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 2

KMIA · aifs_single · lead 2

Target day = initialization date + 2 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, 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
tmax00Zbilinear30d28 2 QC4.40 [3.77, 5.29]1.27-4.40 [-5.29, -3.77]4.67 [3.99, 5.51]0% [0%, 0%]4%18%-1.20+0.372026-08-03 → 2026-08-30
tmax00Zbilinear90d28 2 QC4.40 [3.76, 5.46]1.27-4.40 [-5.46, -3.76]4.67 [3.95, 5.64]0% [0%, 0%]4%18%-1.20+0.372026-08-03 → 2026-08-30
tmax00Zbilinear365d28 2 QC4.40 [3.70, 5.44]1.27-4.40 [-5.44, -3.70]4.67 [3.90, 5.60]0% [0%, 0%]4%18%-1.20+0.372026-08-03 → 2026-08-30
tmax00Zbilinearall28 2 QC4.40 [3.70, 5.65]1.27-4.40 [-5.65, -3.70]4.67 [3.88, 5.85]0% [0%, 0%]4%18%-1.20+0.372026-08-03 → 2026-08-30
tmax00Znearest30d28 2 QC5.24 [4.72, 5.97]1.18-5.24 [-5.97, -4.72]5.43 [4.89, 6.14]0% [0%, 0%]0%4%-1.62+0.422026-08-03 → 2026-08-30
tmax00Znearest90d28 2 QC5.24 [4.66, 6.07]1.18-5.24 [-6.07, -4.66]5.43 [4.82, 6.22]0% [0%, 0%]0%4%-1.62+0.422026-08-03 → 2026-08-30
tmax00Znearest365d28 2 QC5.24 [4.66, 6.06]1.18-5.24 [-6.06, -4.66]5.43 [4.82, 6.18]0% [0%, 0%]0%4%-1.62+0.422026-08-03 → 2026-08-30
tmax00Znearestall28 2 QC5.24 [4.63, 6.23]1.18-5.24 [-6.23, -4.63]5.43 [4.75, 6.42]0% [0%, 0%]0%4%-1.62+0.422026-08-03 → 2026-08-30
tmax12Zbilinear30d28 2 QC4.53 [4.03, 5.18]1.22-4.53 [-5.18, -4.03]4.73 [4.20, 5.34]0% [0%, 0%]0%11%-1.26+0.402026-08-03 → 2026-08-30
tmax12Zbilinear90d28 2 QC4.53 [4.02, 5.30]1.22-4.53 [-5.30, -4.02]4.73 [4.19, 5.44]0% [0%, 0%]0%11%-1.26+0.402026-08-03 → 2026-08-30
tmax12Zbilinear365d28 2 QC4.53 [4.00, 5.31]1.22-4.53 [-5.31, -4.00]4.73 [4.15, 5.43]0% [0%, 0%]0%11%-1.26+0.402026-08-03 → 2026-08-30
tmax12Zbilinearall28 2 QC4.53 [3.97, 5.47]1.22-4.53 [-5.47, -3.97]4.73 [4.11, 5.57]0% [0%, 0%]0%11%-1.26+0.402026-08-03 → 2026-08-30
tmax12Znearest30d28 2 QC5.38 [4.96, 5.90]1.12-5.38 [-5.90, -4.96]5.54 [5.10, 6.03]0% [0%, 0%]0%0%-1.69+0.442026-08-03 → 2026-08-30
tmax12Znearest90d28 2 QC5.38 [4.91, 5.98]1.12-5.38 [-5.98, -4.91]5.54 [5.03, 6.09]0% [0%, 0%]0%0%-1.69+0.442026-08-03 → 2026-08-30
tmax12Znearest365d28 2 QC5.38 [4.92, 5.97]1.12-5.38 [-5.97, -4.92]5.54 [5.03, 6.09]0% [0%, 0%]0%0%-1.69+0.442026-08-03 → 2026-08-30
tmax12Znearestall28 2 QC5.38 [4.86, 6.11]1.12-5.38 [-6.11, -4.86]5.54 [4.97, 6.18]0% [0%, 0%]0%0%-1.69+0.442026-08-03 → 2026-08-30
tmin00Zbilinear30d28 2 QC1.98 [1.38, 2.68]1.64+1.64 [1.01, 2.31]2.62 [1.89, 3.37]39% [18%, 60%]54%82%+0.09+0.252026-08-03 → 2026-08-30
tmin00Zbilinear90d28 2 QC1.98 [1.34, 2.80]1.64+1.64 [0.90, 2.54]2.62 [1.85, 3.53]39% [16%, 63%]54%82%+0.09+0.252026-08-03 → 2026-08-30
tmin00Zbilinear365d28 2 QC1.98 [1.29, 2.82]1.64+1.64 [0.83, 2.51]2.62 [1.80, 3.55]39% [14%, 61%]54%82%+0.09+0.252026-08-03 → 2026-08-30
tmin00Zbilinearall28 2 QC1.98 [1.26, 3.02]1.64+1.64 [0.85, 2.66]2.62 [1.78, 3.80]39% [14%, 63%]54%82%+0.09+0.252026-08-03 → 2026-08-30
tmin00Znearest30d28 2 QC2.56 [1.85, 3.30]1.62+2.44 [1.76, 3.14]3.17 [2.41, 3.91]29% [11%, 50%]46%61%-0.17+0.272026-08-03 → 2026-08-30
tmin00Znearest90d28 2 QC2.56 [1.78, 3.48]1.62+2.44 [1.66, 3.40]3.17 [2.36, 4.07]29% [9%, 53%]46%61%-0.17+0.272026-08-03 → 2026-08-30
tmin00Znearest365d28 2 QC2.56 [1.74, 3.46]1.62+2.44 [1.58, 3.33]3.17 [2.25, 4.10]29% [7%, 56%]46%61%-0.17+0.272026-08-03 → 2026-08-30
tmin00Znearestall28 2 QC2.56 [1.68, 3.64]1.62+2.44 [1.58, 3.50]3.17 [2.23, 4.35]29% [6%, 53%]46%61%-0.17+0.272026-08-03 → 2026-08-30
tmin12Zbilinear30d28 2 QC1.80 [1.21, 2.53]1.58+1.45 [0.85, 2.15]2.46 [1.67, 3.37]43% [23%, 61%]64%82%+0.18+0.282026-08-03 → 2026-08-30
tmin12Zbilinear90d28 2 QC1.80 [1.20, 2.66]1.58+1.45 [0.78, 2.42]2.46 [1.65, 3.57]43% [23%, 64%]64%82%+0.18+0.282026-08-03 → 2026-08-30
tmin12Zbilinear365d28 2 QC1.80 [1.15, 2.68]1.58+1.45 [0.71, 2.37]2.46 [1.59, 3.52]43% [18%, 62%]64%82%+0.18+0.282026-08-03 → 2026-08-30
tmin12Zbilinearall28 2 QC1.80 [1.13, 2.98]1.58+1.45 [0.71, 2.64]2.46 [1.60, 3.81]43% [21%, 64%]64%82%+0.18+0.282026-08-03 → 2026-08-30
tmin12Znearest30d28 2 QC2.32 [1.65, 3.06]1.55+2.22 [1.57, 2.97]2.97 [2.15, 3.89]29% [12%, 47%]54%71%-0.07+0.302026-08-03 → 2026-08-30
tmin12Znearest90d28 2 QC2.32 [1.62, 3.29]1.55+2.22 [1.50, 3.23]2.97 [2.09, 4.07]29% [9%, 50%]54%71%-0.07+0.302026-08-03 → 2026-08-30
tmin12Znearest365d28 2 QC2.32 [1.54, 3.26]1.55+2.22 [1.44, 3.18]2.97 [2.01, 4.04]29% [7%, 50%]54%71%-0.07+0.302026-08-03 → 2026-08-30
tmin12Znearestall28 2 QC2.32 [1.51, 3.56]1.55+2.22 [1.43, 3.42]2.97 [2.04, 4.34]29% [4%, 52%]54%71%-0.07+0.302026-08-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -7.59 °F2026-08-04: -7.26 °F2026-08-05: -5.19 °F2026-08-06: -3.97 °F2026-08-07: -3.76 °F2026-08-08: -2.56 °F2026-08-09: -3.41 °F2026-08-10: -2.8 °F2026-08-11: -3.69 °F2026-08-12: -4.2 °F2026-08-13: -4.68 °F2026-08-14: -6.25 °F2026-08-15: -3.24 °F2026-08-16: -2.94 °F2026-08-17: -3.13 °F2026-08-18: -6.15 °F2026-08-19: -3.45 °F2026-08-20: -1.32 °F2026-08-21: -4.7 °F2026-08-22: -3.72 °F2026-08-23: -3.91 °F2026-08-24: -2.36 °F2026-08-25: -4.19 °F2026-08-26: -6.62 °F2026-08-27: -6.52 °F2026-08-28: -5.27 °F2026-08-29: -4.43 °F2026-08-30: -5.99 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-5.99
2026-08-29-4.43
2026-08-28-5.27
2026-08-27-6.52
2026-08-26-6.62
2026-08-25-4.19
2026-08-24-2.36
2026-08-23-3.91
2026-08-22-3.72
2026-08-21-4.70
2026-08-20-1.32
2026-08-19-3.45
2026-08-18-6.15
2026-08-17-3.13
2026-08-16-2.94
2026-08-15-3.24
2026-08-14-6.25
2026-08-13-4.68
2026-08-12-4.20
2026-08-11-3.69
2026-08-10-2.80
2026-08-09-3.41
2026-08-08-2.56
2026-08-07-3.76
2026-08-06-3.97
2026-08-05-5.19
2026-08-04-7.26
2026-08-03-7.59

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMIA, lead day 2-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 2 days-7 to -6 °F: 4 days-6 to -5 °F: 3 days-5 to -4 °F: 5 days-4 to -3 °F: 9 days-3 to -2 °F: 4 days-2 to -1 °F: 1 day-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| 4.08 · P90 |e| 6.55 °F-100+10 °Fn = 28 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
-8.00-7.002
-7.00-6.004
-6.00-5.003
-5.00-4.005
-4.00-3.009
-3.00-2.004
-2.00-1.001
-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
2026-08284.40 -4.40

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28

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 (IFS init) 1 -0.87 [-0.87, -0.87] yes
FourCastNet v2 (IFS init) 1 +0.73 [0.73, 0.73] yes
NCEP GFS 28 +2.71 [1.74, 4.39] yes
GraphCast (IFS init) 26 -0.28 [-1.09, 0.37] no
ECMWF IFS HRES 22 +0.42 [-0.33, 1.16] no
Pangu-Weather (IFS init) 1 -1.12 [-1.12, -1.12] yes
Persistence (baseline) 28 +2.40 [1.31, 3.75] yes

Cite this page

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

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

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