026-08-06+0.90

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KMIA, lead day 5-10 to -9 °F: 1 day-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 0 days-5 to -4 °F: 1 day-4 to -3 °F: 3 days-3 to -2 °F: 7 days-2 to -1 °F: 6 days-1 to 0 °F: 3 days0 to 1 °F: 3 days1 to 2 °F: 1 day2 to 3 °F: 0 days3 to 4 °F: 0 days4 to 5 °F: 0 days5 to 6 °F: 0 days6 to 7 °F: 0 days7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 1.61 · P90 |e| 3.47 °F-100+10 °Fn = 25 days
All scored days for 00Z bilinear daily maximum, 20 equal bins. The dashed marks are the 50th and 90th percentiles of the absolute error, mirrored on both sides. Hover a bar for its bin and count.
Bin counts as a table
From °FTo °FDays
-10.00-9.001
-9.00-8.000
-8.00-7.000
-7.00-6.000
-6.00-5.000
-5.00-4.001
-4.00-3.003
-3.00-2.007
-2.00-1.006
-1.00+0.003
+0.00+1.003
+1.00+2.001
+2.00+3.000
+3.00+4.000
+4.00+5.000
+5.00+6.000
+6.00+7.000
+7.00+8.000
+8.00+9.000
+9.00+10.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08252.17 -1.92

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-06 → 2026-08-30 25
NCEP GFS2026-08-06 → 2026-08-30 25
NCEP GFS2026-08-06 → 2026-08-30 25
NCEP GFS2026-08-06 → 2026-08-30 25

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means NCEP GFS has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 25 -2.35 [-3.69, -1.56] yes
GraphCast (IFS init) 25 -2.86 [-5.01, -1.61] yes
ECMWF IFS HRES 18 -2.15 [-4.25, -0.79] yes
Persistence (baseline) 25 +0.13 [-0.84, 1.02] no

Cite this page

ShortCastCheck, KMIA gfs lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/gfs/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model gfs, lead day 5. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KMIA/model/gfs/lead/5/

Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)

JSON CSV all scores methodology v0.2 licence