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 7

KMIA · aifs_single · 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, 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
tmax00Zbilinear30d23 2 QC4.27 [3.58, 4.92]1.31-4.27 [-4.92, -3.58]4.66 [3.90, 5.34]4% [0%, 12%]9%17%-0.61+0.512026-08-08 → 2026-08-30
tmax00Zbilinear90d23 2 QC4.27 [3.55, 4.89]1.31-4.27 [-4.89, -3.55]4.66 [3.84, 5.32]4% [0%, 12%]9%17%-0.61+0.512026-08-08 → 2026-08-30
tmax00Zbilinear365d23 2 QC4.27 [3.54, 4.91]1.31-4.27 [-4.91, -3.54]4.66 [3.79, 5.37]4% [0%, 14%]9%17%-0.61+0.512026-08-08 → 2026-08-30
tmax00Zbilinearall23 2 QC4.27 [3.39, 4.95]1.31-4.27 [-4.95, -3.39]4.66 [3.71, 5.38]4% [0%, 14%]9%17%-0.61+0.512026-08-08 → 2026-08-30
tmax00Znearest30d23 2 QC5.16 [4.43, 5.87]1.28-5.16 [-5.87, -4.43]5.49 [4.68, 6.27]0% [0%, 0%]4%9%-0.95+0.522026-08-08 → 2026-08-30
tmax00Znearest90d23 2 QC5.16 [4.40, 5.85]1.28-5.16 [-5.85, -4.40]5.49 [4.61, 6.23]0% [0%, 0%]4%9%-0.95+0.522026-08-08 → 2026-08-30
tmax00Znearest365d23 2 QC5.16 [4.39, 5.90]1.28-5.16 [-5.90, -4.39]5.49 [4.56, 6.34]0% [0%, 0%]4%9%-0.95+0.522026-08-08 → 2026-08-30
tmax00Znearestall23 2 QC5.16 [4.29, 5.88]1.28-5.16 [-5.88, -4.29]5.49 [4.41, 6.29]0% [0%, 0%]4%9%-0.95+0.522026-08-08 → 2026-08-30
tmax12Zbilinear30d23 2 QC4.72 [4.20, 5.27]1.14-4.72 [-5.27, -4.20]5.04 [4.39, 5.65]4% [0%, 12%]4%9%-0.78+0.572026-08-08 → 2026-08-30
tmax12Zbilinear90d23 2 QC4.72 [4.18, 5.25]1.14-4.72 [-5.25, -4.18]5.04 [4.31, 5.60]4% [0%, 12%]4%9%-0.78+0.572026-08-08 → 2026-08-30
tmax12Zbilinear365d23 2 QC4.72 [4.17, 5.30]1.14-4.72 [-5.30, -4.17]5.04 [4.27, 5.70]4% [0%, 14%]4%9%-0.78+0.572026-08-08 → 2026-08-30
tmax12Zbilinearall23 2 QC4.72 [4.05, 5.29]1.14-4.72 [-5.29, -4.05]5.04 [4.23, 5.66]4% [0%, 14%]4%9%-0.78+0.572026-08-08 → 2026-08-30
tmax12Znearest30d23 2 QC5.59 [5.02, 6.16]1.12-5.59 [-6.16, -5.02]5.85 [5.16, 6.52]0% [0%, 0%]4%4%-1.11+0.582026-08-08 → 2026-08-30
tmax12Znearest90d23 2 QC5.59 [4.97, 6.13]1.12-5.59 [-6.13, -4.97]5.85 [5.06, 6.48]0% [0%, 0%]4%4%-1.11+0.582026-08-08 → 2026-08-30
tmax12Znearest365d23 2 QC5.59 [4.95, 6.23]1.12-5.59 [-6.23, -4.95]5.85 [5.04, 6.62]0% [0%, 0%]4%4%-1.11+0.582026-08-08 → 2026-08-30
tmax12Znearestall23 2 QC5.59 [4.86, 6.19]1.12-5.59 [-6.19, -4.86]5.85 [5.03, 6.55]0% [0%, 0%]4%4%-1.11+0.582026-08-08 → 2026-08-30
tmin00Zbilinear30d23 2 QC2.13 [1.48, 2.71]1.78+1.65 [0.24, 2.62]2.67 [1.84, 3.20]26% [5%, 50%]61%65%+0.28+0.412026-08-08 → 2026-08-30
tmin00Zbilinear90d23 2 QC2.13 [1.40, 2.77]1.78+1.65 [-0.22, 2.73]2.67 [1.70, 3.24]26% [0%, 50%]61%65%+0.28+0.412026-08-08 → 2026-08-30
tmin00Zbilinear365d23 2 QC2.13 [1.34, 2.81]1.78+1.65 [-0.07, 2.76]2.67 [1.66, 3.27]26% [0%, 52%]61%65%+0.28+0.412026-08-08 → 2026-08-30
tmin00Zbilinearall23 2 QC2.13 [1.38, 2.92]1.78+1.65 [-0.10, 2.85]2.67 [1.63, 3.30]26% [0%, 52%]61%65%+0.28+0.412026-08-08 → 2026-08-30
tmin00Znearest30d23 2 QC2.60 [1.52, 3.41]1.82+2.41 [0.99, 3.41]3.21 [2.15, 3.85]30% [8%, 64%]43%61%+0.12+0.402026-08-08 → 2026-08-30
tmin00Znearest90d23 2 QC2.60 [1.24, 3.52]1.82+2.41 [0.52, 3.52]3.21 [1.82, 3.90]30% [7%, 74%]43%61%+0.12+0.402026-08-08 → 2026-08-30
tmin00Znearest365d23 2 QC2.60 [1.28, 3.57]1.82+2.41 [0.65, 3.57]3.21 [1.86, 3.96]30% [7%, 73%]43%61%+0.12+0.402026-08-08 → 2026-08-30
tmin00Znearestall23 2 QC2.60 [1.27, 3.63]1.82+2.41 [0.63, 3.63]3.21 [1.85, 3.98]30% [4%, 73%]43%61%+0.12+0.402026-08-08 → 2026-08-30
tmin12Zbilinear30d23 2 QC1.93 [1.33, 2.42]1.69+1.33 [0.14, 2.19]2.46 [1.72, 2.97]30% [18%, 45%]57%78%+0.35+0.442026-08-08 → 2026-08-30
tmin12Zbilinear90d23 2 QC1.93 [1.29, 2.46]1.69+1.33 [-0.19, 2.28]2.46 [1.62, 2.97]30% [17%, 50%]57%78%+0.35+0.442026-08-08 → 2026-08-30
tmin12Zbilinear365d23 2 QC1.93 [1.25, 2.50]1.69+1.33 [-0.16, 2.34]2.46 [1.60, 3.01]30% [14%, 50%]57%78%+0.35+0.442026-08-08 → 2026-08-30
tmin12Zbilinearall23 2 QC1.93 [1.24, 2.53]1.69+1.33 [-0.14, 2.43]2.46 [1.56, 3.04]30% [14%, 50%]57%78%+0.35+0.442026-08-08 → 2026-08-30
tmin12Znearest30d23 2 QC2.34 [1.46, 3.03]1.71+2.09 [0.88, 2.97]2.94 [1.99, 3.55]30% [13%, 57%]52%70%+0.21+0.442026-08-08 → 2026-08-30
tmin12Znearest90d23 2 QC2.34 [1.25, 3.10]1.71+2.09 [0.54, 3.07]2.94 [1.74, 3.58]30% [11%, 67%]52%70%+0.21+0.442026-08-08 → 2026-08-30
tmin12Znearest365d23 2 QC2.34 [1.27, 3.15]1.71+2.09 [0.58, 3.13]2.94 [1.79, 3.63]30% [10%, 67%]52%70%+0.21+0.442026-08-08 → 2026-08-30
tmin12Znearestall23 2 QC2.34 [1.25, 3.21]1.71+2.09 [0.59, 3.21]2.94 [1.70, 3.67]30% [7%, 67%]52%70%+0.21+0.442026-08-08 → 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 ECMWF AIFS Single at KMIA, lead day 7, 00Z bilinear tmax+10+50-5-102026-08-08: -4.19 °F2026-08-09: -3.97 °F2026-08-10: -3.83 °F2026-08-11: -4.33 °F2026-08-12: -3.98 °F2026-08-13: -4.18 °F2026-08-14: -7.24 °F2026-08-15: -2.62 °F2026-08-16: -3.35 °F2026-08-17: -3.84 °F2026-08-18: -9.73 °F2026-08-19: -5.87 °F2026-08-20: -3.1 °F2026-08-21: -4.51 °F2026-08-22: -3.15 °F2026-08-23: -2.59 °F2026-08-24: -0.86 °F2026-08-25: -1.88 °F2026-08-26: -4.33 °F2026-08-27: -7.58 °F2026-08-28: -5.57 °F2026-08-29: -3.33 °F2026-08-30: -4.06 °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
2026-08-30-4.06
2026-08-29-3.33
2026-08-28-5.57
2026-08-27-7.58
2026-08-26-4.33
2026-08-25-1.88
2026-08-24-0.86
2026-08-23-2.59
2026-08-22-3.15
2026-08-21-4.51
2026-08-20-3.10
2026-08-19-5.87
2026-08-18-9.73
2026-08-17-3.84
2026-08-16-3.35
2026-08-15-2.62
2026-08-14-7.24
2026-08-13-4.18
2026-08-12-3.98
2026-08-11-4.33
2026-08-10-3.83
2026-08-09-3.97
2026-08-08-4.19

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMIA, lead day 7-10 to -9 °F: 1 day-9 to -8 °F: 0 days-8 to -7 °F: 2 days-7 to -6 °F: 0 days-6 to -5 °F: 2 days-5 to -4 °F: 6 days-4 to -3 °F: 8 days-3 to -2 °F: 2 days-2 to -1 °F: 1 day-1 to 0 °F: 1 day0 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| 3.98 · P90 |e| 6.97 °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
-10.00-9.001
-9.00-8.000
-8.00-7.002
-7.00-6.000
-6.00-5.002
-5.00-4.006
-4.00-3.008
-3.00-2.002
-2.00-1.001
-1.00+0.001
+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
2026-08234.27 -4.27

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
NCEP GFS 23 +1.51 [0.76, 2.87] yes
GraphCast (IFS init) 23 -0.96 [-2.41, 0.15] no
ECMWF IFS HRES 18 +0.64 [-0.53, 1.39] no
Persistence (baseline) 23 +1.61 [0.69, 2.67] yes

Cite this page

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

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