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 7

KMIA · gfs · lead 7

Target day = initialization date + 7 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
tmax00Zbilinear30d23 2 QC2.76 [1.82, 3.39]1.22-2.67 [-3.39, -1.56]3.11 [2.29, 3.59]4% [0%, 17%]35%61%-0.04+0.542026-08-08 → 2026-08-30
tmax00Zbilinear90d23 2 QC2.76 [1.45, 3.41]1.22-2.67 [-3.41, -1.01]3.11 [1.80, 3.60]4% [0%, 20%]35%61%-0.04+0.542026-08-08 → 2026-08-30
tmax00Zbilinear365d23 2 QC2.76 [1.30, 3.44]1.22-2.67 [-3.44, -0.96]3.11 [1.49, 3.64]4% [0%, 20%]35%61%-0.04+0.542026-08-08 → 2026-08-30
tmax00Zbilinearall23 2 QC2.76 [1.24, 3.43]1.22-2.67 [-3.43, -0.90]3.11 [1.47, 3.60]4% [0%, 25%]35%61%-0.04+0.542026-08-08 → 2026-08-30
tmax00Znearest30d23 2 QC4.52 [3.36, 5.31]1.11-4.52 [-5.31, -3.36]4.76 [3.67, 5.42]0% [0%, 0%]9%13%-0.70+0.582026-08-08 → 2026-08-30
tmax00Znearest90d23 2 QC4.52 [2.88, 5.33]1.11-4.52 [-5.33, -2.88]4.76 [3.12, 5.43]0% [0%, 0%]9%13%-0.70+0.582026-08-08 → 2026-08-30
tmax00Znearest365d23 2 QC4.52 [2.87, 5.41]1.11-4.52 [-5.41, -2.87]4.76 [3.11, 5.49]0% [0%, 0%]9%13%-0.70+0.582026-08-08 → 2026-08-30
tmax00Znearestall23 2 QC4.52 [2.78, 5.39]1.11-4.52 [-5.39, -2.78]4.76 [3.05, 5.49]0% [0%, 0%]9%13%-0.70+0.582026-08-08 → 2026-08-30
tmax12Zbilinear30d23 2 QC2.79 [1.55, 3.77]1.25-2.73 [-3.77, -1.38]3.17 [1.88, 4.00]13% [0%, 36%]30%57%-0.05+0.532026-08-08 → 2026-08-30
tmax12Zbilinear90d23 2 QC2.79 [1.13, 3.72]1.25-2.73 [-3.72, -0.94]3.17 [1.39, 3.98]13% [0%, 46%]30%57%-0.05+0.532026-08-08 → 2026-08-30
tmax12Zbilinear365d23 2 QC2.79 [1.09, 3.89]1.25-2.73 [-3.89, -0.88]3.17 [1.29, 4.11]13% [0%, 45%]30%57%-0.05+0.532026-08-08 → 2026-08-30
tmax12Zbilinearall23 2 QC2.79 [1.00, 3.85]1.25-2.73 [-3.85, -0.75]3.17 [1.19, 4.08]13% [0%, 50%]30%57%-0.05+0.532026-08-08 → 2026-08-30
tmax12Znearest30d23 2 QC4.79 [3.32, 5.89]1.37-4.79 [-5.89, -3.32]5.09 [3.62, 6.06]0% [0%, 0%]9%9%-0.81+0.492026-08-08 → 2026-08-30
tmax12Znearest90d23 2 QC4.79 [2.83, 5.86]1.37-4.79 [-5.86, -2.83]5.09 [3.05, 6.05]0% [0%, 0%]9%9%-0.81+0.492026-08-08 → 2026-08-30
tmax12Znearest365d23 2 QC4.79 [2.82, 6.09]1.37-4.79 [-6.09, -2.82]5.09 [3.02, 6.23]0% [0%, 0%]9%9%-0.81+0.492026-08-08 → 2026-08-30
tmax12Znearestall23 2 QC4.79 [2.70, 6.01]1.37-4.79 [-6.01, -2.70]5.09 [2.90, 6.13]0% [0%, 0%]9%9%-0.81+0.492026-08-08 → 2026-08-30
tmin00Zbilinear30d23 2 QC4.76 [3.24, 6.21]1.90+4.76 [3.24, 6.21]5.28 [3.76, 6.48]4% [0%, 14%]13%30%-0.61+0.372026-08-08 → 2026-08-30
tmin00Zbilinear90d23 2 QC4.76 [2.86, 6.42]1.90+4.76 [2.86, 6.42]5.28 [3.36, 6.65]4% [0%, 16%]13%30%-0.61+0.372026-08-08 → 2026-08-30
tmin00Zbilinear365d23 2 QC4.76 [2.86, 6.56]1.90+4.76 [2.86, 6.56]5.28 [3.29, 6.86]4% [0%, 15%]13%30%-0.61+0.372026-08-08 → 2026-08-30
tmin00Zbilinearall23 2 QC4.76 [2.84, 6.47]1.90+4.76 [2.84, 6.47]5.28 [3.29, 6.77]4% [0%, 17%]13%30%-0.61+0.372026-08-08 → 2026-08-30
tmin00Znearest30d23 2 QC4.91 [3.43, 6.29]1.82+4.91 [3.43, 6.29]5.39 [3.90, 6.58]0% [0%, 0%]9%30%-0.66+0.402026-08-08 → 2026-08-30
tmin00Znearest90d23 2 QC4.91 [3.10, 6.48]1.82+4.91 [3.10, 6.48]5.39 [3.54, 6.78]0% [0%, 0%]9%30%-0.66+0.402026-08-08 → 2026-08-30
tmin00Znearest365d23 2 QC4.91 [3.10, 6.71]1.82+4.91 [3.10, 6.71]5.39 [3.49, 6.97]0% [0%, 0%]9%30%-0.66+0.402026-08-08 → 2026-08-30
tmin00Znearestall23 2 QC4.91 [3.06, 6.56]1.82+4.91 [3.06, 6.56]5.39 [3.47, 6.91]0% [0%, 0%]9%30%-0.66+0.402026-08-08 → 2026-08-30
tmin12Zbilinear30d23 2 QC4.31 [2.96, 5.64]1.75+4.31 [2.96, 5.64]4.81 [3.50, 5.94]4% [0%, 14%]17%35%-0.46+0.422026-08-08 → 2026-08-30
tmin12Zbilinear90d23 2 QC4.31 [2.65, 5.85]1.75+4.31 [2.65, 5.85]4.81 [3.17, 6.20]4% [0%, 16%]17%35%-0.46+0.422026-08-08 → 2026-08-30
tmin12Zbilinear365d23 2 QC4.31 [2.69, 6.08]1.75+4.31 [2.69, 6.08]4.81 [3.18, 6.34]4% [0%, 15%]17%35%-0.46+0.422026-08-08 → 2026-08-30
tmin12Zbilinearall23 2 QC4.31 [2.64, 5.91]1.75+4.31 [2.64, 5.91]4.81 [3.16, 6.30]4% [0%, 17%]17%35%-0.46+0.422026-08-08 → 2026-08-30
tmin12Znearest30d23 2 QC4.47 [3.10, 5.78]1.77+4.47 [3.10, 5.78]4.96 [3.63, 6.06]4% [0%, 14%]13%30%-0.51+0.422026-08-08 → 2026-08-30
tmin12Znearest90d23 2 QC4.47 [2.73, 5.95]1.77+4.47 [2.73, 5.95]4.96 [3.23, 6.30]4% [0%, 16%]13%30%-0.51+0.422026-08-08 → 2026-08-30
tmin12Znearest365d23 2 QC4.47 [2.79, 6.17]1.77+4.47 [2.79, 6.17]4.96 [3.28, 6.44]4% [0%, 15%]13%30%-0.51+0.422026-08-08 → 2026-08-30
tmin12Znearestall23 2 QC4.47 [2.75, 6.03]1.77+4.47 [2.75, 6.03]4.96 [3.23, 6.33]4% [0%, 17%]13%30%-0.51+0.422026-08-08 → 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 7, 00Z bilinear tmax+10+50-5-102026-08-08: -2.98 °F2026-08-09: -3.29 °F2026-08-10: -3.18 °F2026-08-11: -3.82 °F2026-08-12: -3.57 °F2026-08-13: -2.37 °F2026-08-14: -4.86 °F2026-08-15: -2.65 °F2026-08-16: -2.88 °F2026-08-17: -3.31 °F2026-08-18: -4.4 °F2026-08-19: -4.36 °F2026-08-20: -1.62 °F2026-08-21: -1.92 °F2026-08-22: -2.85 °F2026-08-23: -6.55 °F2026-08-24: -1.01 °F2026-08-25: -1.16 °F2026-08-26: -1.95 °F2026-08-27: -1.42 °F2026-08-28: -2.19 °F2026-08-29: +1.01 °F2026-08-30: -0.01 °F2026-08-082026-08-30°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 (23 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.01
2026-08-29+1.01
2026-08-28-2.19
2026-08-27-1.42
2026-08-26-1.95
2026-08-25-1.16
2026-08-24-1.01
2026-08-23-6.55
2026-08-22-2.85
2026-08-21-1.92
2026-08-20-1.62
2026-08-19-4.36
2026-08-18-4.40
2026-08-17-3.31
2026-08-16-2.88
2026-08-15-2.65
2026-08-14-4.86
2026-08-13-2.37
2026-08-12-3.57
2026-08-11-3.82
2026-08-10-3.18
2026-08-09-3.29
2026-08-08-2.98

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KMIA, lead day 7-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 1 day-6 to -5 °F: 0 days-5 to -4 °F: 3 days-4 to -3 °F: 5 days-3 to -2 °F: 6 days-2 to -1 °F: 6 days-1 to 0 °F: 1 day0 to 1 °F: 0 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| 2.85 · P90 |e| 4.4 °F-100+10 °Fn = 23 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
-9.00-8.000
-8.00-7.000
-7.00-6.001
-6.00-5.000
-5.00-4.003
-4.00-3.005
-3.00-2.006
-2.00-1.006
-1.00+0.001
+0.00+1.000
+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
2026-08232.76 -2.67

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-08 → 2026-08-30 23
NCEP GFS2026-08-08 → 2026-08-30 23
NCEP GFS2026-08-08 → 2026-08-30 23
NCEP GFS2026-08-08 → 2026-08-30 23

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 23 -1.51 [-2.87, -0.76] yes
GraphCast (IFS init) 23 -2.47 [-4.87, -0.87] yes
ECMWF IFS HRES 18 -1.07 [-2.97, 0.22] no
Persistence (baseline) 23 +0.10 [-1.09, 1.29] no

Cite this page

ShortCastCheck, KMIA gfs lead 7, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/gfs/lead/7/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model gfs, lead day 7. 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/7/

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