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 8

KORD · graphcast_ifs · lead 8

Target day = initialization date + 8 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
tmax00Zbilinear30d22 1 QC4.57 [3.47, 5.81]4.00-2.86 [-5.00, -0.63]5.88 [4.33, 7.55]23% [12%, 36%]32%41%-0.21-0.062026-08-09 → 2026-08-30
tmax00Zbilinear90d22 1 QC4.57 [3.50, 5.95]4.00-2.86 [-5.51, -0.56]5.88 [4.34, 8.04]23% [11%, 38%]32%41%-0.21-0.062026-08-09 → 2026-08-30
tmax00Zbilinear365d28 1 QC5.55 [3.99, 7.77]4.42-4.21 [-7.60, -1.48]7.14 [4.97, 9.51]18% [5%, 30%]25%36%+0.06+0.282026-01-09 → 2026-08-30
tmax00Zbilinearall28 1 QC5.55 [3.96, 8.34]4.42-4.21 [-8.24, -1.49]7.14 [5.00, 9.87]18% [5%, 32%]25%36%+0.06+0.282026-01-09 → 2026-08-30
tmax00Znearest30d22 1 QC4.59 [3.50, 5.80]4.00-2.80 [-4.94, -0.62]5.85 [4.34, 7.48]14% [0%, 30%]32%41%-0.22-0.062026-08-09 → 2026-08-30
tmax00Znearest90d22 1 QC4.59 [3.54, 5.94]4.00-2.80 [-5.40, -0.52]5.85 [4.35, 7.96]14% [0%, 33%]32%41%-0.22-0.062026-08-09 → 2026-08-30
tmax00Znearest365d28 1 QC5.58 [4.02, 7.80]4.41-4.17 [-7.57, -1.47]7.12 [4.96, 9.51]11% [0%, 25%]25%36%+0.06+0.282026-01-09 → 2026-08-30
tmax00Znearestall28 1 QC5.58 [4.01, 8.38]4.41-4.17 [-8.24, -1.48]7.12 [5.01, 9.89]11% [0%, 27%]25%36%+0.06+0.282026-01-09 → 2026-08-30
tmax12Zbilinear30d22 1 QC4.35 [2.99, 6.47]3.52-3.42 [-6.06, -1.04]5.69 [3.53, 8.13]14% [5%, 22%]32%50%-0.15+0.072026-08-09 → 2026-08-30
tmax12Zbilinear90d22 1 QC4.35 [3.00, 6.98]3.52-3.42 [-6.66, -0.96]5.69 [3.49, 8.75]14% [0%, 22%]32%50%-0.15+0.072026-08-09 → 2026-08-30
tmax12Zbilinear365d27 1 QC5.75 [3.40, 9.81]4.43-4.99 [-9.69, -2.08]7.65 [4.20, 11.28]11% [0%, 19%]26%41%+0.05+0.292026-01-09 → 2026-08-30
tmax12Zbilinearall27 1 QC5.75 [3.49, 10.52]4.43-4.99 [-10.49, -1.93]7.65 [4.13, 12.06]11% [0%, 18%]26%41%+0.05+0.292026-01-09 → 2026-08-30
tmax12Znearest30d22 1 QC4.28 [2.91, 6.48]3.56-3.34 [-6.04, -0.97]5.68 [3.48, 8.18]14% [5%, 22%]32%50%-0.13+0.062026-08-09 → 2026-08-30
tmax12Znearest90d22 1 QC4.28 [2.90, 7.04]3.56-3.34 [-6.74, -0.90]5.68 [3.37, 8.80]14% [0%, 22%]32%50%-0.13+0.062026-08-09 → 2026-08-30
tmax12Znearest365d27 1 QC5.72 [3.29, 9.89]4.52-4.96 [-9.74, -2.00]7.67 [4.07, 11.35]11% [0%, 19%]26%41%+0.05+0.272026-01-09 → 2026-08-30
tmax12Znearestall27 1 QC5.72 [3.39, 10.61]4.52-4.96 [-10.61, -1.82]7.67 [4.08, 12.13]11% [0%, 18%]26%41%+0.05+0.272026-01-09 → 2026-08-30
tmin00Zbilinear30d22 1 QC4.81 [3.92, 5.83]4.82+0.42 [-2.64, 3.43]5.81 [4.88, 6.70]23% [7%, 36%]27%32%-0.06-0.012026-08-09 → 2026-08-30
tmin00Zbilinear90d22 1 QC4.81 [3.81, 5.88]4.82+0.42 [-2.71, 3.79]5.81 [4.76, 6.69]23% [0%, 36%]27%32%-0.06-0.012026-08-09 → 2026-08-30
tmin00Zbilinear365d28 1 QC4.85 [3.97, 5.76]4.82+0.39 [-2.17, 3.19]5.73 [4.85, 6.51]21% [6%, 34%]25%29%+0.16+0.162026-01-09 → 2026-08-30
tmin00Zbilinearall28 1 QC4.85 [3.95, 5.76]4.82+0.39 [-2.14, 3.31]5.73 [4.86, 6.49]21% [7%, 35%]25%29%+0.16+0.162026-01-09 → 2026-08-30
tmin00Znearest30d22 1 QC4.90 [4.05, 5.90]4.91+0.13 [-2.96, 3.20]5.91 [5.09, 6.70]18% [0%, 30%]27%36%-0.08-0.032026-08-09 → 2026-08-30
tmin00Znearest90d22 1 QC4.90 [3.93, 5.92]4.91+0.13 [-3.04, 3.57]5.91 [4.94, 6.70]18% [0%, 29%]27%36%-0.08-0.032026-08-09 → 2026-08-30
tmin00Znearest365d28 1 QC4.90 [4.05, 5.82]4.90+0.12 [-2.48, 2.96]5.80 [4.98, 6.53]14% [0%, 27%]25%32%+0.15+0.152026-01-09 → 2026-08-30
tmin00Znearestall28 1 QC4.90 [4.08, 5.74]4.90+0.12 [-2.45, 3.07]5.80 [4.99, 6.49]14% [0%, 26%]25%32%+0.15+0.152026-01-09 → 2026-08-30
tmin12Zbilinear30d22 1 QC4.03 [2.91, 5.14]3.99-0.15 [-2.53, 2.22]4.73 [3.51, 5.69]9% [0%, 20%]32%41%+0.11+0.162026-08-09 → 2026-08-30
tmin12Zbilinear90d22 1 QC4.03 [2.85, 5.34]3.99-0.15 [-3.15, 2.55]4.73 [3.43, 5.73]9% [0%, 22%]32%41%+0.11+0.162026-08-09 → 2026-08-30
tmin12Zbilinear365d27 1 QC4.17 [3.13, 5.13]4.08-0.36 [-2.54, 1.86]4.82 [3.78, 5.65]7% [0%, 17%]26%37%+0.22+0.222026-01-09 → 2026-08-30
tmin12Zbilinearall27 1 QC4.17 [3.13, 5.17]4.08-0.36 [-2.82, 1.90]4.82 [3.73, 5.69]7% [0%, 17%]26%37%+0.22+0.222026-01-09 → 2026-08-30
tmin12Znearest30d22 1 QC4.18 [3.13, 5.24]4.03-0.52 [-2.96, 1.88]4.82 [3.79, 5.73]14% [5%, 21%]32%41%+0.08+0.152026-08-09 → 2026-08-30
tmin12Znearest90d22 1 QC4.18 [3.03, 5.51]4.03-0.52 [-3.60, 2.23]4.82 [3.61, 5.83]14% [5%, 22%]32%41%+0.08+0.152026-08-09 → 2026-08-30
tmin12Znearest365d27 1 QC4.29 [3.36, 5.29]4.10-0.72 [-2.93, 1.51]4.91 [3.92, 5.72]11% [0%, 19%]30%37%+0.20+0.212026-01-09 → 2026-08-30
tmin12Znearestall27 1 QC4.29 [3.33, 5.31]4.10-0.72 [-3.20, 1.57]4.91 [3.94, 5.76]11% [0%, 18%]30%37%+0.20+0.212026-01-09 → 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 8, 00Z bilinear tmax+20+100-10-202026-08-09: -3.39 °F2026-08-10: -7.63 °F2026-08-11: +0.78 °F2026-08-12: -8.04 °F2026-08-13: +0.83 °F2026-08-14: -8.52 °F2026-08-15: -3.84 °F2026-08-16: -4.43 °F2026-08-17: -5.07 °F2026-08-18: -2.47 °F2026-08-19: +7.13 °F2026-08-20: -1.04 °F2026-08-21: +0.13 °F2026-08-22: -2.47 °F2026-08-23: +7.57 °F2026-08-24: -4.19 °F2026-08-25: -5.5 °F2026-08-26: +0.53 °F2026-08-27: +1.84 °F2026-08-28: -14.96 °F2026-08-29: -9.82 °F2026-08-30: -0.28 °F2026-08-092026-08-30°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 (22 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.28
2026-08-29-9.82
2026-08-28-14.96
2026-08-27+1.84
2026-08-26+0.53
2026-08-25-5.50
2026-08-24-4.19
2026-08-23+7.57
2026-08-22-2.47
2026-08-21+0.13
2026-08-20-1.04
2026-08-19+7.13
2026-08-18-2.47
2026-08-17-5.07
2026-08-16-4.43
2026-08-15-3.84
2026-08-14-8.52
2026-08-13+0.83
2026-08-12-8.04
2026-08-11+0.78
2026-08-10-7.63
2026-08-09-3.39

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 8-20 to -18 °F: 0 days-18 to -16 °F: 1 day-16 to -14 °F: 2 days-14 to -12 °F: 0 days-12 to -10 °F: 0 days-10 to -8 °F: 4 days-8 to -6 °F: 2 days-6 to -4 °F: 5 days-4 to -2 °F: 5 days-2 to 0 °F: 2 days0 to 2 °F: 5 days2 to 4 °F: 0 days4 to 6 °F: 0 days6 to 8 °F: 2 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| 4.74 · P90 |e| 11.3 °F-200+20 °Fn = 28 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
-18.00-16.001
-16.00-14.002
-14.00-12.000
-12.00-10.000
-10.00-8.004
-8.00-6.002
-6.00-4.005
-4.00-2.005
-2.00+0.002
+0.00+2.005
+2.00+4.000
+4.00+6.000
+6.00+8.002
+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
2026-08224.57 -2.86
2026-0169.17 -9.17

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-09 → 2026-08-30 28
GraphCast (IFS init)2026-01-09 → 2026-08-30 28
GraphCast (IFS init)2026-01-09 → 2026-08-30 27
GraphCast (IFS init)2026-01-09 → 2026-08-30 27

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 22 -0.96 [-2.26, 0.41] no
NCEP GFS 22 -0.09 [-1.60, 2.51] no
ECMWF IFS HRES 17 -0.74 [-2.63, 3.17] no
Persistence (baseline) 22 +0.79 [-1.38, 3.25] no

Cite this page

ShortCastCheck, KORD graphcast_ifs lead 8, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KORD/model/graphcast_ifs/lead/8/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KORD (Chicago O'Hare), model graphcast_ifs, lead day 8. 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/8/

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