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 7

KORD · 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, 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
tmax00Zbilinear30d23 1 QC4.22 [2.66, 5.99]3.11-3.30 [-5.67, -1.34]5.29 [3.30, 7.15]13% [0%, 27%]30%35%-0.10+0.192026-08-08 → 2026-08-30
tmax00Zbilinear90d23 1 QC4.22 [2.54, 6.25]3.11-3.30 [-6.23, -1.23]5.29 [3.19, 7.61]13% [0%, 29%]30%35%-0.10+0.192026-08-08 → 2026-08-30
tmax00Zbilinear365d29 1 QC5.43 [3.28, 8.25]3.75-4.70 [-8.17, -2.11]6.89 [4.03, 9.68]10% [0%, 22%]24%28%+0.16+0.452026-01-08 → 2026-08-30
tmax00Zbilinearall29 1 QC5.43 [3.25, 8.74]3.75-4.70 [-8.74, -2.02]6.89 [4.12, 10.23]10% [0%, 23%]24%28%+0.16+0.452026-01-08 → 2026-08-30
tmax00Znearest30d23 1 QC4.18 [2.61, 5.95]3.05-3.27 [-5.63, -1.29]5.25 [3.23, 7.11]13% [0%, 27%]30%35%-0.09+0.202026-08-08 → 2026-08-30
tmax00Znearest90d23 1 QC4.18 [2.47, 6.26]3.05-3.27 [-6.21, -1.22]5.25 [3.13, 7.59]13% [0%, 29%]30%35%-0.09+0.202026-08-08 → 2026-08-30
tmax00Znearest365d29 1 QC5.39 [3.24, 8.22]3.73-4.67 [-8.15, -2.09]6.83 [3.98, 9.62]10% [0%, 22%]24%28%+0.16+0.452026-01-08 → 2026-08-30
tmax00Znearestall29 1 QC5.39 [3.18, 8.71]3.73-4.67 [-8.71, -2.01]6.83 [4.04, 10.12]10% [0%, 23%]24%28%+0.16+0.452026-01-08 → 2026-08-30
tmax12Zbilinear30d23 1 QC4.15 [2.72, 5.86]3.21-3.41 [-5.75, -1.32]5.35 [3.35, 7.11]13% [0%, 24%]26%52%-0.08+0.162026-08-08 → 2026-08-30
tmax12Zbilinear90d23 1 QC4.15 [2.79, 6.27]3.21-3.41 [-6.27, -1.40]5.35 [3.42, 7.38]13% [0%, 24%]26%52%-0.08+0.162026-08-08 → 2026-08-30
tmax12Zbilinear365d28 1 QC4.53 [3.09, 6.32]3.22-3.92 [-6.32, -1.77]5.84 [3.79, 7.70]11% [0%, 22%]21%43%+0.30+0.532026-01-08 → 2026-08-30
tmax12Zbilinearall28 1 QC4.53 [3.08, 6.52]3.22-3.92 [-6.46, -1.93]5.84 [3.81, 7.77]11% [0%, 20%]21%43%+0.30+0.532026-01-08 → 2026-08-30
tmax12Znearest30d23 1 QC4.10 [2.69, 5.81]3.18-3.36 [-5.69, -1.28]5.29 [3.31, 7.02]22% [0%, 37%]26%52%-0.07+0.172026-08-08 → 2026-08-30
tmax12Znearest90d23 1 QC4.10 [2.76, 6.26]3.18-3.36 [-6.26, -1.35]5.29 [3.38, 7.30]22% [0%, 36%]26%52%-0.07+0.172026-08-08 → 2026-08-30
tmax12Znearest365d28 1 QC4.52 [3.05, 6.39]3.19-3.91 [-6.39, -1.73]5.83 [3.74, 7.73]18% [0%, 33%]21%43%+0.30+0.532026-01-08 → 2026-08-30
tmax12Znearestall28 1 QC4.52 [3.08, 6.53]3.19-3.91 [-6.47, -1.90]5.83 [3.79, 7.82]18% [0%, 31%]21%43%+0.30+0.532026-01-08 → 2026-08-30
tmin00Zbilinear30d23 1 QC3.53 [2.38, 4.69]3.53-0.00 [-2.07, 2.47]4.61 [2.88, 5.86]30% [19%, 44%]43%48%+0.24+0.252026-08-08 → 2026-08-30
tmin00Zbilinear90d23 1 QC3.53 [2.26, 4.66]3.53-0.00 [-2.24, 2.74]4.61 [2.73, 5.92]30% [20%, 45%]43%48%+0.24+0.252026-08-08 → 2026-08-30
tmin00Zbilinear365d29 1 QC3.54 [2.56, 4.55]3.55-0.20 [-1.97, 1.87]4.49 [3.09, 5.67]24% [10%, 38%]38%48%+0.39+0.402026-01-08 → 2026-08-30
tmin00Zbilinearall29 1 QC3.54 [2.50, 4.39]3.55-0.20 [-2.09, 2.02]4.49 [3.01, 5.56]24% [10%, 39%]38%48%+0.39+0.402026-01-08 → 2026-08-30
tmin00Znearest30d23 1 QC3.57 [2.39, 4.80]3.58-0.35 [-2.46, 2.16]4.74 [3.05, 6.03]30% [19%, 44%]43%48%+0.23+0.242026-08-08 → 2026-08-30
tmin00Znearest90d23 1 QC3.57 [2.26, 4.80]3.58-0.35 [-2.65, 2.44]4.74 [2.93, 6.05]30% [20%, 45%]43%48%+0.23+0.242026-08-08 → 2026-08-30
tmin00Znearest365d29 1 QC3.56 [2.57, 4.63]3.58-0.51 [-2.32, 1.58]4.59 [3.22, 5.79]28% [15%, 42%]38%48%+0.39+0.392026-01-08 → 2026-08-30
tmin00Znearestall29 1 QC3.56 [2.54, 4.50]3.58-0.51 [-2.46, 1.72]4.59 [3.23, 5.69]28% [17%, 42%]38%48%+0.39+0.392026-01-08 → 2026-08-30
tmin12Zbilinear30d23 1 QC2.30 [1.93, 2.69]2.32+0.37 [-0.91, 1.70]2.93 [2.41, 3.38]26% [12%, 40%]61%74%+0.51+0.512026-08-08 → 2026-08-30
tmin12Zbilinear90d23 1 QC2.30 [1.90, 2.69]2.32+0.37 [-1.24, 1.95]2.93 [2.31, 3.38]26% [11%, 40%]61%74%+0.51+0.512026-08-08 → 2026-08-30
tmin12Zbilinear365d28 1 QC2.35 [2.02, 2.75]2.38+0.47 [-0.81, 1.72]2.99 [2.53, 3.44]25% [11%, 38%]57%75%+0.61+0.612026-01-08 → 2026-08-30
tmin12Zbilinearall28 1 QC2.35 [1.95, 2.71]2.38+0.47 [-0.97, 1.75]2.99 [2.42, 3.43]25% [12%, 38%]57%75%+0.61+0.612026-01-08 → 2026-08-30
tmin12Znearest30d23 1 QC2.31 [1.99, 2.66]2.31+0.06 [-1.19, 1.36]2.91 [2.46, 3.31]26% [11%, 38%]57%70%+0.50+0.512026-08-08 → 2026-08-30
tmin12Znearest90d23 1 QC2.31 [1.97, 2.67]2.31+0.06 [-1.51, 1.65]2.91 [2.40, 3.30]26% [8%, 39%]57%70%+0.50+0.512026-08-08 → 2026-08-30
tmin12Znearest365d28 1 QC2.35 [2.07, 2.70]2.36+0.19 [-1.08, 1.42]2.96 [2.59, 3.34]25% [10%, 38%]54%71%+0.61+0.612026-01-08 → 2026-08-30
tmin12Znearestall28 1 QC2.35 [2.00, 2.67]2.36+0.19 [-1.23, 1.45]2.96 [2.48, 3.31]25% [11%, 38%]54%71%+0.61+0.612026-01-08 → 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 KORD, lead day 7, 00Z bilinear tmax+20+100-10-202026-08-08: -0.54 °F2026-08-09: -3.61 °F2026-08-10: -9.42 °F2026-08-11: -5.05 °F2026-08-12: -3.62 °F2026-08-13: +4.9 °F2026-08-14: -5.96 °F2026-08-15: -3.17 °F2026-08-16: -2.36 °F2026-08-17: -5.64 °F2026-08-18: +1.87 °F2026-08-19: +0.76 °F2026-08-20: +1.48 °F2026-08-21: +1.55 °F2026-08-22: -0.06 °F2026-08-23: -4.55 °F2026-08-24: -4.53 °F2026-08-25: -3.12 °F2026-08-26: -1.89 °F2026-08-27: -7.52 °F2026-08-28: -14.8 °F2026-08-29: -5.1 °F2026-08-30: -5.59 °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
2026-08-30-5.59
2026-08-29-5.10
2026-08-28-14.80
2026-08-27-7.52
2026-08-26-1.89
2026-08-25-3.12
2026-08-24-4.53
2026-08-23-4.55
2026-08-22-0.06
2026-08-21+1.55
2026-08-20+1.48
2026-08-19+0.76
2026-08-18+1.87
2026-08-17-5.64
2026-08-16-2.36
2026-08-15-3.17
2026-08-14-5.96
2026-08-13+4.90
2026-08-12-3.62
2026-08-11-5.05
2026-08-10-9.42
2026-08-09-3.61
2026-08-08-0.54

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 7-20 to -18 °F: 1 day-18 to -16 °F: 0 days-16 to -14 °F: 1 day-14 to -12 °F: 0 days-12 to -10 °F: 2 days-10 to -8 °F: 2 days-8 to -6 °F: 1 day-6 to -4 °F: 8 days-4 to -2 °F: 6 days-2 to 0 °F: 3 days0 to 2 °F: 4 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| 4.55 · P90 |e| 10.96 °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
-20.00-18.001
-18.00-16.000
-16.00-14.001
-14.00-12.000
-12.00-10.002
-10.00-8.002
-8.00-6.001
-6.00-4.008
-4.00-2.006
-2.00+0.003
+0.00+2.004
+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
2026-08234.22 -3.30
2026-01610.04 -10.04

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 -0.44 [-2.00, 0.85] no
NCEP GFS 23 -1.39 [-2.82, 0.60] no
ECMWF IFS HRES 18 +0.51 [-1.28, 2.52] no
Persistence (baseline) 23 +0.39 [-1.66, 2.80] no

Cite this page

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

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