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 9

KORD · graphcast_ifs · lead 9

Target day = initialization date + 9 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
tmax00Zbilinear30d21 1 QC5.11 [3.66, 7.09]4.88-3.01 [-5.99, -0.49]6.58 [4.58, 8.42]10% [0%, 18%]29%43%-0.36-0.322026-08-10 → 2026-08-30
tmax00Zbilinear90d21 1 QC5.11 [3.64, 7.61]4.88-3.01 [-6.65, -0.22]6.58 [4.47, 8.79]10% [0%, 18%]29%43%-0.36-0.322026-08-10 → 2026-08-30
tmax00Zbilinear365d27 1 QC6.20 [4.02, 9.37]5.69-4.57 [-9.01, -1.26]8.07 [5.22, 11.13]11% [0%, 22%]26%37%+0.00+0.102026-01-10 → 2026-08-30
tmax00Zbilinearall27 1 QC6.20 [3.96, 9.62]5.69-4.57 [-9.40, -1.05]8.07 [5.05, 11.33]11% [0%, 20%]26%37%+0.00+0.102026-01-10 → 2026-08-30
tmax00Znearest30d21 1 QC5.09 [3.64, 7.07]4.95-2.90 [-5.94, -0.34]6.59 [4.63, 8.43]10% [0%, 18%]33%43%-0.35-0.342026-08-10 → 2026-08-30
tmax00Znearest90d21 1 QC5.09 [3.59, 7.60]4.95-2.90 [-6.63, -0.04]6.59 [4.54, 8.78]10% [0%, 18%]33%43%-0.35-0.342026-08-10 → 2026-08-30
tmax00Znearest365d27 1 QC6.20 [4.00, 9.40]5.76-4.50 [-9.04, -1.11]8.09 [5.25, 11.18]11% [0%, 22%]30%37%+0.00+0.082026-01-10 → 2026-08-30
tmax00Znearestall27 1 QC6.20 [3.96, 9.65]5.76-4.50 [-9.48, -0.92]8.09 [5.10, 11.33]11% [0%, 20%]30%37%+0.00+0.082026-01-10 → 2026-08-30
tmax12Zbilinear30d21 1 QC4.50 [3.34, 6.21]3.34-3.04 [-6.00, -0.57]5.27 [3.71, 7.17]0% [0%, 0%]14%33%-0.20+0.102026-08-10 → 2026-08-30
tmax12Zbilinear90d21 1 QC4.50 [3.19, 6.74]3.34-3.04 [-6.61, -0.26]5.27 [3.51, 7.68]0% [0%, 0%]14%33%-0.20+0.102026-08-10 → 2026-08-30
tmax12Zbilinear365d26 1 QC5.38 [3.58, 8.21]3.70-4.20 [-8.17, -1.21]6.72 [3.98, 9.97]0% [0%, 0%]12%27%+0.05+0.362026-01-10 → 2026-08-30
tmax12Zbilinearall26 1 QC5.38 [3.61, 8.53]3.70-4.20 [-8.53, -1.17]6.72 [4.12, 10.21]0% [0%, 0%]12%27%+0.05+0.362026-01-10 → 2026-08-30
tmax12Znearest30d21 1 QC4.44 [3.26, 6.20]3.35-2.98 [-5.92, -0.55]5.24 [3.64, 7.19]0% [0%, 0%]19%33%-0.18+0.102026-08-10 → 2026-08-30
tmax12Znearest90d21 1 QC4.44 [3.13, 6.74]3.35-2.98 [-6.56, -0.22]5.24 [3.48, 7.67]0% [0%, 0%]19%33%-0.18+0.102026-08-10 → 2026-08-30
tmax12Znearest365d26 1 QC5.36 [3.53, 8.24]3.75-4.17 [-8.20, -1.18]6.73 [3.93, 10.02]0% [0%, 0%]15%27%+0.05+0.352026-01-10 → 2026-08-30
tmax12Znearestall26 1 QC5.36 [3.54, 8.59]3.75-4.17 [-8.59, -1.13]6.73 [4.09, 10.31]0% [0%, 0%]15%27%+0.05+0.352026-01-10 → 2026-08-30
tmin00Zbilinear30d21 1 QC5.70 [4.19, 6.98]5.71+0.11 [-4.39, 4.38]6.72 [5.26, 7.93]10% [0%, 33%]24%29%-0.15-0.112026-08-10 → 2026-08-30
tmin00Zbilinear90d21 1 QC5.70 [3.74, 7.02]5.71+0.11 [-4.64, 4.66]6.72 [4.86, 7.97]10% [0%, 43%]24%29%-0.15-0.112026-08-10 → 2026-08-30
tmin00Zbilinear365d27 1 QC5.68 [4.48, 6.80]5.68+0.07 [-3.79, 3.95]6.64 [5.48, 7.59]7% [0%, 27%]22%30%+0.13+0.152026-01-10 → 2026-08-30
tmin00Zbilinearall27 1 QC5.68 [4.46, 6.80]5.68+0.07 [-3.78, 4.26]6.64 [5.52, 7.79]7% [0%, 25%]22%30%+0.13+0.152026-01-10 → 2026-08-30
tmin00Znearest30d21 1 QC5.83 [4.38, 7.01]5.82-0.20 [-4.78, 4.19]6.87 [5.53, 7.96]5% [0%, 19%]19%29%-0.18-0.132026-08-10 → 2026-08-30
tmin00Znearest90d21 1 QC5.83 [3.92, 7.22]5.82-0.20 [-5.05, 4.47]6.87 [5.09, 8.04]5% [0%, 25%]19%29%-0.18-0.132026-08-10 → 2026-08-30
tmin00Znearest365d27 1 QC5.77 [4.61, 6.81]5.77-0.23 [-4.16, 3.73]6.77 [5.65, 7.66]7% [0%, 20%]19%30%+0.11+0.142026-01-10 → 2026-08-30
tmin00Znearestall27 1 QC5.77 [4.62, 6.80]5.77-0.23 [-4.18, 4.06]6.77 [5.67, 7.77]7% [0%, 21%]19%30%+0.11+0.142026-01-10 → 2026-08-30
tmin12Zbilinear30d21 1 QC5.99 [5.06, 6.81]6.01-0.47 [-5.04, 3.66]6.90 [5.96, 7.67]0% [0%, 0%]14%24%-0.21-0.172026-08-10 → 2026-08-30
tmin12Zbilinear90d21 1 QC5.99 [4.69, 6.79]6.01-0.47 [-5.33, 4.24]6.90 [5.63, 7.64]0% [0%, 0%]14%24%-0.21-0.172026-08-10 → 2026-08-30
tmin12Zbilinear365d26 1 QC6.21 [5.34, 7.15]6.23-0.34 [-4.56, 3.57]7.00 [6.21, 7.70]0% [0%, 0%]12%19%-0.04-0.042026-01-10 → 2026-08-30
tmin12Zbilinearall26 1 QC6.21 [5.42, 7.19]6.23-0.34 [-4.29, 3.87]7.00 [6.21, 7.69]0% [0%, 0%]12%19%-0.04-0.042026-01-10 → 2026-08-30
tmin12Znearest30d21 1 QC6.10 [5.18, 6.92]6.14-0.81 [-5.45, 3.39]7.05 [6.11, 7.83]0% [0%, 0%]24%24%-0.23-0.202026-08-10 → 2026-08-30
tmin12Znearest90d21 1 QC6.10 [4.82, 6.93]6.14-0.81 [-5.72, 4.00]7.05 [5.72, 7.82]0% [0%, 0%]24%24%-0.23-0.202026-08-10 → 2026-08-30
tmin12Znearest365d26 1 QC6.28 [5.42, 7.17]6.33-0.66 [-4.95, 3.30]7.12 [6.30, 7.79]0% [0%, 0%]19%19%-0.05-0.062026-01-10 → 2026-08-30
tmin12Znearestall26 1 QC6.28 [5.46, 7.21]6.33-0.66 [-4.69, 3.65]7.12 [6.30, 7.79]0% [0%, 0%]19%19%-0.05-0.062026-01-10 → 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 9, 00Z bilinear tmax+20+100-10-202026-08-10: -9.26 °F2026-08-11: +1.75 °F2026-08-12: -6.5 °F2026-08-13: +1.18 °F2026-08-14: -3.82 °F2026-08-15: -10.34 °F2026-08-16: -15.08 °F2026-08-17: +2.72 °F2026-08-18: -0.79 °F2026-08-19: +3.51 °F2026-08-20: +4.33 °F2026-08-21: -3.01 °F2026-08-22: -1.42 °F2026-08-23: +6.34 °F2026-08-24: -0.78 °F2026-08-25: -1.83 °F2026-08-26: -7.44 °F2026-08-27: -2.2 °F2026-08-28: +2.2 °F2026-08-29: -13.48 °F2026-08-30: -9.4 °F2026-08-102026-08-30°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 (21 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-9.40
2026-08-29-13.48
2026-08-28+2.20
2026-08-27-2.20
2026-08-26-7.44
2026-08-25-1.83
2026-08-24-0.78
2026-08-23+6.34
2026-08-22-1.42
2026-08-21-3.01
2026-08-20+4.33
2026-08-19+3.51
2026-08-18-0.79
2026-08-17+2.72
2026-08-16-15.08
2026-08-15-10.34
2026-08-14-3.82
2026-08-13+1.18
2026-08-12-6.50
2026-08-11+1.75
2026-08-10-9.26

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 9-20 to -18 °F: 1 day-18 to -16 °F: 0 days-16 to -14 °F: 2 days-14 to -12 °F: 2 days-12 to -10 °F: 1 day-10 to -8 °F: 3 days-8 to -6 °F: 2 days-6 to -4 °F: 1 day-4 to -2 °F: 3 days-2 to 0 °F: 5 days0 to 2 °F: 2 days2 to 4 °F: 3 days4 to 6 °F: 1 day6 to 8 °F: 1 day8 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| 4.19 · P90 |e| 14.12 °F-200+20 °Fn = 27 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
-16.00-14.002
-14.00-12.002
-12.00-10.001
-10.00-8.003
-8.00-6.002
-6.00-4.001
-4.00-2.003
-2.00+0.005
+0.00+2.002
+2.00+4.003
+4.00+6.001
+6.00+8.001
+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
2026-08215.11 -3.01
2026-01610.00 -10.00

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 26
GraphCast (IFS init)2026-01-10 → 2026-08-30 26

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 21 -0.17 [-1.22, 2.07] no
NCEP GFS 21 -2.06 [-3.42, 1.22] no
ECMWF IFS HRES 16 -0.49 [-2.20, 4.11] no
Persistence (baseline) 21 +1.35 [-1.21, 4.06] no

Cite this page

ShortCastCheck, KORD graphcast_ifs lead 9, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KORD/model/graphcast_ifs/lead/9/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KORD (Chicago O'Hare), model graphcast_ifs, lead day 9. 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/9/

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