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 0

KMIA · aifs_single · lead 0

Target day = initialization date + 0 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
tmax00Zbilinear30d30 2 QC4.05 [3.57, 4.54]1.25-4.05 [-4.54, -3.57]4.29 [3.80, 4.73]0% [0%, 0%]7%27%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 2 QC4.05 [3.56, 4.69]1.25-4.05 [-4.69, -3.56]4.29 [3.80, 4.86]0% [0%, 0%]7%27%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 2 QC4.05 [3.51, 4.82]1.25-4.05 [-4.82, -3.51]4.29 [3.75, 4.97]0% [0%, 0%]7%27%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 2 QC4.05 [3.50, 4.71]1.25-4.05 [-4.71, -3.50]4.29 [3.71, 4.90]0% [0%, 0%]7%27%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 2 QC4.89 [4.50, 5.26]1.13-4.89 [-5.26, -4.50]5.06 [4.68, 5.40]0% [0%, 0%]0%10%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 2 QC4.89 [4.47, 5.38]1.13-4.89 [-5.38, -4.47]5.06 [4.63, 5.51]0% [0%, 0%]0%10%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 2 QC4.89 [4.45, 5.46]1.13-4.89 [-5.46, -4.45]5.06 [4.63, 5.57]0% [0%, 0%]0%10%——2026-08-01 → 2026-08-30
tmax00Znearestall30 2 QC4.89 [4.43, 5.39]1.13-4.89 [-5.39, -4.43]5.06 [4.58, 5.52]0% [0%, 0%]0%10%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 2 QC2.10 [1.38, 2.97]1.59+1.89 [1.12, 2.74]2.73 [1.83, 3.67]33% [13%, 53%]50%73%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 2 QC2.10 [1.35, 3.19]1.59+1.89 [1.03, 3.10]2.73 [1.82, 3.93]33% [10%, 57%]50%73%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 2 QC2.10 [1.31, 3.13]1.59+1.89 [1.01, 3.01]2.73 [1.79, 3.86]33% [7%, 59%]50%73%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 2 QC2.10 [1.33, 3.42]1.59+1.89 [1.02, 3.32]2.73 [1.78, 4.17]33% [5%, 58%]50%73%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 2 QC2.76 [1.97, 3.64]1.55+2.68 [1.90, 3.54]3.33 [2.37, 4.28]20% [7%, 37%]37%60%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 2 QC2.76 [1.89, 3.93]1.55+2.68 [1.78, 3.93]3.33 [2.33, 4.57]20% [4%, 40%]37%60%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 2 QC2.76 [1.85, 3.90]1.55+2.68 [1.75, 3.83]3.33 [2.30, 4.55]20% [4%, 42%]37%60%——2026-08-01 → 2026-08-30
tmin00Znearestall30 2 QC2.76 [1.85, 4.18]1.55+2.68 [1.76, 4.13]3.33 [2.29, 4.83]20% [0%, 42%]37%60%——2026-08-01 → 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 0, 00Z bilinear tmax+10+50-5-102026-08-01: -4.02 °F2026-08-02: -2.02 °F2026-08-03: -5.64 °F2026-08-04: -5.5 °F2026-08-05: -5.43 °F2026-08-06: -5.26 °F2026-08-07: -3.57 °F2026-08-08: -1.9 °F2026-08-09: -3.51 °F2026-08-10: -2.77 °F2026-08-11: -3.69 °F2026-08-12: -3.94 °F2026-08-13: -4.94 °F2026-08-14: -6.08 °F2026-08-15: -2.28 °F2026-08-16: -2.92 °F2026-08-17: -2.74 °F2026-08-18: -6 °F2026-08-19: -3.16 °F2026-08-20: -1.33 °F2026-08-21: -5.03 °F2026-08-22: -3.03 °F2026-08-23: -3.2 °F2026-08-24: -2.88 °F2026-08-25: -3.15 °F2026-08-26: -5.41 °F2026-08-27: -5.65 °F2026-08-28: -5.25 °F2026-08-29: -6.21 °F2026-08-30: -5.1 °F2026-08-012026-08-30°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 (30 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-5.10
2026-08-29-6.21
2026-08-28-5.25
2026-08-27-5.65
2026-08-26-5.41
2026-08-25-3.15
2026-08-24-2.88
2026-08-23-3.20
2026-08-22-3.03
2026-08-21-5.03
2026-08-20-1.33
2026-08-19-3.16
2026-08-18-6.00
2026-08-17-2.74
2026-08-16-2.92
2026-08-15-2.28
2026-08-14-6.08
2026-08-13-4.94
2026-08-12-3.94
2026-08-11-3.69
2026-08-10-2.77
2026-08-09-3.51
2026-08-08-1.90
2026-08-07-3.57
2026-08-06-5.26
2026-08-05-5.43
2026-08-04-5.50
2026-08-03-5.64
2026-08-02-2.02
2026-08-01-4.02

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMIA, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 3 days-6 to -5 °F: 9 days-5 to -4 °F: 2 days-4 to -3 °F: 8 days-3 to -2 °F: 6 days-2 to -1 °F: 2 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| 3.81 · P90 |e| 5.68 °F-100+10 °Fn = 30 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
-7.00-6.003
-6.00-5.009
-5.00-4.002
-4.00-3.008
-3.00-2.006
-2.00-1.002
-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
2026-08304.05 -4.05

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-01 → 2026-08-30 30
ECMWF AIFS Single2026-08-01 → 2026-08-30 30

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) 2 -1.30 [-2.35, -0.25] yes
Aurora (IFS init) 3 -1.41 [-1.56, -1.12] yes
FourCastNet v2 (GFS init) 2 +1.11 [0.14, 2.08] yes
FourCastNet v2 (IFS init) 3 +0.44 [-0.33, 0.82] no
NCEP GFS 30 +2.54 [1.96, 3.40] yes
GraphCast (GFS init) 2 -0.39 [-1.42, 0.63] no
GraphCast (IFS init) 28 +0.29 [-0.27, 0.72] no
ECMWF IFS HRES 24 +0.65 [-0.15, 1.14] no
Pangu-Weather (GFS init) 2 -0.18 [-1.31, 0.95] no
Pangu-Weather (IFS init) 3 +0.87 [0.67, 1.27] yes

Cite this page

ShortCastCheck, KMIA aifs_single lead 0, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/aifs_single/lead/0/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model aifs_single, lead day 0. 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/0/

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