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 6

KMIA · gfs · lead 6

Target day = initialization date + 6 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
tmax00Zbilinear30d24 2 QC2.71 [1.73, 3.60]1.48-2.54 [-3.57, -1.16]3.23 [2.12, 4.11]21% [0%, 44%]38%71%-0.10+0.402026-08-07 → 2026-08-30
tmax00Zbilinear90d24 2 QC2.71 [1.49, 3.59]1.48-2.54 [-3.57, -0.71]3.23 [1.77, 4.12]21% [0%, 46%]38%71%-0.10+0.402026-08-07 → 2026-08-30
tmax00Zbilinear365d24 2 QC2.71 [1.19, 3.74]1.48-2.54 [-3.74, -0.48]3.23 [1.33, 4.33]21% [0%, 50%]38%71%-0.10+0.402026-08-07 → 2026-08-30
tmax00Zbilinearall24 2 QC2.71 [1.40, 3.72]1.48-2.54 [-3.72, -0.55]3.23 [1.70, 4.23]21% [0%, 50%]38%71%-0.10+0.402026-08-07 → 2026-08-30
tmax00Znearest30d24 2 QC4.50 [3.03, 5.54]1.51-4.50 [-5.54, -3.03]4.92 [3.49, 5.92]4% [0%, 14%]8%21%-0.83+0.392026-08-07 → 2026-08-30
tmax00Znearest90d24 2 QC4.50 [2.58, 5.59]1.51-4.50 [-5.59, -2.58]4.92 [2.90, 5.95]4% [0%, 17%]8%21%-0.83+0.392026-08-07 → 2026-08-30
tmax00Znearest365d24 2 QC4.50 [2.43, 5.77]1.51-4.50 [-5.77, -2.43]4.92 [2.72, 6.13]4% [0%, 17%]8%21%-0.83+0.392026-08-07 → 2026-08-30
tmax00Znearestall24 2 QC4.50 [2.36, 5.69]1.51-4.50 [-5.69, -2.36]4.92 [2.74, 6.02]4% [0%, 17%]8%21%-0.83+0.392026-08-07 → 2026-08-30
tmax12Zbilinear30d24 2 QC2.58 [1.54, 3.48]1.27-2.51 [-3.48, -1.35]3.11 [1.88, 4.07]21% [0%, 44%]33%75%-0.05+0.482026-08-07 → 2026-08-30
tmax12Zbilinear90d24 2 QC2.58 [1.39, 3.43]1.27-2.51 [-3.43, -1.02]3.11 [1.63, 4.01]21% [0%, 50%]33%75%-0.05+0.482026-08-07 → 2026-08-30
tmax12Zbilinear365d24 2 QC2.58 [1.20, 3.57]1.27-2.51 [-3.57, -0.90]3.11 [1.51, 4.20]21% [0%, 53%]33%75%-0.05+0.482026-08-07 → 2026-08-30
tmax12Zbilinearall24 2 QC2.58 [1.16, 3.47]1.27-2.51 [-3.47, -0.86]3.11 [1.43, 4.16]21% [0%, 50%]33%75%-0.05+0.482026-08-07 → 2026-08-30
tmax12Znearest30d24 2 QC4.56 [3.26, 5.60]1.31-4.56 [-5.60, -3.26]4.93 [3.57, 6.00]0% [0%, 0%]8%17%-0.85+0.472026-08-07 → 2026-08-30
tmax12Znearest90d24 2 QC4.56 [2.85, 5.59]1.31-4.56 [-5.59, -2.85]4.93 [3.10, 5.97]0% [0%, 0%]8%17%-0.85+0.472026-08-07 → 2026-08-30
tmax12Znearest365d24 2 QC4.56 [2.81, 5.77]1.31-4.56 [-5.77, -2.81]4.93 [3.03, 6.21]0% [0%, 0%]8%17%-0.85+0.472026-08-07 → 2026-08-30
tmax12Znearestall24 2 QC4.56 [2.77, 5.68]1.31-4.56 [-5.68, -2.77]4.93 [3.02, 6.10]0% [0%, 0%]8%17%-0.85+0.472026-08-07 → 2026-08-30
tmin00Zbilinear30d24 2 QC4.68 [3.33, 6.04]1.74+4.68 [3.33, 6.04]5.16 [3.83, 6.28]4% [0%, 12%]12%29%-0.52+0.462026-08-07 → 2026-08-30
tmin00Zbilinear90d24 2 QC4.68 [3.06, 6.18]1.74+4.68 [3.06, 6.18]5.16 [3.50, 6.36]4% [0%, 14%]12%29%-0.52+0.462026-08-07 → 2026-08-30
tmin00Zbilinear365d24 2 QC4.68 [3.01, 6.40]1.74+4.68 [3.01, 6.40]5.16 [3.47, 6.66]4% [0%, 14%]12%29%-0.52+0.462026-08-07 → 2026-08-30
tmin00Zbilinearall24 2 QC4.68 [3.06, 6.21]1.74+4.68 [3.06, 6.21]5.16 [3.48, 6.44]4% [0%, 14%]12%29%-0.52+0.462026-08-07 → 2026-08-30
tmin00Znearest30d24 2 QC4.91 [3.48, 6.31]1.78+4.91 [3.48, 6.31]5.39 [3.97, 6.57]4% [0%, 12%]12%21%-0.59+0.442026-08-07 → 2026-08-30
tmin00Znearest90d24 2 QC4.91 [3.15, 6.41]1.78+4.91 [3.15, 6.41]5.39 [3.62, 6.61]4% [0%, 14%]12%21%-0.59+0.442026-08-07 → 2026-08-30
tmin00Znearest365d24 2 QC4.91 [3.10, 6.61]1.78+4.91 [3.10, 6.61]5.39 [3.55, 6.87]4% [0%, 14%]12%21%-0.59+0.442026-08-07 → 2026-08-30
tmin00Znearestall24 2 QC4.91 [3.15, 6.45]1.78+4.91 [3.15, 6.45]5.39 [3.57, 6.69]4% [0%, 14%]12%21%-0.59+0.442026-08-07 → 2026-08-30
tmin12Zbilinear30d24 2 QC4.30 [3.06, 5.70]1.80+4.30 [3.06, 5.70]4.86 [3.64, 5.99]12% [0%, 27%]17%33%-0.39+0.442026-08-07 → 2026-08-30
tmin12Zbilinear90d24 2 QC4.30 [2.86, 5.95]1.80+4.30 [2.86, 5.95]4.86 [3.44, 6.20]12% [0%, 30%]17%33%-0.39+0.442026-08-07 → 2026-08-30
tmin12Zbilinear365d24 2 QC4.30 [2.83, 6.18]1.80+4.30 [2.83, 6.18]4.86 [3.38, 6.39]12% [0%, 29%]17%33%-0.39+0.442026-08-07 → 2026-08-30
tmin12Zbilinearall24 2 QC4.30 [2.85, 5.97]1.80+4.30 [2.85, 5.97]4.86 [3.44, 6.21]12% [0%, 29%]17%33%-0.39+0.442026-08-07 → 2026-08-30
tmin12Znearest30d24 2 QC4.54 [3.22, 5.97]1.82+4.54 [3.22, 5.97]5.07 [3.75, 6.24]8% [0%, 24%]12%25%-0.47+0.432026-08-07 → 2026-08-30
tmin12Znearest90d24 2 QC4.54 [3.02, 6.17]1.82+4.54 [3.02, 6.17]5.07 [3.54, 6.39]8% [0%, 30%]12%25%-0.47+0.432026-08-07 → 2026-08-30
tmin12Znearest365d24 2 QC4.54 [2.94, 6.40]1.82+4.54 [2.94, 6.40]5.07 [3.46, 6.61]8% [0%, 27%]12%25%-0.47+0.432026-08-07 → 2026-08-30
tmin12Znearestall24 2 QC4.54 [3.04, 6.23]1.82+4.54 [3.04, 6.23]5.07 [3.52, 6.44]8% [0%, 29%]12%25%-0.47+0.432026-08-07 → 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 6, 00Z bilinear tmax+10+50-5-102026-08-07: -4.15 °F2026-08-08: -2.57 °F2026-08-09: -1.59 °F2026-08-10: -2.83 °F2026-08-11: -3.84 °F2026-08-12: -2.88 °F2026-08-13: -2.73 °F2026-08-14: -4.6 °F2026-08-15: -2.9 °F2026-08-16: -2.44 °F2026-08-17: -2.5 °F2026-08-18: -8.22 °F2026-08-19: -4.73 °F2026-08-20: -0.72 °F2026-08-21: -2.52 °F2026-08-22: -5.03 °F2026-08-23: -3.71 °F2026-08-24: -0.78 °F2026-08-25: -0.78 °F2026-08-26: -0.81 °F2026-08-27: -1.67 °F2026-08-28: -1.05 °F2026-08-29: +1.22 °F2026-08-30: +0.86 °F2026-08-072026-08-30°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 (24 days, newest first) · download CSV
Climatological dayError °F
2026-08-30+0.86
2026-08-29+1.22
2026-08-28-1.05
2026-08-27-1.67
2026-08-26-0.81
2026-08-25-0.78
2026-08-24-0.78
2026-08-23-3.71
2026-08-22-5.03
2026-08-21-2.52
2026-08-20-0.72
2026-08-19-4.73
2026-08-18-8.22
2026-08-17-2.50
2026-08-16-2.44
2026-08-15-2.90
2026-08-14-4.60
2026-08-13-2.73
2026-08-12-2.88
2026-08-11-3.84
2026-08-10-2.83
2026-08-09-1.59
2026-08-08-2.57
2026-08-07-4.15

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KMIA, lead day 6-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 1 day-5 to -4 °F: 3 days-4 to -3 °F: 2 days-3 to -2 °F: 8 days-2 to -1 °F: 3 days-1 to 0 °F: 4 days0 to 1 °F: 1 day1 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| 2.55 · P90 |e| 4.69 °F-100+10 °Fn = 24 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
-10.00-9.000
-9.00-8.001
-8.00-7.000
-7.00-6.000
-6.00-5.001
-5.00-4.003
-4.00-3.002
-3.00-2.008
-2.00-1.003
-1.00+0.004
+0.00+1.001
+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
2026-08242.71 -2.54

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-07 → 2026-08-30 24
NCEP GFS2026-08-07 → 2026-08-30 24
NCEP GFS2026-08-07 → 2026-08-30 24
NCEP GFS2026-08-07 → 2026-08-30 24

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 24 -1.72 [-3.32, -0.72] yes
GraphCast (IFS init) 24 -2.40 [-4.77, -1.08] yes
ECMWF IFS HRES 19 -1.25 [-4.13, 1.18] no
Persistence (baseline) 24 +0.25 [-0.75, 1.31] no

Cite this page

ShortCastCheck, KMIA gfs lead 6, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/gfs/lead/6/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model gfs, lead day 6. 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/6/

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