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 · ECMWF AIFS Single · lead day 1

KMIA · aifs_single · lead 1

Target day = initialization date + 1 day. 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, aifs-single-gpid5, 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
tmax00Zbilinear30d29 2 QC4.35 [3.79, 5.02]1.34-4.35 [-5.02, -3.79]4.59 [3.99, 5.23]0% [0%, 0%]0%31%-1.80+0.152026-08-02 → 2026-08-30
tmax00Zbilinear90d29 2 QC4.35 [3.77, 5.17]1.34-4.35 [-5.17, -3.77]4.59 [3.96, 5.34]0% [0%, 0%]0%31%-1.80+0.152026-08-02 → 2026-08-30
tmax00Zbilinear365d29 2 QC4.35 [3.76, 5.25]1.34-4.35 [-5.25, -3.76]4.59 [3.96, 5.44]0% [0%, 0%]0%31%-1.80+0.152026-08-02 → 2026-08-30
tmax00Zbilinearall29 2 QC4.35 [3.74, 5.21]1.34-4.35 [-5.21, -3.74]4.59 [3.94, 5.39]0% [0%, 0%]0%31%-1.80+0.152026-08-02 → 2026-08-30
tmax00Znearest30d29 2 QC5.17 [4.72, 5.67]1.23-5.17 [-5.67, -4.72]5.35 [4.87, 5.83]0% [0%, 0%]0%0%-2.33+0.222026-08-02 → 2026-08-30
tmax00Znearest90d29 2 QC5.17 [4.67, 5.79]1.23-5.17 [-5.79, -4.67]5.35 [4.80, 5.94]0% [0%, 0%]0%0%-2.33+0.222026-08-02 → 2026-08-30
tmax00Znearest365d29 2 QC5.17 [4.69, 5.90]1.23-5.17 [-5.90, -4.69]5.35 [4.83, 6.03]0% [0%, 0%]0%0%-2.33+0.222026-08-02 → 2026-08-30
tmax00Znearestall29 2 QC5.17 [4.65, 5.85]1.23-5.17 [-5.85, -4.65]5.35 [4.77, 5.99]0% [0%, 0%]0%0%-2.33+0.222026-08-02 → 2026-08-30
tmax12Zbilinear30d29 2 QC4.38 [3.90, 4.90]1.31-4.38 [-4.90, -3.90]4.63 [4.12, 5.10]0% [0%, 0%]3%24%-1.82+0.172026-08-02 → 2026-08-30
tmax12Zbilinear90d29 2 QC4.38 [3.86, 5.02]1.31-4.38 [-5.02, -3.86]4.63 [4.06, 5.22]0% [0%, 0%]3%24%-1.82+0.172026-08-02 → 2026-08-30
tmax12Zbilinear365d29 2 QC4.38 [3.86, 5.11]1.31-4.38 [-5.11, -3.86]4.63 [4.07, 5.28]0% [0%, 0%]3%24%-1.82+0.172026-08-02 → 2026-08-30
tmax12Zbilinearall29 2 QC4.38 [3.82, 5.11]1.31-4.38 [-5.11, -3.82]4.63 [4.02, 5.27]0% [0%, 0%]3%24%-1.82+0.172026-08-02 → 2026-08-30
tmax12Znearest30d29 2 QC5.23 [4.80, 5.65]1.23-5.23 [-5.65, -4.80]5.43 [4.98, 5.83]0% [0%, 0%]0%3%-2.37+0.222026-08-02 → 2026-08-30
tmax12Znearest90d29 2 QC5.23 [4.76, 5.76]1.23-5.23 [-5.76, -4.76]5.43 [4.92, 5.92]0% [0%, 0%]0%3%-2.37+0.222026-08-02 → 2026-08-30
tmax12Znearest365d29 2 QC5.23 [4.78, 5.77]1.23-5.23 [-5.77, -4.78]5.43 [4.96, 5.92]0% [0%, 0%]0%3%-2.37+0.222026-08-02 → 2026-08-30
tmax12Znearestall29 2 QC5.23 [4.72, 5.78]1.23-5.23 [-5.78, -4.72]5.43 [4.86, 5.91]0% [0%, 0%]0%3%-2.37+0.222026-08-02 → 2026-08-30
tmin00Zbilinear30d29 2 QC1.89 [1.33, 2.58]1.45+1.60 [1.00, 2.25]2.46 [1.73, 3.29]34% [14%, 53%]59%83%+0.27+0.442026-08-02 → 2026-08-30
tmin00Zbilinear90d29 2 QC1.89 [1.32, 2.69]1.45+1.60 [0.91, 2.47]2.46 [1.72, 3.45]34% [12%, 56%]59%83%+0.27+0.442026-08-02 → 2026-08-30
tmin00Zbilinear365d29 2 QC1.89 [1.27, 2.71]1.45+1.60 [0.86, 2.47]2.46 [1.70, 3.40]34% [12%, 56%]59%83%+0.27+0.442026-08-02 → 2026-08-30
tmin00Zbilinearall29 2 QC1.89 [1.26, 2.94]1.45+1.60 [0.84, 2.70]2.46 [1.68, 3.63]34% [10%, 57%]59%83%+0.27+0.442026-08-02 → 2026-08-30
tmin00Znearest30d29 2 QC2.48 [1.81, 3.19]1.43+2.38 [1.73, 3.06]3.02 [2.26, 3.84]24% [10%, 41%]41%66%+0.04+0.442026-08-02 → 2026-08-30
tmin00Znearest90d29 2 QC2.48 [1.76, 3.39]1.43+2.38 [1.64, 3.31]3.02 [2.24, 4.01]24% [6%, 45%]41%66%+0.04+0.442026-08-02 → 2026-08-30
tmin00Znearest365d29 2 QC2.48 [1.71, 3.37]1.43+2.38 [1.57, 3.26]3.02 [2.16, 3.97]24% [7%, 48%]41%66%+0.04+0.442026-08-02 → 2026-08-30
tmin00Znearestall29 2 QC2.48 [1.70, 3.62]1.43+2.38 [1.58, 3.50]3.02 [2.17, 4.23]24% [3%, 47%]41%66%+0.04+0.442026-08-02 → 2026-08-30
tmin12Zbilinear30d29 2 QC1.82 [1.24, 2.54]1.49+1.50 [0.87, 2.20]2.48 [1.66, 3.35]38% [17%, 59%]69%83%+0.29+0.422026-08-02 → 2026-08-30
tmin12Zbilinear90d29 2 QC1.82 [1.22, 2.67]1.49+1.50 [0.79, 2.44]2.48 [1.66, 3.52]38% [15%, 60%]69%83%+0.29+0.422026-08-02 → 2026-08-30
tmin12Zbilinear365d29 2 QC1.82 [1.16, 2.68]1.49+1.50 [0.70, 2.41]2.48 [1.60, 3.47]38% [14%, 60%]69%83%+0.29+0.422026-08-02 → 2026-08-30
tmin12Zbilinearall29 2 QC1.82 [1.16, 2.92]1.49+1.50 [0.73, 2.68]2.48 [1.61, 3.71]38% [14%, 62%]69%83%+0.29+0.422026-08-02 → 2026-08-30
tmin12Znearest30d29 2 QC2.38 [1.68, 3.16]1.48+2.25 [1.55, 2.99]2.98 [2.13, 3.87]24% [7%, 43%]48%76%+0.08+0.432026-08-02 → 2026-08-30
tmin12Znearest90d29 2 QC2.38 [1.64, 3.34]1.48+2.25 [1.47, 3.22]2.98 [2.09, 4.05]24% [5%, 45%]48%76%+0.08+0.432026-08-02 → 2026-08-30
tmin12Znearest365d29 2 QC2.38 [1.56, 3.33]1.48+2.25 [1.42, 3.22]2.98 [2.02, 4.00]24% [4%, 47%]48%76%+0.08+0.432026-08-02 → 2026-08-30
tmin12Znearestall29 2 QC2.38 [1.56, 3.57]1.48+2.25 [1.42, 3.44]2.98 [2.06, 4.28]24% [0%, 48%]48%76%+0.08+0.432026-08-02 → 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 ECMWF AIFS Single at KMIA, lead day 1, 00Z bilinear tmax+10+50-5-102026-08-02: -3.38 °F2026-08-03: -5.6 °F2026-08-04: -6.8 °F2026-08-05: -6.18 °F2026-08-06: -4.01 °F2026-08-07: -3.46 °F2026-08-08: -2.89 °F2026-08-09: -2.99 °F2026-08-10: -2.81 °F2026-08-11: -3.79 °F2026-08-12: -4.1 °F2026-08-13: -5.36 °F2026-08-14: -5.92 °F2026-08-15: -2.43 °F2026-08-16: -3.07 °F2026-08-17: -2.72 °F2026-08-18: -6.37 °F2026-08-19: -2.88 °F2026-08-20: -2.66 °F2026-08-21: -5.37 °F2026-08-22: -2.86 °F2026-08-23: -3.85 °F2026-08-24: -2.66 °F2026-08-25: -3.9 °F2026-08-26: -7 °F2026-08-27: -6.41 °F2026-08-28: -5.54 °F2026-08-29: -4.73 °F2026-08-30: -6.4 °F2026-08-022026-08-30°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 (29 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-6.40
2026-08-29-4.73
2026-08-28-5.54
2026-08-27-6.41
2026-08-26-7.00
2026-08-25-3.90
2026-08-24-2.66
2026-08-23-3.85
2026-08-22-2.86
2026-08-21-5.37
2026-08-20-2.66
2026-08-19-2.88
2026-08-18-6.37
2026-08-17-2.72
2026-08-16-3.07
2026-08-15-2.43
2026-08-14-5.92
2026-08-13-5.36
2026-08-12-4.10
2026-08-11-3.79
2026-08-10-2.81
2026-08-09-2.99
2026-08-08-2.89
2026-08-07-3.46
2026-08-06-4.01
2026-08-05-6.18
2026-08-04-6.80
2026-08-03-5.60
2026-08-02-3.38

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMIA, lead day 1-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 6 days-6 to -5 °F: 5 days-5 to -4 °F: 3 days-4 to -3 °F: 6 days-3 to -2 °F: 9 days-2 to -1 °F: 0 days-1 to 0 °F: 0 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| 3.9 · P90 |e| 6.41 °F-100+10 °Fn = 29 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
-7.00-6.006
-6.00-5.005
-5.00-4.003
-4.00-3.006
-3.00-2.009
-2.00-1.000
-1.00+0.000
+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
2026-08294.35 -4.35

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
Aurora (GFS init) 1 -0.53 [-0.53, -0.53] yes
Aurora (IFS init) 2 -1.31 [-1.66, -0.96] yes
FourCastNet v2 (GFS init) 1 +1.07 [1.07, 1.07] yes
FourCastNet v2 (IFS init) 2 +0.58 [0.39, 0.77] yes
NCEP GFS 29 +2.70 [1.81, 3.81] yes
GraphCast (GFS init) 1 +0.33 [0.33, 0.33] yes
GraphCast (IFS init) 27 -0.20 [-0.94, 0.32] no
ECMWF IFS HRES 23 +0.20 [-0.53, 0.76] no
Pangu-Weather (GFS init) 1 +0.41 [0.41, 0.41] yes
Pangu-Weather (IFS init) 2 -0.98 [-1.03, -0.93] yes
Persistence (baseline) 29 +2.80 [1.88, 3.89] yes

Cite this page

ShortCastCheck, KMIA aifs_single lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/aifs_single/lead/1/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model aifs_single, lead day 1. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KMIA/model/aifs_single/lead/1/

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