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 · GraphCast (IFS init) · lead day 6

KMIA · graphcast_ifs · lead 6

Target day = initialization date + 6 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, GRAP_v100, starting 2026-01-01 — days before that ran a different version of the model and are excluded rather than silently pooled. Of the scored days, 3 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
tmax00Zbilinear30d24 2 QC5.12 [4.43, 6.15]1.88-5.12 [-6.15, -4.43]5.56 [4.87, 6.36]0% [0%, 0%]4%17%-1.08+0.242026-08-07 → 2026-08-30
tmax00Zbilinear90d24 2 QC5.12 [4.37, 6.30]1.88-5.12 [-6.30, -4.37]5.56 [4.73, 6.46]0% [0%, 0%]4%17%-1.08+0.242026-08-07 → 2026-08-30
tmax00Zbilinear365d30 3 QC4.76 [3.88, 5.73]1.95-4.73 [-5.73, -3.80]5.27 [4.40, 6.07]3% [0%, 13%]10%20%-0.47+0.382026-01-07 → 2026-08-30
tmax00Zbilinearall30 3 QC4.76 [3.87, 5.76]1.95-4.73 [-5.76, -3.75]5.27 [4.39, 6.11]3% [0%, 13%]10%20%-0.47+0.382026-01-07 → 2026-08-30
tmax00Znearest30d24 2 QC5.54 [4.95, 6.39]1.69-5.54 [-6.39, -4.95]5.90 [5.28, 6.58]0% [0%, 0%]0%4%-1.26+0.312026-08-07 → 2026-08-30
tmax00Znearest90d24 2 QC5.54 [4.89, 6.48]1.69-5.54 [-6.48, -4.89]5.90 [5.18, 6.65]0% [0%, 0%]0%4%-1.26+0.312026-08-07 → 2026-08-30
tmax00Znearest365d30 3 QC5.16 [4.27, 6.01]1.77-5.16 [-6.01, -4.27]5.60 [4.77, 6.34]3% [0%, 13%]7%10%-0.60+0.432026-01-07 → 2026-08-30
tmax00Znearestall30 3 QC5.16 [4.24, 6.05]1.77-5.16 [-6.05, -4.24]5.60 [4.74, 6.36]3% [0%, 13%]7%10%-0.60+0.432026-01-07 → 2026-08-30
tmax12Zbilinear30d24 2 QC5.32 [4.45, 6.38]1.82-5.32 [-6.38, -4.45]5.75 [4.84, 6.58]0% [0%, 0%]4%12%-1.17+0.262026-08-07 → 2026-08-30
tmax12Zbilinear90d24 2 QC5.32 [4.30, 6.58]1.82-5.32 [-6.58, -4.30]5.75 [4.58, 6.71]0% [0%, 0%]4%12%-1.17+0.262026-08-07 → 2026-08-30
tmax12Zbilinear365d29 3 QC4.97 [3.94, 6.04]1.79-4.97 [-6.04, -3.94]5.42 [4.10, 6.34]0% [0%, 0%]7%17%-0.55+0.422026-01-07 → 2026-08-30
tmax12Zbilinearall29 3 QC4.97 [3.84, 6.11]1.79-4.97 [-6.11, -3.84]5.42 [3.99, 6.36]0% [0%, 0%]7%17%-0.55+0.422026-01-07 → 2026-08-30
tmax12Znearest30d24 2 QC5.72 [4.92, 6.59]1.66-5.72 [-6.59, -4.92]6.07 [5.22, 6.78]0% [0%, 0%]4%4%-1.33+0.322026-08-07 → 2026-08-30
tmax12Znearest90d24 2 QC5.72 [4.75, 6.70]1.66-5.72 [-6.70, -4.75]6.07 [4.95, 6.87]0% [0%, 0%]4%4%-1.33+0.322026-08-07 → 2026-08-30
tmax12Znearest365d29 3 QC5.37 [4.40, 6.29]1.66-5.37 [-6.29, -4.40]5.74 [4.50, 6.58]0% [0%, 0%]3%7%-0.68+0.462026-01-07 → 2026-08-30
tmax12Znearestall29 3 QC5.37 [4.25, 6.31]1.66-5.37 [-6.31, -4.25]5.74 [4.43, 6.58]0% [0%, 0%]3%7%-0.68+0.462026-01-07 → 2026-08-30
tmin00Zbilinear30d24 2 QC1.68 [1.29, 2.13]1.63-0.34 [-1.42, 0.50]1.98 [1.56, 2.41]25% [9%, 41%]67%83%+0.46+0.492026-08-07 → 2026-08-30
tmin00Zbilinear90d24 2 QC1.68 [1.26, 2.22]1.63-0.34 [-1.78, 0.52]1.98 [1.53, 2.47]25% [0%, 41%]67%83%+0.46+0.492026-08-07 → 2026-08-30
tmin00Zbilinear365d30 2 QC1.75 [1.39, 2.18]1.68-0.39 [-1.34, 0.44]2.04 [1.68, 2.43]23% [9%, 39%]67%83%+0.64+0.672026-01-07 → 2026-08-30
tmin00Zbilinearall30 2 QC1.75 [1.35, 2.14]1.68-0.39 [-1.35, 0.39]2.04 [1.61, 2.40]23% [9%, 39%]67%83%+0.64+0.672026-01-07 → 2026-08-30
tmin00Znearest30d24 2 QC1.65 [1.41, 1.89]1.67+0.16 [-0.90, 1.04]1.96 [1.68, 2.22]38% [25%, 53%]71%88%+0.46+0.482026-08-07 → 2026-08-30
tmin00Znearest90d24 2 QC1.65 [1.42, 1.92]1.67+0.16 [-1.22, 1.07]1.96 [1.66, 2.29]38% [23%, 53%]71%88%+0.46+0.482026-08-07 → 2026-08-30
tmin00Znearest365d30 2 QC1.71 [1.48, 1.96]1.72+0.08 [-0.85, 0.97]2.01 [1.75, 2.28]33% [20%, 47%]70%83%+0.65+0.662026-01-07 → 2026-08-30
tmin00Znearestall30 2 QC1.71 [1.48, 1.96]1.72+0.08 [-0.83, 0.90]2.01 [1.74, 2.27]33% [20%, 47%]70%83%+0.65+0.662026-01-07 → 2026-08-30
tmin12Zbilinear30d24 2 QC1.66 [1.30, 2.06]1.58-0.37 [-1.38, 0.45]2.03 [1.57, 2.40]29% [15%, 41%]71%83%+0.46+0.502026-08-07 → 2026-08-30
tmin12Zbilinear90d24 2 QC1.66 [1.26, 2.14]1.58-0.37 [-1.69, 0.47]2.03 [1.46, 2.43]29% [14%, 43%]71%83%+0.46+0.502026-08-07 → 2026-08-30
tmin12Zbilinear365d29 2 QC1.78 [1.41, 2.25]1.56-0.71 [-1.98, 0.29]2.12 [1.71, 2.49]24% [7%, 37%]66%79%+0.64+0.702026-01-07 → 2026-08-30
tmin12Zbilinearall29 2 QC1.78 [1.37, 2.27]1.56-0.71 [-2.11, 0.26]2.12 [1.65, 2.47]24% [6%, 38%]66%79%+0.64+0.702026-01-07 → 2026-08-30
tmin12Znearest30d24 2 QC1.53 [1.25, 1.82]1.55+0.13 [-0.84, 0.99]1.92 [1.52, 2.25]29% [17%, 43%]71%92%+0.51+0.522026-08-07 → 2026-08-30
tmin12Znearest90d24 2 QC1.53 [1.22, 1.85]1.55+0.13 [-1.16, 1.00]1.92 [1.47, 2.26]29% [15%, 44%]71%92%+0.51+0.522026-08-07 → 2026-08-30
tmin12Znearest365d29 2 QC1.61 [1.33, 1.94]1.55-0.23 [-1.51, 0.82]1.97 [1.58, 2.26]31% [19%, 44%]66%90%+0.68+0.702026-01-07 → 2026-08-30
tmin12Znearestall29 2 QC1.61 [1.30, 1.92]1.55-0.23 [-1.64, 0.77]1.97 [1.52, 2.26]31% [20%, 44%]66%90%+0.68+0.702026-01-07 → 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 GraphCast (IFS init) at KMIA, lead day 6, 00Z bilinear tmax+20+100-10-202026-08-07: -6.23 °F2026-08-08: -6.28 °F2026-08-09: -2.96 °F2026-08-10: -3.2 °F2026-08-11: -4.02 °F2026-08-12: -3.37 °F2026-08-13: -3.12 °F2026-08-14: -10.72 °F2026-08-15: -2.62 °F2026-08-16: -3.23 °F2026-08-17: -3.5 °F2026-08-18: -7.29 °F2026-08-19: -5.77 °F2026-08-20: -1.44 °F2026-08-21: -3.41 °F2026-08-22: -6.43 °F2026-08-23: -6.36 °F2026-08-24: -3 °F2026-08-25: -5.27 °F2026-08-26: -7.07 °F2026-08-27: -8.18 °F2026-08-28: -7.34 °F2026-08-29: -5.01 °F2026-08-30: -6.99 °F2026-08-072026-08-30°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 (24 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-6.99
2026-08-29-5.01
2026-08-28-7.34
2026-08-27-8.18
2026-08-26-7.07
2026-08-25-5.27
2026-08-24-3.00
2026-08-23-6.36
2026-08-22-6.43
2026-08-21-3.41
2026-08-20-1.44
2026-08-19-5.77
2026-08-18-7.29
2026-08-17-3.50
2026-08-16-3.23
2026-08-15-2.62
2026-08-14-10.72
2026-08-13-3.12
2026-08-12-3.37
2026-08-11-4.02
2026-08-10-3.20
2026-08-09-2.96
2026-08-08-6.28
2026-08-07-6.23

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMIA, lead day 6-20 to -18 °F: 0 days-18 to -16 °F: 0 days-16 to -14 °F: 0 days-14 to -12 °F: 0 days-12 to -10 °F: 1 day-10 to -8 °F: 1 day-8 to -6 °F: 9 days-6 to -4 °F: 5 days-4 to -2 °F: 11 days-2 to 0 °F: 2 days0 to 2 °F: 1 day2 to 4 °F: 0 days4 to 6 °F: 0 days6 to 8 °F: 0 days8 to 10 °F: 0 days10 to 12 °F: 0 days12 to 14 °F: 0 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 4.24 · P90 |e| 7.29 °F-200+20 °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
-20.00-18.000
-18.00-16.000
-16.00-14.000
-14.00-12.000
-12.00-10.001
-10.00-8.001
-8.00-6.009
-6.00-4.005
-4.00-2.0011
-2.00+0.002
+0.00+2.001
+2.00+4.000
+4.00+6.000
+6.00+8.000
+8.00+10.000
+10.00+12.000
+12.00+14.000
+14.00+16.000
+16.00+18.000
+18.00+20.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08245.12 -5.12
2026-0163.32 -3.18

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 29
GraphCast (IFS init)2026-01-07 → 2026-08-30 29

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 24 +0.68 [-0.24, 1.81] no
NCEP GFS 24 +2.40 [1.08, 4.77] yes
ECMWF IFS HRES 19 +1.47 [0.55, 2.55] yes
Persistence (baseline) 24 +2.66 [1.67, 4.50] yes

Cite this page

ShortCastCheck, KMIA graphcast_ifs lead 6, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/graphcast_ifs/lead/6/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model graphcast_ifs, lead day 6. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KMIA/model/graphcast_ifs/lead/6/

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