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 7

KMIA · graphcast_ifs · 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, 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
tmax00Zbilinear30d23 2 QC5.22 [4.31, 6.22]1.75-5.22 [-6.22, -4.31]5.62 [4.63, 6.49]0% [0%, 0%]0%9%-0.97+0.342026-08-08 → 2026-08-30
tmax00Zbilinear90d23 2 QC5.22 [4.17, 6.38]1.75-5.22 [-6.38, -4.17]5.62 [4.37, 6.57]0% [0%, 0%]0%9%-0.97+0.342026-08-08 → 2026-08-30
tmax00Zbilinear365d29 3 QC5.32 [4.35, 6.42]2.22-4.91 [-5.94, -3.84]5.80 [4.77, 6.73]0% [0%, 0%]3%10%-0.48+0.382026-01-08 → 2026-08-30
tmax00Zbilinearall29 3 QC5.32 [4.44, 6.35]2.22-4.91 [-5.96, -3.80]5.80 [4.88, 6.72]0% [0%, 0%]3%10%-0.48+0.382026-01-08 → 2026-08-30
tmax00Znearest30d23 2 QC5.65 [4.88, 6.43]1.55-5.65 [-6.43, -4.88]5.95 [5.09, 6.68]0% [0%, 0%]0%0%-1.13+0.422026-08-08 → 2026-08-30
tmax00Znearest90d23 2 QC5.65 [4.73, 6.53]1.55-5.65 [-6.53, -4.73]5.95 [4.85, 6.73]0% [0%, 0%]0%0%-1.13+0.422026-08-08 → 2026-08-30
tmax00Znearest365d29 3 QC5.69 [4.92, 6.56]1.99-5.32 [-6.16, -4.25]6.06 [5.23, 6.82]0% [0%, 0%]0%3%-0.59+0.442026-01-08 → 2026-08-30
tmax00Znearestall29 3 QC5.69 [5.00, 6.51]1.99-5.32 [-6.22, -4.18]6.06 [5.29, 6.81]0% [0%, 0%]0%3%-0.59+0.442026-01-08 → 2026-08-30
tmax12Zbilinear30d23 2 QC5.23 [4.02, 6.37]2.00-5.23 [-6.37, -4.02]5.73 [4.26, 6.77]0% [0%, 0%]0%13%-0.97+0.252026-08-08 → 2026-08-30
tmax12Zbilinear90d23 2 QC5.23 [3.74, 6.40]2.00-5.23 [-6.40, -3.74]5.73 [3.87, 6.72]0% [0%, 0%]0%13%-0.97+0.252026-08-08 → 2026-08-30
tmax12Zbilinear365d28 3 QC5.06 [3.85, 6.06]1.84-5.06 [-6.06, -3.85]5.53 [4.02, 6.52]0% [0%, 0%]0%14%-0.48+0.462026-01-08 → 2026-08-30
tmax12Zbilinearall28 3 QC5.06 [3.94, 6.07]1.84-5.06 [-6.07, -3.94]5.53 [4.11, 6.51]0% [0%, 0%]0%14%-0.48+0.462026-01-08 → 2026-08-30
tmax12Znearest30d23 2 QC5.66 [4.64, 6.57]1.81-5.66 [-6.57, -4.64]6.08 [4.81, 6.96]0% [0%, 0%]0%4%-1.14+0.322026-08-08 → 2026-08-30
tmax12Znearest90d23 2 QC5.66 [4.29, 6.56]1.81-5.66 [-6.56, -4.29]6.08 [4.40, 6.92]0% [0%, 0%]0%4%-1.14+0.322026-08-08 → 2026-08-30
tmax12Znearest365d28 3 QC5.49 [4.43, 6.36]1.68-5.49 [-6.36, -4.43]5.87 [4.58, 6.76]0% [0%, 0%]0%7%-0.60+0.502026-01-08 → 2026-08-30
tmax12Znearestall28 3 QC5.49 [4.46, 6.35]1.68-5.49 [-6.35, -4.46]5.87 [4.61, 6.77]0% [0%, 0%]0%7%-0.60+0.502026-01-08 → 2026-08-30
tmin00Zbilinear30d23 2 QC1.68 [1.22, 2.31]1.65-0.44 [-1.57, 0.41]2.04 [1.55, 2.55]35% [12%, 56%]70%83%+0.43+0.462026-08-08 → 2026-08-30
tmin00Zbilinear90d23 2 QC1.68 [1.18, 2.44]1.65-0.44 [-1.92, 0.49]2.04 [1.50, 2.65]35% [5%, 57%]70%83%+0.43+0.462026-08-08 → 2026-08-30
tmin00Zbilinear365d29 2 QC2.13 [1.38, 3.32]1.92-1.15 [-2.98, 0.16]2.91 [1.75, 4.46]28% [0%, 50%]59%79%+0.57+0.622026-01-08 → 2026-08-30
tmin00Zbilinearall29 2 QC2.13 [1.37, 3.47]1.92-1.15 [-3.39, 0.21]2.91 [1.69, 4.60]28% [0%, 50%]59%79%+0.57+0.622026-01-08 → 2026-08-30
tmin00Znearest30d23 2 QC1.65 [1.29, 2.08]1.66+0.03 [-1.02, 0.92]1.97 [1.63, 2.30]22% [0%, 43%]70%87%+0.44+0.452026-08-08 → 2026-08-30
tmin00Znearest90d23 2 QC1.65 [1.29, 2.21]1.66+0.03 [-1.41, 0.97]1.97 [1.60, 2.39]22% [0%, 44%]70%87%+0.44+0.452026-08-08 → 2026-08-30
tmin00Znearest365d29 2 QC2.04 [1.40, 3.11]1.94-0.71 [-2.48, 0.61]2.76 [1.76, 4.21]21% [0%, 39%]59%83%+0.59+0.622026-01-08 → 2026-08-30
tmin00Znearestall29 2 QC2.04 [1.43, 3.17]1.94-0.71 [-2.99, 0.70]2.76 [1.75, 4.35]21% [0%, 42%]59%83%+0.59+0.622026-01-08 → 2026-08-30
tmin12Zbilinear30d23 2 QC1.69 [1.18, 2.21]1.64-0.49 [-1.44, 0.28]2.08 [1.52, 2.51]39% [14%, 59%]61%83%+0.43+0.462026-08-08 → 2026-08-30
tmin12Zbilinear90d23 2 QC1.69 [1.15, 2.37]1.64-0.49 [-1.71, 0.36]2.08 [1.49, 2.59]39% [5%, 60%]61%83%+0.43+0.462026-08-08 → 2026-08-30
tmin12Zbilinear365d28 2 QC1.75 [1.26, 2.29]1.63-0.75 [-1.92, 0.13]2.15 [1.66, 2.58]36% [14%, 57%]61%82%+0.65+0.692026-01-08 → 2026-08-30
tmin12Zbilinearall28 2 QC1.75 [1.22, 2.27]1.63-0.75 [-1.95, 0.13]2.15 [1.60, 2.56]36% [13%, 56%]61%82%+0.65+0.692026-01-08 → 2026-08-30
tmin12Znearest30d23 2 QC1.67 [1.30, 2.07]1.67+0.01 [-0.93, 0.85]2.02 [1.62, 2.39]39% [15%, 61%]70%83%+0.43+0.452026-08-08 → 2026-08-30
tmin12Znearest90d23 2 QC1.67 [1.24, 2.13]1.67+0.01 [-1.20, 0.91]2.02 [1.57, 2.42]39% [10%, 62%]70%83%+0.43+0.452026-08-08 → 2026-08-30
tmin12Znearest365d28 2 QC1.71 [1.33, 2.09]1.68-0.28 [-1.42, 0.66]2.06 [1.69, 2.39]39% [16%, 62%]68%82%+0.66+0.682026-01-08 → 2026-08-30
tmin12Znearestall28 2 QC1.71 [1.30, 2.08]1.68-0.28 [-1.50, 0.65]2.06 [1.63, 2.37]39% [16%, 62%]68%82%+0.66+0.682026-01-08 → 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 GraphCast (IFS init) at KMIA, lead day 7, 00Z bilinear tmax+10+50-5-102026-08-08: -4.52 °F2026-08-09: -3.47 °F2026-08-10: -3.39 °F2026-08-11: -4.2 °F2026-08-12: -3.89 °F2026-08-13: -2.86 °F2026-08-14: -9.67 °F2026-08-15: -2.31 °F2026-08-16: -3.23 °F2026-08-17: -3.34 °F2026-08-18: -8.6 °F2026-08-19: -5.03 °F2026-08-20: -3.27 °F2026-08-21: -6.59 °F2026-08-22: -4.89 °F2026-08-23: -5.6 °F2026-08-24: -3.39 °F2026-08-25: -7.66 °F2026-08-26: -7.49 °F2026-08-27: -8.52 °F2026-08-28: -7.39 °F2026-08-29: -5.23 °F2026-08-30: -5.63 °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
2026-08-30-5.63
2026-08-29-5.23
2026-08-28-7.39
2026-08-27-8.52
2026-08-26-7.49
2026-08-25-7.66
2026-08-24-3.39
2026-08-23-5.60
2026-08-22-4.89
2026-08-21-6.59
2026-08-20-3.27
2026-08-19-5.03
2026-08-18-8.60
2026-08-17-3.34
2026-08-16-3.23
2026-08-15-2.31
2026-08-14-9.67
2026-08-13-2.86
2026-08-12-3.89
2026-08-11-4.20
2026-08-10-3.39
2026-08-09-3.47
2026-08-08-4.52

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMIA, lead day 7-20 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: 3 days-8 to -6 °F: 5 days-6 to -4 °F: 8 days-4 to -2 °F: 10 days-2 to 0 °F: 1 day0 to 2 °F: 0 days2 to 4 °F: 0 days4 to 6 °F: 1 day6 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| 4.89 · P90 |e| 8.54 °F-200+20 °Fn = 29 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
-10.00-8.003
-8.00-6.005
-6.00-4.008
-4.00-2.0010
-2.00+0.001
+0.00+2.000
+2.00+4.000
+4.00+6.001
+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
2026-08235.22 -5.22
2026-0165.69 -3.73

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 28
GraphCast (IFS init)2026-01-08 → 2026-08-30 28

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 23 +0.96 [-0.15, 2.41] no
NCEP GFS 23 +2.47 [0.87, 4.87] yes
ECMWF IFS HRES 18 +2.00 [0.22, 2.82] yes
Persistence (baseline) 23 +2.57 [1.56, 3.73] yes

Cite this page

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

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