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 8

KMIA · gfs · lead 8

Target day = initialization date + 8 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
tmax00Zbilinear30d22 2 QC2.56 [1.56, 3.46]1.08-2.56 [-3.46, -1.56]2.89 [1.72, 3.70]14% [0%, 28%]41%68%+0.09+0.622026-08-09 → 2026-08-30
tmax00Zbilinear90d22 2 QC2.56 [1.35, 3.47]1.08-2.56 [-3.47, -1.35]2.89 [1.40, 3.67]14% [0%, 30%]41%68%+0.09+0.622026-08-09 → 2026-08-30
tmax00Zbilinear365d22 2 QC2.56 [1.32, 3.50]1.08-2.56 [-3.50, -1.32]2.89 [1.37, 3.71]14% [0%, 31%]41%68%+0.09+0.622026-08-09 → 2026-08-30
tmax00Zbilinearall22 2 QC2.56 [1.30, 3.52]1.08-2.56 [-3.52, -1.30]2.89 [1.35, 3.71]14% [0%, 33%]41%68%+0.09+0.622026-08-09 → 2026-08-30
tmax00Znearest30d22 2 QC4.35 [3.24, 5.30]1.14-4.35 [-5.30, -3.24]4.58 [3.34, 5.48]0% [0%, 0%]0%23%-0.54+0.602026-08-09 → 2026-08-30
tmax00Znearest90d22 2 QC4.35 [2.96, 5.32]1.14-4.35 [-5.32, -2.96]4.58 [3.03, 5.46]0% [0%, 0%]0%23%-0.54+0.602026-08-09 → 2026-08-30
tmax00Znearest365d22 2 QC4.35 [2.95, 5.39]1.14-4.35 [-5.39, -2.95]4.58 [3.01, 5.54]0% [0%, 0%]0%23%-0.54+0.602026-08-09 → 2026-08-30
tmax00Znearestall22 2 QC4.35 [2.86, 5.39]1.14-4.35 [-5.39, -2.86]4.58 [2.92, 5.53]0% [0%, 0%]0%23%-0.54+0.602026-08-09 → 2026-08-30
tmax12Zbilinear30d22 2 QC2.82 [1.99, 3.55]1.15-2.73 [-3.54, -1.71]3.29 [2.24, 4.15]14% [0%, 36%]27%64%-0.00+0.602026-08-09 → 2026-08-30
tmax12Zbilinear90d22 2 QC2.82 [1.81, 3.49]1.15-2.73 [-3.49, -1.48]3.29 [2.10, 4.11]14% [0%, 43%]27%64%-0.00+0.602026-08-09 → 2026-08-30
tmax12Zbilinear365d22 2 QC2.82 [1.82, 3.57]1.15-2.73 [-3.57, -1.51]3.29 [2.09, 4.23]14% [0%, 44%]27%64%-0.00+0.602026-08-09 → 2026-08-30
tmax12Zbilinearall22 2 QC2.82 [1.66, 3.52]1.15-2.73 [-3.52, -1.35]3.29 [1.99, 4.19]14% [0%, 50%]27%64%-0.00+0.602026-08-09 → 2026-08-30
tmax12Znearest30d22 2 QC4.65 [3.50, 5.54]1.25-4.65 [-5.54, -3.50]5.04 [3.82, 5.99]5% [0%, 16%]5%14%-0.65+0.562026-08-09 → 2026-08-30
tmax12Znearest90d22 2 QC4.65 [3.20, 5.51]1.25-4.65 [-5.51, -3.20]5.04 [3.54, 5.93]5% [0%, 19%]5%14%-0.65+0.562026-08-09 → 2026-08-30
tmax12Znearest365d22 2 QC4.65 [3.22, 5.62]1.25-4.65 [-5.62, -3.22]5.04 [3.53, 6.08]5% [0%, 19%]5%14%-0.65+0.562026-08-09 → 2026-08-30
tmax12Znearestall22 2 QC4.65 [3.04, 5.57]1.25-4.65 [-5.57, -3.04]5.04 [3.36, 6.03]5% [0%, 20%]5%14%-0.65+0.562026-08-09 → 2026-08-30
tmin00Zbilinear30d22 2 QC4.28 [3.04, 5.40]1.81+4.11 [2.92, 5.14]4.74 [3.53, 5.76]5% [0%, 16%]14%32%-0.29+0.462026-08-09 → 2026-08-30
tmin00Zbilinear90d22 2 QC4.28 [2.84, 5.52]1.81+4.11 [2.69, 5.23]4.74 [3.41, 5.84]5% [0%, 20%]14%32%-0.29+0.462026-08-09 → 2026-08-30
tmin00Zbilinear365d22 2 QC4.28 [2.87, 5.67]1.81+4.11 [2.75, 5.39]4.74 [3.22, 5.91]5% [0%, 18%]14%32%-0.29+0.462026-08-09 → 2026-08-30
tmin00Zbilinearall22 2 QC4.28 [2.85, 5.60]1.81+4.11 [2.72, 5.45]4.74 [3.31, 5.89]5% [0%, 18%]14%32%-0.29+0.462026-08-09 → 2026-08-30
tmin00Znearest30d22 2 QC4.55 [3.25, 5.73]1.84+4.51 [3.24, 5.66]5.08 [3.76, 6.22]9% [0%, 22%]9%27%-0.37+0.452026-08-09 → 2026-08-30
tmin00Znearest90d22 2 QC4.55 [3.02, 5.85]1.84+4.51 [3.02, 5.74]5.08 [3.59, 6.33]9% [0%, 27%]9%27%-0.37+0.452026-08-09 → 2026-08-30
tmin00Znearest365d22 2 QC4.55 [3.07, 6.03]1.84+4.51 [3.07, 5.92]5.08 [3.49, 6.44]9% [0%, 25%]9%27%-0.37+0.452026-08-09 → 2026-08-30
tmin00Znearestall22 2 QC4.55 [3.07, 5.97]1.84+4.51 [3.07, 5.90]5.08 [3.55, 6.36]9% [0%, 25%]9%27%-0.37+0.452026-08-09 → 2026-08-30
tmin12Zbilinear30d22 2 QC4.60 [3.20, 6.02]2.15+3.97 [2.82, 4.90]5.08 [3.68, 6.29]5% [0%, 16%]14%27%-0.39+0.362026-08-09 → 2026-08-30
tmin12Zbilinear90d22 2 QC4.60 [2.93, 6.48]2.15+3.97 [2.64, 4.94]5.08 [3.37, 6.69]5% [0%, 20%]14%27%-0.39+0.362026-08-09 → 2026-08-30
tmin12Zbilinear365d22 2 QC4.60 [2.89, 6.50]2.15+3.97 [2.51, 5.12]5.08 [3.36, 6.70]5% [0%, 18%]14%27%-0.39+0.362026-08-09 → 2026-08-30
tmin12Zbilinearall22 2 QC4.60 [2.94, 6.48]2.15+3.97 [2.48, 5.22]5.08 [3.36, 6.68]5% [0%, 18%]14%27%-0.39+0.362026-08-09 → 2026-08-30
tmin12Znearest30d22 2 QC4.76 [3.34, 6.17]2.15+4.18 [2.98, 5.14]5.23 [3.82, 6.42]5% [0%, 16%]9%23%-0.44+0.362026-08-09 → 2026-08-30
tmin12Znearest90d22 2 QC4.76 [3.11, 6.59]2.15+4.18 [2.84, 5.18]5.23 [3.50, 6.79]5% [0%, 20%]9%23%-0.44+0.362026-08-09 → 2026-08-30
tmin12Znearest365d22 2 QC4.76 [3.05, 6.60]2.15+4.18 [2.68, 5.35]5.23 [3.48, 6.81]5% [0%, 18%]9%23%-0.44+0.362026-08-09 → 2026-08-30
tmin12Znearestall22 2 QC4.76 [3.09, 6.59]2.15+4.18 [2.69, 5.47]5.23 [3.49, 6.79]5% [0%, 18%]9%23%-0.44+0.362026-08-09 → 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 8, 00Z bilinear tmax+10+50-5-102026-08-09: -2.21 °F2026-08-10: -3.4 °F2026-08-11: -2.87 °F2026-08-12: -3.05 °F2026-08-13: -3.66 °F2026-08-14: -5.1 °F2026-08-15: -2.95 °F2026-08-16: -2.54 °F2026-08-17: -4.07 °F2026-08-18: -5.96 °F2026-08-19: -2.94 °F2026-08-20: -0.7 °F2026-08-21: -3.08 °F2026-08-22: -2.93 °F2026-08-23: -1.94 °F2026-08-24: -1.24 °F2026-08-25: -0.91 °F2026-08-26: -1.15 °F2026-08-27: -1.95 °F2026-08-28: -1.04 °F2026-08-29: -1.66 °F2026-08-30: -0.94 °F2026-08-092026-08-30°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 (22 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.94
2026-08-29-1.66
2026-08-28-1.04
2026-08-27-1.95
2026-08-26-1.15
2026-08-25-0.91
2026-08-24-1.24
2026-08-23-1.94
2026-08-22-2.93
2026-08-21-3.08
2026-08-20-0.70
2026-08-19-2.94
2026-08-18-5.96
2026-08-17-4.07
2026-08-16-2.54
2026-08-15-2.95
2026-08-14-5.10
2026-08-13-3.66
2026-08-12-3.05
2026-08-11-2.87
2026-08-10-3.40
2026-08-09-2.21

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KMIA, lead day 8-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 2 days-5 to -4 °F: 1 day-4 to -3 °F: 4 days-3 to -2 °F: 6 days-2 to -1 °F: 6 days-1 to 0 °F: 3 days0 to 1 °F: 0 days1 to 2 °F: 0 days2 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| 2.71 · P90 |e| 4.03 °F-100+10 °Fn = 22 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
-7.00-6.000
-6.00-5.002
-5.00-4.001
-4.00-3.004
-3.00-2.006
-2.00-1.006
-1.00+0.003
+0.00+1.000
+1.00+2.000
+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
2026-08222.56 -2.56

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-09 → 2026-08-30 22
NCEP GFS2026-08-09 → 2026-08-30 22
NCEP GFS2026-08-09 → 2026-08-30 22
NCEP GFS2026-08-09 → 2026-08-30 22

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 22 -1.65 [-2.73, -0.95] yes
GraphCast (IFS init) 22 -2.54 [-4.80, -0.61] yes
ECMWF IFS HRES 17 -2.02 [-4.11, -0.32] yes
Persistence (baseline) 22 -0.26 [-1.68, 0.81] no

Cite this page

ShortCastCheck, KMIA gfs lead 8, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/gfs/lead/8/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model gfs, lead day 8. 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/8/

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