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

Chicago O'Hare · GraphCast (IFS init) · lead day 5

KORD · graphcast_ifs · 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, 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, 1 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 1 QC3.67 [2.53, 4.89]2.20-3.36 [-4.51, -2.21]4.35 [3.11, 5.43]12% [0%, 29%]32%36%+0.00+0.412026-08-06 → 2026-08-30
tmax00Zbilinear90d25 1 QC3.67 [2.44, 5.05]2.20-3.36 [-4.75, -2.14]4.35 [3.03, 5.61]12% [0%, 29%]32%36%+0.00+0.412026-08-06 → 2026-08-30
tmax00Zbilinear365d31 1 QC3.85 [2.65, 4.92]2.50-3.49 [-4.52, -2.33]4.92 [3.27, 6.40]10% [0%, 26%]32%42%+0.44+0.652026-01-06 → 2026-08-30
tmax00Zbilinearall31 1 QC3.85 [2.78, 5.02]2.50-3.49 [-4.61, -2.43]4.92 [3.41, 6.54]10% [0%, 26%]32%42%+0.44+0.652026-01-06 → 2026-08-30
tmax00Znearest30d25 1 QC3.67 [2.50, 4.91]2.21-3.33 [-4.51, -2.16]4.36 [3.09, 5.45]12% [0%, 29%]32%36%+0.00+0.402026-08-06 → 2026-08-30
tmax00Znearest90d25 1 QC3.67 [2.45, 5.08]2.21-3.33 [-4.76, -2.08]4.36 [2.98, 5.64]12% [0%, 29%]32%36%+0.00+0.402026-08-06 → 2026-08-30
tmax00Znearest365d31 1 QC3.84 [2.63, 4.93]2.53-3.47 [-4.55, -2.29]4.93 [3.26, 6.42]10% [0%, 26%]35%42%+0.44+0.652026-01-06 → 2026-08-30
tmax00Znearestall31 1 QC3.84 [2.76, 5.02]2.53-3.47 [-4.61, -2.41]4.93 [3.38, 6.55]10% [0%, 26%]35%42%+0.44+0.652026-01-06 → 2026-08-30
tmax12Zbilinear30d25 1 QC4.01 [3.04, 5.28]2.44-3.60 [-4.94, -2.58]4.73 [3.55, 6.01]12% [0%, 22%]24%32%-0.09+0.342026-08-06 → 2026-08-30
tmax12Zbilinear90d25 1 QC4.01 [2.94, 5.66]2.44-3.60 [-5.39, -2.44]4.73 [3.47, 6.46]12% [0%, 24%]24%32%-0.09+0.342026-08-06 → 2026-08-30
tmax12Zbilinear365d30 1 QC4.69 [3.07, 6.62]2.77-4.35 [-6.37, -2.78]5.78 [3.59, 7.90]10% [0%, 20%]20%30%+0.30+0.612026-01-06 → 2026-08-30
tmax12Zbilinearall30 1 QC4.69 [3.22, 6.92]2.77-4.35 [-6.85, -2.86]5.78 [3.66, 8.26]10% [0%, 20%]20%30%+0.30+0.612026-01-06 → 2026-08-30
tmax12Znearest30d25 1 QC3.99 [3.02, 5.30]2.45-3.56 [-4.92, -2.52]4.72 [3.51, 6.05]12% [0%, 22%]24%36%-0.08+0.342026-08-06 → 2026-08-30
tmax12Znearest90d25 1 QC3.99 [2.92, 5.64]2.45-3.56 [-5.36, -2.38]4.72 [3.43, 6.45]12% [0%, 24%]24%36%-0.08+0.342026-08-06 → 2026-08-30
tmax12Znearest365d30 1 QC4.69 [3.03, 6.67]2.81-4.33 [-6.39, -2.73]5.82 [3.56, 8.01]10% [0%, 20%]20%33%+0.30+0.602026-01-06 → 2026-08-30
tmax12Znearestall30 1 QC4.69 [3.19, 6.99]2.81-4.33 [-6.88, -2.80]5.82 [3.61, 8.38]10% [0%, 20%]20%33%+0.30+0.602026-01-06 → 2026-08-30
tmin00Zbilinear30d25 1 QC1.50 [0.88, 2.15]1.47+0.11 [-0.49, 0.81]2.07 [1.08, 2.73]36% [16%, 61%]84%88%+0.65+0.652026-08-06 → 2026-08-30
tmin00Zbilinear90d25 1 QC1.50 [0.77, 2.14]1.47+0.11 [-0.51, 0.89]2.07 [0.91, 2.74]36% [16%, 67%]84%88%+0.65+0.652026-08-06 → 2026-08-30
tmin00Zbilinear365d31 1 QC1.99 [1.02, 3.12]1.95+0.25 [-0.58, 1.19]2.77 [1.31, 3.92]32% [15%, 53%]74%77%+0.70+0.712026-01-06 → 2026-08-30
tmin00Zbilinearall31 1 QC1.99 [1.05, 3.24]1.95+0.25 [-0.54, 1.24]2.77 [1.25, 4.06]32% [14%, 56%]74%77%+0.70+0.712026-01-06 → 2026-08-30
tmin00Znearest30d25 1 QC1.47 [0.85, 2.12]1.49-0.22 [-0.79, 0.44]2.10 [1.11, 2.78]56% [36%, 78%]76%88%+0.65+0.652026-08-06 → 2026-08-30
tmin00Znearest90d25 1 QC1.47 [0.77, 2.13]1.49-0.22 [-0.82, 0.53]2.10 [0.94, 2.80]56% [33%, 82%]76%88%+0.65+0.652026-08-06 → 2026-08-30
tmin00Znearest365d31 1 QC1.96 [1.00, 3.07]1.96-0.05 [-0.89, 0.87]2.78 [1.39, 3.89]48% [28%, 71%]68%77%+0.70+0.702026-01-06 → 2026-08-30
tmin00Znearestall31 1 QC1.96 [1.04, 3.24]1.96-0.05 [-0.82, 0.94]2.78 [1.30, 3.99]48% [25%, 74%]68%77%+0.70+0.702026-01-06 → 2026-08-30
tmin12Zbilinear30d25 1 QC1.71 [1.13, 2.39]1.72-0.08 [-0.81, 0.79]2.26 [1.57, 2.91]40% [16%, 65%]72%80%+0.60+0.592026-08-06 → 2026-08-30
tmin12Zbilinear90d25 1 QC1.71 [1.08, 2.39]1.72-0.08 [-0.88, 0.84]2.26 [1.53, 2.93]40% [14%, 70%]72%80%+0.60+0.592026-08-06 → 2026-08-30
tmin12Zbilinear365d30 1 QC1.94 [1.23, 2.75]1.94-0.02 [-0.75, 0.94]2.63 [1.66, 3.50]37% [13%, 63%]70%77%+0.70+0.702026-01-06 → 2026-08-30
tmin12Zbilinearall30 1 QC1.94 [1.25, 2.76]1.94-0.02 [-0.79, 0.95]2.63 [1.67, 3.56]37% [14%, 62%]70%77%+0.70+0.702026-01-06 → 2026-08-30
tmin12Znearest30d25 1 QC1.67 [1.09, 2.40]1.73-0.40 [-1.10, 0.43]2.31 [1.63, 3.00]44% [21%, 64%]64%80%+0.60+0.592026-08-06 → 2026-08-30
tmin12Znearest90d25 1 QC1.67 [1.06, 2.40]1.73-0.40 [-1.20, 0.51]2.31 [1.60, 2.99]44% [20%, 66%]64%80%+0.60+0.592026-08-06 → 2026-08-30
tmin12Znearest365d30 1 QC1.91 [1.20, 2.76]1.95-0.32 [-1.03, 0.62]2.66 [1.74, 3.51]43% [21%, 62%]63%77%+0.70+0.702026-01-06 → 2026-08-30
tmin12Znearestall30 1 QC1.91 [1.18, 2.80]1.95-0.32 [-1.06, 0.62]2.66 [1.73, 3.58]43% [21%, 63%]63%77%+0.70+0.702026-01-06 → 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 GraphCast (IFS init) at KORD, lead day 5, 00Z bilinear tmax+10+50-5-102026-08-06: -5.7 °F2026-08-07: -7.56 °F2026-08-08: +1.2 °F2026-08-09: -3.78 °F2026-08-10: -7.57 °F2026-08-11: -6.14 °F2026-08-12: -4.66 °F2026-08-13: +1.32 °F2026-08-14: +0.3 °F2026-08-15: -0.22 °F2026-08-16: -3.21 °F2026-08-17: -3.38 °F2026-08-18: -0.69 °F2026-08-19: -1.95 °F2026-08-20: -3.81 °F2026-08-21: -1.74 °F2026-08-22: -3.27 °F2026-08-23: -3.95 °F2026-08-24: -3.7 °F2026-08-25: -5.09 °F2026-08-26: -5.87 °F2026-08-27: -4.21 °F2026-08-28: -9.06 °F2026-08-29: -2.32 °F2026-08-30: +1.07 °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+1.07
2026-08-29-2.32
2026-08-28-9.06
2026-08-27-4.21
2026-08-26-5.87
2026-08-25-5.09
2026-08-24-3.70
2026-08-23-3.95
2026-08-22-3.27
2026-08-21-1.74
2026-08-20-3.81
2026-08-19-1.95
2026-08-18-0.69
2026-08-17-3.38
2026-08-16-3.21
2026-08-15-0.22
2026-08-14+0.30
2026-08-13+1.32
2026-08-12-4.66
2026-08-11-6.14
2026-08-10-7.57
2026-08-09-3.78
2026-08-08+1.20
2026-08-07-7.56
2026-08-06-5.70

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 5-20 to -18 °F: 0 days-18 to -16 °F: 0 days-16 to -14 °F: 1 day-14 to -12 °F: 0 days-12 to -10 °F: 0 days-10 to -8 °F: 1 day-8 to -6 °F: 3 days-6 to -4 °F: 6 days-4 to -2 °F: 10 days-2 to 0 °F: 5 days0 to 2 °F: 5 days2 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| 3.38 · P90 |e| 7.56 °F-200+20 °Fn = 31 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
-16.00-14.001
-14.00-12.000
-12.00-10.000
-10.00-8.001
-8.00-6.003
-6.00-4.006
-4.00-2.0010
-2.00+0.005
+0.00+2.005
+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
2026-08253.67 -3.36
2026-0164.59 -4.03

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 30
GraphCast (IFS init)2026-01-06 → 2026-08-30 30

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 25 +0.20 [-0.34, 0.68] no
NCEP GFS 25 +0.27 [-1.32, 2.18] no
ECMWF IFS HRES 18 +0.80 [-0.82, 2.81] no
Persistence (baseline) 25 -0.01 [-1.68, 1.40] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KORD (Chicago O'Hare), model graphcast_ifs, 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/KORD/model/graphcast_ifs/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