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 2

KORD · graphcast_ifs · lead 2

Target day = initialization date + 2 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
tmax00Zbilinear30d26 1 QC4.29 [2.97, 5.59]1.62-4.20 [-5.59, -2.70]4.74 [3.44, 5.77]8% [0%, 21%]15%19%-0.27+0.532026-08-03 → 2026-08-30
tmax00Zbilinear90d26 1 QC4.29 [2.93, 5.76]1.62-4.20 [-5.76, -2.69]4.74 [3.40, 5.91]8% [0%, 22%]15%19%-0.27+0.532026-08-03 → 2026-08-30
tmax00Zbilinear365d32 1 QC4.40 [3.23, 5.59]1.66-4.32 [-5.59, -3.00]4.85 [3.72, 5.78]9% [0%, 22%]16%19%+0.06+0.652026-01-03 → 2026-08-30
tmax00Zbilinearall32 1 QC4.40 [3.18, 5.61]1.66-4.32 [-5.61, -3.01]4.85 [3.75, 5.78]9% [0%, 23%]16%19%+0.06+0.652026-01-03 → 2026-08-30
tmax00Znearest30d26 1 QC4.29 [2.96, 5.61]1.63-4.18 [-5.61, -2.66]4.75 [3.43, 5.82]8% [0%, 21%]19%19%-0.27+0.522026-08-03 → 2026-08-30
tmax00Znearest90d26 1 QC4.29 [2.89, 5.79]1.63-4.18 [-5.79, -2.61]4.75 [3.36, 5.95]8% [0%, 22%]19%19%-0.27+0.522026-08-03 → 2026-08-30
tmax00Znearest365d32 1 QC4.42 [3.20, 5.62]1.68-4.33 [-5.62, -2.94]4.86 [3.68, 5.81]9% [0%, 22%]19%19%+0.06+0.652026-01-03 → 2026-08-30
tmax00Znearestall32 1 QC4.42 [3.17, 5.63]1.68-4.33 [-5.63, -2.97]4.86 [3.74, 5.81]9% [0%, 23%]19%19%+0.06+0.652026-01-03 → 2026-08-30
tmax12Zbilinear30d26 1 QC4.38 [3.19, 5.44]1.51-4.35 [-5.44, -3.12]4.73 [3.60, 5.58]4% [0%, 11%]15%23%-0.29+0.562026-08-03 → 2026-08-30
tmax12Zbilinear90d26 1 QC4.38 [3.21, 5.53]1.51-4.35 [-5.53, -3.14]4.73 [3.62, 5.66]4% [0%, 11%]15%23%-0.29+0.562026-08-03 → 2026-08-30
tmax12Zbilinear365d31 1 QC4.49 [3.38, 5.47]1.56-4.47 [-5.47, -3.31]4.85 [3.86, 5.60]3% [0%, 10%]16%23%-0.03+0.652026-01-03 → 2026-08-30
tmax12Zbilinearall31 1 QC4.49 [3.37, 5.50]1.56-4.47 [-5.50, -3.32]4.85 [3.81, 5.63]3% [0%, 10%]16%23%-0.03+0.652026-01-03 → 2026-08-30
tmax12Znearest30d26 1 QC4.36 [3.16, 5.45]1.53-4.34 [-5.45, -3.09]4.72 [3.60, 5.60]4% [0%, 11%]15%23%-0.29+0.552026-08-03 → 2026-08-30
tmax12Znearest90d26 1 QC4.36 [3.13, 5.54]1.53-4.34 [-5.54, -3.07]4.72 [3.56, 5.69]4% [0%, 11%]15%23%-0.29+0.552026-08-03 → 2026-08-30
tmax12Znearest365d31 1 QC4.50 [3.38, 5.49]1.58-4.49 [-5.49, -3.34]4.87 [3.88, 5.66]3% [0%, 10%]16%23%-0.03+0.652026-01-03 → 2026-08-30
tmax12Znearestall31 1 QC4.50 [3.36, 5.54]1.58-4.49 [-5.54, -3.31]4.87 [3.82, 5.70]3% [0%, 10%]16%23%-0.03+0.652026-01-03 → 2026-08-30
tmin00Zbilinear30d26 1 QC1.39 [1.08, 1.83]1.38+0.09 [-0.55, 0.73]1.85 [1.50, 2.34]46% [27%, 68%]69%88%+0.57+0.582026-08-03 → 2026-08-30
tmin00Zbilinear90d26 1 QC1.39 [1.02, 1.97]1.38+0.09 [-0.58, 0.81]1.85 [1.43, 2.44]46% [25%, 75%]69%88%+0.57+0.582026-08-03 → 2026-08-30
tmin00Zbilinear365d32 1 QC1.51 [1.15, 2.00]1.52-0.30 [-1.36, 0.51]1.93 [1.51, 2.42]44% [25%, 65%]66%88%+0.62+0.632026-01-03 → 2026-08-30
tmin00Zbilinearall32 1 QC1.51 [1.14, 2.03]1.52-0.30 [-1.26, 0.44]1.93 [1.54, 2.44]44% [25%, 66%]66%88%+0.62+0.632026-01-03 → 2026-08-30
tmin00Znearest30d26 1 QC1.39 [1.12, 1.82]1.40-0.25 [-0.89, 0.37]1.85 [1.44, 2.36]50% [32%, 69%]65%88%+0.57+0.582026-08-03 → 2026-08-30
tmin00Znearest90d26 1 QC1.39 [1.04, 1.91]1.40-0.25 [-0.96, 0.44]1.85 [1.34, 2.46]50% [29%, 75%]65%88%+0.57+0.582026-08-03 → 2026-08-30
tmin00Znearest365d32 1 QC1.57 [1.16, 2.12]1.53-0.64 [-1.69, 0.15]2.02 [1.47, 2.55]44% [25%, 66%]59%84%+0.61+0.632026-01-03 → 2026-08-30
tmin00Znearestall32 1 QC1.57 [1.16, 2.18]1.53-0.64 [-1.62, 0.10]2.02 [1.52, 2.59]44% [23%, 67%]59%84%+0.61+0.632026-01-03 → 2026-08-30
tmin12Zbilinear30d26 1 QC1.41 [1.11, 1.80]1.41+0.03 [-0.77, 0.66]1.91 [1.49, 2.41]50% [38%, 63%]69%88%+0.56+0.572026-08-03 → 2026-08-30
tmin12Zbilinear90d26 1 QC1.41 [1.04, 1.91]1.41+0.03 [-0.92, 0.69]1.91 [1.39, 2.47]50% [36%, 67%]69%88%+0.56+0.572026-08-03 → 2026-08-30
tmin12Zbilinear365d31 1 QC1.53 [1.14, 2.07]1.52-0.33 [-1.65, 0.51]2.09 [1.47, 2.70]45% [29%, 60%]68%87%+0.61+0.632026-01-03 → 2026-08-30
tmin12Zbilinearall31 1 QC1.53 [1.12, 2.09]1.52-0.33 [-1.44, 0.47]2.09 [1.51, 2.71]45% [30%, 61%]68%87%+0.61+0.632026-01-03 → 2026-08-30
tmin12Znearest30d26 1 QC1.46 [1.18, 1.83]1.43-0.31 [-1.14, 0.29]1.90 [1.45, 2.41]38% [27%, 50%]73%92%+0.55+0.572026-08-03 → 2026-08-30
tmin12Znearest90d26 1 QC1.46 [1.09, 1.89]1.43-0.31 [-1.28, 0.34]1.90 [1.33, 2.47]38% [25%, 52%]73%92%+0.55+0.572026-08-03 → 2026-08-30
tmin12Znearest365d31 1 QC1.65 [1.18, 2.25]1.54-0.68 [-2.01, 0.14]2.18 [1.45, 2.96]35% [23%, 50%]71%90%+0.58+0.622026-01-03 → 2026-08-30
tmin12Znearestall31 1 QC1.65 [1.21, 2.28]1.54-0.68 [-1.83, 0.11]2.18 [1.47, 2.91]35% [23%, 50%]71%90%+0.58+0.622026-01-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -6.17 °F2026-08-04: -5.57 °F2026-08-05: -6.67 °F2026-08-06: -5.24 °F2026-08-07: -5.27 °F2026-08-08: -4.1 °F2026-08-09: -6.66 °F2026-08-10: -9.45 °F2026-08-11: -5.58 °F2026-08-12: -3.69 °F2026-08-13: -3.2 °F2026-08-14: -3.67 °F2026-08-15: -1.71 °F2026-08-16: -4.04 °F2026-08-17: -3.66 °F2026-08-18: +1.24 °F2026-08-19: -2.1 °F2026-08-20: +0.04 °F2026-08-21: -0.69 °F2026-08-22: -4.11 °F2026-08-23: -3.79 °F2026-08-24: -6.07 °F2026-08-25: -5.14 °F2026-08-26: -4.3 °F2026-08-27: -4.86 °F2026-08-30: -4.64 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.64
2026-08-29—
2026-08-28—
2026-08-27-4.86
2026-08-26-4.30
2026-08-25-5.14
2026-08-24-6.07
2026-08-23-3.79
2026-08-22-4.11
2026-08-21-0.69
2026-08-20+0.04
2026-08-19-2.10
2026-08-18+1.24
2026-08-17-3.66
2026-08-16-4.04
2026-08-15-1.71
2026-08-14-3.67
2026-08-13-3.20
2026-08-12-3.69
2026-08-11-5.58
2026-08-10-9.45
2026-08-09-6.66
2026-08-08-4.10
2026-08-07-5.27
2026-08-06-5.24
2026-08-05-6.67
2026-08-04-5.57
2026-08-03-6.17

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KORD, lead day 2-10 to -9 °F: 1 day-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 5 days-6 to -5 °F: 9 days-5 to -4 °F: 6 days-4 to -3 °F: 5 days-3 to -2 °F: 1 day-2 to -1 °F: 1 day-1 to 0 °F: 2 days0 to 1 °F: 1 day1 to 2 °F: 1 day2 to 3 °F: 0 days3 to 4 °F: 0 days4 to 5 °F: 0 days5 to 6 °F: 0 days6 to 7 °F: 0 days7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 4.75 · P90 |e| 6.61 °F-100+10 °Fn = 32 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
-10.00-9.001
-9.00-8.000
-8.00-7.000
-7.00-6.005
-6.00-5.009
-5.00-4.006
-4.00-3.005
-3.00-2.001
-2.00-1.001
-1.00+0.002
+0.00+1.001
+1.00+2.001
+2.00+3.000
+3.00+4.000
+4.00+5.000
+5.00+6.000
+6.00+7.000
+7.00+8.000
+8.00+9.000
+9.00+10.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08264.29 -4.20
2026-0164.87 -4.87

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 31
GraphCast (IFS init)2026-01-03 → 2026-08-30 31

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 26 +0.67 [0.27, 1.35] yes
Aurora (IFS init) 1 +3.21 [3.21, 3.21] yes
FourCastNet v2 (IFS init) 1 +4.62 [4.62, 4.62] yes
NCEP GFS 26 +1.26 [0.11, 2.59] yes
ECMWF IFS HRES 20 +1.01 [-0.09, 2.41] no
Pangu-Weather (IFS init) 1 +3.20 [3.20, 3.20] yes
Persistence (baseline) 26 +0.91 [-0.18, 2.23] no

Cite this page

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

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

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