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 5

KMIA · aifs_single · lead 5

Target day = initialization date + 5 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
tmax00Zbilinear30d25 2 QC4.52 [4.03, 5.03]1.41-4.52 [-5.03, -4.03]4.87 [4.32, 5.41]0% [0%, 0%]4%8%-1.21+0.312026-08-06 → 2026-08-30
tmax00Zbilinear90d25 2 QC4.52 [4.00, 5.03]1.41-4.52 [-5.03, -4.00]4.87 [4.31, 5.41]0% [0%, 0%]4%8%-1.21+0.312026-08-06 → 2026-08-30
tmax00Zbilinear365d25 2 QC4.52 [4.00, 5.02]1.41-4.52 [-5.02, -4.00]4.87 [4.32, 5.39]0% [0%, 0%]4%8%-1.21+0.312026-08-06 → 2026-08-30
tmax00Zbilinearall25 2 QC4.52 [3.98, 5.12]1.41-4.52 [-5.12, -3.98]4.87 [4.28, 5.48]0% [0%, 0%]4%8%-1.21+0.312026-08-06 → 2026-08-30
tmax00Znearest30d25 2 QC5.34 [4.86, 5.81]1.36-5.34 [-5.81, -4.86]5.63 [5.10, 6.13]0% [0%, 0%]0%4%-1.62+0.342026-08-06 → 2026-08-30
tmax00Znearest90d25 2 QC5.34 [4.85, 5.80]1.36-5.34 [-5.80, -4.85]5.63 [5.10, 6.11]0% [0%, 0%]0%4%-1.62+0.342026-08-06 → 2026-08-30
tmax00Znearest365d25 2 QC5.34 [4.86, 5.84]1.36-5.34 [-5.84, -4.86]5.63 [5.12, 6.16]0% [0%, 0%]0%4%-1.62+0.342026-08-06 → 2026-08-30
tmax00Znearestall25 2 QC5.34 [4.79, 5.87]1.36-5.34 [-5.87, -4.79]5.63 [5.02, 6.20]0% [0%, 0%]0%4%-1.62+0.342026-08-06 → 2026-08-30
tmax12Zbilinear30d24 2 QC4.82 [4.41, 5.21]1.10-4.82 [-5.21, -4.41]5.03 [4.54, 5.46]0% [0%, 0%]0%4%-1.41+0.462026-08-06 → 2026-08-30
tmax12Zbilinear90d24 2 QC4.82 [4.38, 5.22]1.10-4.82 [-5.22, -4.38]5.03 [4.55, 5.43]0% [0%, 0%]0%4%-1.41+0.462026-08-06 → 2026-08-30
tmax12Zbilinear365d24 2 QC4.82 [4.38, 5.24]1.10-4.82 [-5.24, -4.38]5.03 [4.53, 5.45]0% [0%, 0%]0%4%-1.41+0.462026-08-06 → 2026-08-30
tmax12Zbilinearall24 2 QC4.82 [4.35, 5.29]1.10-4.82 [-5.29, -4.35]5.03 [4.51, 5.49]0% [0%, 0%]0%4%-1.41+0.462026-08-06 → 2026-08-30
tmax12Znearest30d24 2 QC5.66 [5.19, 6.09]1.08-5.66 [-6.09, -5.19]5.84 [5.31, 6.31]0% [0%, 0%]0%0%-1.83+0.472026-08-06 → 2026-08-30
tmax12Znearest90d24 2 QC5.66 [5.14, 6.06]1.08-5.66 [-6.06, -5.14]5.84 [5.25, 6.28]0% [0%, 0%]0%0%-1.83+0.472026-08-06 → 2026-08-30
tmax12Znearest365d24 2 QC5.66 [5.13, 6.08]1.08-5.66 [-6.08, -5.13]5.84 [5.22, 6.32]0% [0%, 0%]0%0%-1.83+0.472026-08-06 → 2026-08-30
tmax12Znearestall24 2 QC5.66 [5.11, 6.13]1.08-5.66 [-6.13, -5.11]5.84 [5.21, 6.31]0% [0%, 0%]0%0%-1.83+0.472026-08-06 → 2026-08-30
tmin00Zbilinear30d25 2 QC2.01 [1.54, 2.51]1.66+1.61 [0.70, 2.40]2.58 [2.01, 3.10]36% [23%, 47%]60%76%+0.24+0.382026-08-06 → 2026-08-30
tmin00Zbilinear90d25 2 QC2.01 [1.49, 2.56]1.66+1.61 [0.50, 2.43]2.58 [1.94, 3.14]36% [22%, 50%]60%76%+0.24+0.382026-08-06 → 2026-08-30
tmin00Zbilinear365d25 2 QC2.01 [1.44, 2.59]1.66+1.61 [0.51, 2.53]2.58 [1.87, 3.14]36% [20%, 50%]60%76%+0.24+0.382026-08-06 → 2026-08-30
tmin00Zbilinearall25 2 QC2.01 [1.43, 2.65]1.66+1.61 [0.51, 2.55]2.58 [1.84, 3.16]36% [19%, 50%]60%76%+0.24+0.382026-08-06 → 2026-08-30
tmin00Znearest30d25 2 QC2.45 [1.69, 3.16]1.66+2.34 [1.41, 3.16]3.08 [2.43, 3.67]28% [4%, 60%]44%60%+0.07+0.382026-08-06 → 2026-08-30
tmin00Znearest90d25 2 QC2.45 [1.51, 3.22]1.66+2.34 [1.20, 3.20]3.08 [2.28, 3.69]28% [3%, 69%]44%60%+0.07+0.382026-08-06 → 2026-08-30
tmin00Znearest365d25 2 QC2.45 [1.52, 3.28]1.66+2.34 [1.21, 3.28]3.08 [2.24, 3.74]28% [0%, 67%]44%60%+0.07+0.382026-08-06 → 2026-08-30
tmin00Znearestall25 2 QC2.45 [1.52, 3.31]1.66+2.34 [1.21, 3.29]3.08 [2.20, 3.78]28% [0%, 67%]44%60%+0.07+0.382026-08-06 → 2026-08-30
tmin12Zbilinear30d24 2 QC1.81 [1.38, 2.25]1.54+1.47 [0.83, 2.05]2.42 [1.91, 2.88]38% [23%, 50%]67%75%+0.28+0.402026-08-06 → 2026-08-30
tmin12Zbilinear90d24 2 QC1.81 [1.35, 2.26]1.54+1.47 [0.67, 2.09]2.42 [1.83, 2.91]38% [22%, 53%]67%75%+0.28+0.402026-08-06 → 2026-08-30
tmin12Zbilinear365d24 2 QC1.81 [1.31, 2.31]1.54+1.47 [0.64, 2.13]2.42 [1.81, 2.94]38% [20%, 54%]67%75%+0.28+0.402026-08-06 → 2026-08-30
tmin12Zbilinearall24 2 QC1.81 [1.30, 2.37]1.54+1.47 [0.67, 2.20]2.42 [1.79, 2.96]38% [19%, 53%]67%75%+0.28+0.402026-08-06 → 2026-08-30
tmin12Znearest30d24 2 QC2.27 [1.72, 2.80]1.53+2.19 [1.57, 2.79]2.90 [2.35, 3.39]33% [11%, 59%]46%75%+0.09+0.402026-08-06 → 2026-08-30
tmin12Znearest90d24 2 QC2.27 [1.60, 2.86]1.53+2.19 [1.38, 2.84]2.90 [2.28, 3.41]33% [10%, 65%]46%75%+0.09+0.402026-08-06 → 2026-08-30
tmin12Znearest365d24 2 QC2.27 [1.59, 2.89]1.53+2.19 [1.39, 2.88]2.90 [2.21, 3.43]33% [7%, 64%]46%75%+0.09+0.402026-08-06 → 2026-08-30
tmin12Znearestall24 2 QC2.27 [1.59, 2.99]1.53+2.19 [1.38, 2.98]2.90 [2.17, 3.48]33% [5%, 67%]46%75%+0.09+0.402026-08-06 → 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 5, 00Z bilinear tmax+10+50-5-102026-08-06: -3.93 °F2026-08-07: -8.8 °F2026-08-08: -3.21 °F2026-08-09: -3.47 °F2026-08-10: -3.6 °F2026-08-11: -4.28 °F2026-08-12: -4.72 °F2026-08-13: -4.17 °F2026-08-14: -8.42 °F2026-08-15: -3.66 °F2026-08-16: -3.33 °F2026-08-17: -3.33 °F2026-08-18: -8.19 °F2026-08-19: -4.13 °F2026-08-20: -3 °F2026-08-21: -3.35 °F2026-08-22: -4.03 °F2026-08-23: -3.19 °F2026-08-24: -1.41 °F2026-08-25: -4.97 °F2026-08-26: -6.4 °F2026-08-27: -6.32 °F2026-08-28: -5.84 °F2026-08-29: -2.63 °F2026-08-30: -4.6 °F2026-08-062026-08-30°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.60
2026-08-29-2.63
2026-08-28-5.84
2026-08-27-6.32
2026-08-26-6.40
2026-08-25-4.97
2026-08-24-1.41
2026-08-23-3.19
2026-08-22-4.03
2026-08-21-3.35
2026-08-20-3.00
2026-08-19-4.13
2026-08-18-8.19
2026-08-17-3.33
2026-08-16-3.33
2026-08-15-3.66
2026-08-14-8.42
2026-08-13-4.17
2026-08-12-4.72
2026-08-11-4.28
2026-08-10-3.60
2026-08-09-3.47
2026-08-08-3.21
2026-08-07-8.80
2026-08-06-3.93

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMIA, lead day 5-10 to -9 °F: 0 days-9 to -8 °F: 3 days-8 to -7 °F: 0 days-7 to -6 °F: 2 days-6 to -5 °F: 1 day-5 to -4 °F: 7 days-4 to -3 °F: 10 days-3 to -2 °F: 1 day-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| 4.03 · P90 |e| 7.47 °F-100+10 °Fn = 25 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
-9.00-8.003
-8.00-7.000
-7.00-6.002
-6.00-5.001
-5.00-4.007
-4.00-3.0010
-3.00-2.001
-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
2026-08254.52 -4.52

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 24
ECMWF AIFS Single2026-08-06 → 2026-08-30 24

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 25 +2.35 [1.56, 3.69] yes
GraphCast (IFS init) 25 -0.51 [-1.65, 0.25] no
ECMWF IFS HRES 18 +0.40 [-0.78, 1.32] no
Persistence (baseline) 25 +2.48 [1.71, 3.53] yes

Cite this page

ShortCastCheck, KMIA aifs_single lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/aifs_single/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model aifs_single, lead day 5. 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/5/

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