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 6

KORD · 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, 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
tmax00Zbilinear30d24 1 QC4.09 [2.84, 5.32]2.52-3.65 [-5.17, -2.22]4.89 [3.53, 6.13]12% [0%, 29%]21%42%-0.21+0.252026-08-07 → 2026-08-30
tmax00Zbilinear90d24 1 QC4.09 [2.70, 5.47]2.52-3.65 [-5.41, -2.12]4.89 [3.31, 6.34]12% [0%, 29%]21%42%-0.21+0.252026-08-07 → 2026-08-30
tmax00Zbilinear365d30 1 QC4.80 [3.02, 6.86]3.19-4.40 [-6.73, -2.57]6.20 [3.73, 8.82]13% [0%, 28%]20%40%+0.26+0.552026-01-07 → 2026-08-30
tmax00Zbilinearall30 1 QC4.80 [3.15, 7.03]3.19-4.40 [-6.93, -2.53]6.20 [3.87, 8.97]13% [0%, 29%]20%40%+0.26+0.552026-01-07 → 2026-08-30
tmax00Znearest30d24 1 QC4.05 [2.82, 5.22]2.48-3.59 [-5.12, -2.16]4.82 [3.49, 6.00]12% [0%, 29%]21%42%-0.20+0.262026-08-07 → 2026-08-30
tmax00Znearest90d24 1 QC4.05 [2.68, 5.37]2.48-3.59 [-5.32, -2.06]4.82 [3.29, 6.19]12% [0%, 29%]21%42%-0.20+0.262026-08-07 → 2026-08-30
tmax00Znearest365d30 1 QC4.78 [3.03, 6.85]3.13-4.36 [-6.70, -2.54]6.16 [3.69, 8.78]13% [0%, 28%]20%37%+0.26+0.552026-01-07 → 2026-08-30
tmax00Znearestall30 1 QC4.78 [3.13, 7.01]3.13-4.36 [-6.88, -2.51]6.16 [3.86, 8.95]13% [0%, 29%]20%37%+0.26+0.552026-01-07 → 2026-08-30
tmax12Zbilinear30d24 1 QC4.06 [2.65, 5.55]2.94-3.62 [-5.10, -2.14]5.15 [3.43, 6.62]12% [0%, 24%]33%46%-0.20+0.122026-08-07 → 2026-08-30
tmax12Zbilinear90d24 1 QC4.06 [2.56, 5.71]2.94-3.62 [-5.31, -2.05]5.15 [3.30, 6.75]12% [0%, 25%]33%46%-0.20+0.122026-08-07 → 2026-08-30
tmax12Zbilinear365d29 1 QC4.08 [2.73, 5.33]3.04-3.48 [-4.70, -2.10]5.18 [3.54, 6.43]10% [0%, 21%]34%45%+0.38+0.572026-01-07 → 2026-08-30
tmax12Zbilinearall29 1 QC4.08 [2.81, 5.30]3.04-3.48 [-4.81, -2.12]5.18 [3.60, 6.41]10% [0%, 21%]34%45%+0.38+0.572026-01-07 → 2026-08-30
tmax12Znearest30d24 1 QC3.99 [2.56, 5.49]2.95-3.53 [-5.01, -2.05]5.10 [3.37, 6.59]17% [3%, 33%]38%46%-0.18+0.122026-08-07 → 2026-08-30
tmax12Znearest90d24 1 QC3.99 [2.49, 5.67]2.95-3.53 [-5.24, -1.94]5.10 [3.22, 6.70]17% [0%, 33%]38%46%-0.18+0.122026-08-07 → 2026-08-30
tmax12Znearest365d29 1 QC4.05 [2.70, 5.33]3.04-3.40 [-4.64, -2.04]5.14 [3.50, 6.41]14% [0%, 29%]34%45%+0.39+0.572026-01-07 → 2026-08-30
tmax12Znearestall29 1 QC4.05 [2.77, 5.29]3.04-3.40 [-4.75, -2.04]5.14 [3.56, 6.36]14% [0%, 29%]34%45%+0.39+0.572026-01-07 → 2026-08-30
tmin00Zbilinear30d24 1 QC2.06 [1.40, 2.70]2.07+0.10 [-1.02, 1.37]2.82 [1.80, 3.51]46% [35%, 55%]62%71%+0.54+0.542026-08-07 → 2026-08-30
tmin00Zbilinear90d24 1 QC2.06 [1.24, 2.72]2.07+0.10 [-1.19, 1.52]2.82 [1.51, 3.57]46% [33%, 57%]62%71%+0.54+0.542026-08-07 → 2026-08-30
tmin00Zbilinear365d30 1 QC2.43 [1.63, 3.37]2.45+0.14 [-1.07, 1.51]3.22 [2.19, 4.11]40% [25%, 52%]57%63%+0.62+0.622026-01-07 → 2026-08-30
tmin00Zbilinearall30 1 QC2.43 [1.57, 3.33]2.45+0.14 [-1.19, 1.42]3.22 [2.14, 4.07]40% [23%, 52%]57%63%+0.62+0.622026-01-07 → 2026-08-30
tmin00Znearest30d24 1 QC2.14 [1.44, 2.83]2.09-0.25 [-1.36, 1.00]2.88 [1.89, 3.61]38% [22%, 53%]62%67%+0.52+0.532026-08-07 → 2026-08-30
tmin00Znearest90d24 1 QC2.14 [1.36, 2.83]2.09-0.25 [-1.55, 1.20]2.88 [1.64, 3.66]38% [19%, 57%]62%67%+0.52+0.532026-08-07 → 2026-08-30
tmin00Znearest365d30 1 QC2.50 [1.66, 3.46]2.46-0.19 [-1.36, 1.17]3.26 [2.23, 4.14]33% [17%, 50%]57%60%+0.61+0.622026-01-07 → 2026-08-30
tmin00Znearestall30 1 QC2.50 [1.66, 3.40]2.46-0.19 [-1.55, 1.14]3.26 [2.16, 4.13]33% [17%, 50%]57%60%+0.61+0.622026-01-07 → 2026-08-30
tmin12Zbilinear30d24 1 QC1.91 [1.25, 2.60]1.90+0.09 [-0.91, 1.26]2.69 [1.53, 3.61]42% [29%, 53%]62%79%+0.57+0.582026-08-07 → 2026-08-30
tmin12Zbilinear90d24 1 QC1.91 [1.20, 2.64]1.90+0.09 [-0.97, 1.38]2.69 [1.45, 3.63]42% [29%, 54%]62%79%+0.57+0.582026-08-07 → 2026-08-30
tmin12Zbilinear365d29 1 QC2.25 [1.45, 3.25]2.24+0.37 [-0.74, 1.79]3.04 [1.78, 4.03]34% [15%, 48%]59%72%+0.65+0.652026-01-07 → 2026-08-30
tmin12Zbilinearall29 1 QC2.25 [1.35, 3.25]2.24+0.37 [-0.78, 1.90]3.04 [1.67, 4.00]34% [14%, 50%]59%72%+0.65+0.652026-01-07 → 2026-08-30
tmin12Znearest30d24 1 QC1.91 [1.22, 2.67]1.90-0.23 [-1.22, 0.92]2.74 [1.54, 3.74]42% [28%, 58%]58%79%+0.57+0.582026-08-07 → 2026-08-30
tmin12Znearest90d24 1 QC1.91 [1.16, 2.68]1.90-0.23 [-1.24, 1.04]2.74 [1.49, 3.73]42% [28%, 57%]58%79%+0.57+0.582026-08-07 → 2026-08-30
tmin12Znearest365d29 1 QC2.22 [1.40, 3.17]2.23+0.09 [-1.02, 1.50]3.03 [1.82, 4.02]34% [15%, 51%]55%72%+0.65+0.652026-01-07 → 2026-08-30
tmin12Znearestall29 1 QC2.22 [1.36, 3.19]2.23+0.09 [-1.07, 1.62]3.03 [1.69, 4.02]34% [14%, 52%]55%72%+0.65+0.652026-01-07 → 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 KORD, lead day 6, 00Z bilinear tmax+20+100-10-202026-08-07: -6.56 °F2026-08-08: -1.68 °F2026-08-09: -3.95 °F2026-08-10: -7.3 °F2026-08-11: -4.14 °F2026-08-12: -4.18 °F2026-08-13: +2.2 °F2026-08-14: -8.41 °F2026-08-15: +3.01 °F2026-08-16: -3.2 °F2026-08-17: -1.83 °F2026-08-18: -0.61 °F2026-08-19: -0.79 °F2026-08-20: -2.39 °F2026-08-21: -2.8 °F2026-08-22: -2.92 °F2026-08-23: -4.75 °F2026-08-24: -3.93 °F2026-08-25: -3.91 °F2026-08-26: -8.38 °F2026-08-27: -8.32 °F2026-08-28: -10.16 °F2026-08-29: -2.71 °F2026-08-30: +0.11 °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+0.11
2026-08-29-2.71
2026-08-28-10.16
2026-08-27-8.32
2026-08-26-8.38
2026-08-25-3.91
2026-08-24-3.93
2026-08-23-4.75
2026-08-22-2.92
2026-08-21-2.80
2026-08-20-2.39
2026-08-19-0.79
2026-08-18-0.61
2026-08-17-1.83
2026-08-16-3.20
2026-08-15+3.01
2026-08-14-8.41
2026-08-13+2.20
2026-08-12-4.18
2026-08-11-4.14
2026-08-10-7.30
2026-08-09-3.95
2026-08-08-1.68
2026-08-07-6.56

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 6-20 to -18 °F: 1 day-18 to -16 °F: 0 days-16 to -14 °F: 0 days-14 to -12 °F: 0 days-12 to -10 °F: 2 days-10 to -8 °F: 3 days-8 to -6 °F: 3 days-6 to -4 °F: 4 days-4 to -2 °F: 9 days-2 to 0 °F: 4 days0 to 2 °F: 2 days2 to 4 °F: 2 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| 3.92 · P90 |e| 8.59 °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
-20.00-18.001
-18.00-16.000
-16.00-14.000
-14.00-12.000
-12.00-10.002
-10.00-8.003
-8.00-6.003
-6.00-4.004
-4.00-2.009
-2.00+0.004
+0.00+2.002
+2.00+4.002
+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
2026-08244.09 -3.65
2026-0167.63 -7.42

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 -0.14 [-1.37, 0.75] no
NCEP GFS 24 +1.25 [-0.06, 2.99] no
ECMWF IFS HRES 19 +0.61 [-0.84, 2.77] no
Persistence (baseline) 24 +0.72 [-1.28, 2.20] no

Cite this page

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

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