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 · ECMWF AIFS Single · lead day 0

KORD · aifs_single · lead 0

Target day = initialization date + 0 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, aifs-single-gpid5, starting 2026-08-01 — 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
tmax00Zbilinear30d30 1 QC3.20 [2.73, 3.75]1.03-3.17 [-3.73, -2.67]3.48 [2.97, 4.01]7% [0%, 13%]13%47%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 1 QC3.20 [2.73, 3.80]1.03-3.17 [-3.79, -2.68]3.48 [2.99, 4.09]7% [0%, 16%]13%47%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 1 QC3.20 [2.73, 3.75]1.03-3.17 [-3.75, -2.67]3.48 [2.98, 4.02]7% [0%, 17%]13%47%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 1 QC3.20 [2.72, 3.78]1.03-3.17 [-3.78, -2.68]3.48 [2.99, 4.07]7% [0%, 18%]13%47%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 1 QC2.78 [2.29, 3.35]1.11-2.74 [-3.34, -2.22]3.09 [2.52, 3.69]7% [0%, 13%]33%63%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 1 QC2.78 [2.29, 3.44]1.11-2.74 [-3.44, -2.24]3.09 [2.52, 3.78]7% [0%, 16%]33%63%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 1 QC2.78 [2.29, 3.40]1.11-2.74 [-3.39, -2.22]3.09 [2.52, 3.73]7% [0%, 17%]33%63%——2026-08-01 → 2026-08-30
tmax00Znearestall30 1 QC2.78 [2.31, 3.40]1.11-2.74 [-3.40, -2.25]3.09 [2.52, 3.75]7% [0%, 18%]33%63%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 1 QC1.55 [1.19, 1.97]1.61+0.69 [-0.20, 1.47]1.99 [1.56, 2.40]40% [30%, 53%]63%87%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 1 QC1.55 [1.12, 2.13]1.61+0.69 [-0.41, 1.79]1.99 [1.47, 2.59]40% [26%, 55%]63%87%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 1 QC1.55 [1.09, 2.11]1.61+0.69 [-0.58, 1.76]1.99 [1.42, 2.54]40% [27%, 55%]63%87%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 1 QC1.55 [1.12, 2.19]1.61+0.69 [-0.43, 1.82]1.99 [1.46, 2.64]40% [26%, 56%]63%87%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 1 QC1.76 [1.42, 2.15]1.77+0.07 [-0.97, 0.99]2.04 [1.64, 2.42]17% [10%, 27%]67%87%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 1 QC1.76 [1.39, 2.23]1.77+0.07 [-1.23, 1.33]2.04 [1.60, 2.49]17% [7%, 27%]67%87%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 1 QC1.76 [1.35, 2.20]1.77+0.07 [-1.41, 1.29]2.04 [1.56, 2.45]17% [7%, 29%]67%87%——2026-08-01 → 2026-08-30
tmin00Znearestall30 1 QC1.76 [1.40, 2.25]1.77+0.07 [-1.20, 1.33]2.04 [1.60, 2.52]17% [5%, 29%]67%87%——2026-08-01 → 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 ECMWF AIFS Single at KORD, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-01: -0.03 °F2026-08-02: -2.95 °F2026-08-03: -5.07 °F2026-08-04: -2.91 °F2026-08-05: -3.99 °F2026-08-06: -4.31 °F2026-08-07: -4.45 °F2026-08-08: -2.59 °F2026-08-09: -5.09 °F2026-08-10: -7.06 °F2026-08-11: -2.52 °F2026-08-12: -3.69 °F2026-08-13: -1.72 °F2026-08-14: -3.3 °F2026-08-15: +0.36 °F2026-08-16: -2.24 °F2026-08-17: -4.55 °F2026-08-18: -3.2 °F2026-08-19: -2.64 °F2026-08-20: -1.85 °F2026-08-21: -3.56 °F2026-08-22: -3.02 °F2026-08-23: -2.82 °F2026-08-24: -3.1 °F2026-08-25: -4.34 °F2026-08-26: -2.07 °F2026-08-27: -2.29 °F2026-08-28: -3.19 °F2026-08-29: -2.97 °F2026-08-30: -4.02 °F2026-08-012026-08-30°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 (30 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.02
2026-08-29-2.97
2026-08-28-3.19
2026-08-27-2.29
2026-08-26-2.07
2026-08-25-4.34
2026-08-24-3.10
2026-08-23-2.82
2026-08-22-3.02
2026-08-21-3.56
2026-08-20-1.85
2026-08-19-2.64
2026-08-18-3.20
2026-08-17-4.55
2026-08-16-2.24
2026-08-15+0.36
2026-08-14-3.30
2026-08-13-1.72
2026-08-12-3.69
2026-08-11-2.52
2026-08-10-7.06
2026-08-09-5.09
2026-08-08-2.59
2026-08-07-4.45
2026-08-06-4.31
2026-08-05-3.99
2026-08-04-2.91
2026-08-03-5.07
2026-08-02-2.95
2026-08-01-0.03

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KORD, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 1 day-7 to -6 °F: 0 days-6 to -5 °F: 2 days-5 to -4 °F: 5 days-4 to -3 °F: 8 days-3 to -2 °F: 10 days-2 to -1 °F: 2 days-1 to 0 °F: 1 day0 to 1 °F: 1 day1 to 2 °F: 0 days2 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| 3.06 · P90 |e| 4.6 °F-100+10 °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
-10.00-9.000
-9.00-8.000
-8.00-7.001
-7.00-6.000
-6.00-5.002
-5.00-4.005
-4.00-3.008
-3.00-2.0010
-2.00-1.002
-1.00+0.001
+0.00+1.001
+1.00+2.000
+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
2026-08303.20 -3.17

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-01 → 2026-08-30 30
ECMWF AIFS Single2026-08-01 → 2026-08-30 30

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means ECMWF AIFS Single has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
Aurora (GFS init) 2 -1.61 [-3.20, -0.03] yes
Aurora (IFS init) 3 +0.44 [-0.48, 1.25] no
FourCastNet v2 (GFS init) 2 +1.97 [1.66, 2.28] yes
FourCastNet v2 (IFS init) 3 +0.03 [-1.80, 1.66] no
NCEP GFS 30 +0.94 [0.22, 1.53] yes
GraphCast (GFS init) 2 -0.02 [-0.47, 0.43] no
GraphCast (IFS init) 28 -0.27 [-0.82, 0.17] no
ECMWF IFS HRES 24 +0.59 [-0.29, 1.46] no
Pangu-Weather (GFS init) 2 +1.13 [0.40, 1.86] yes
Pangu-Weather (IFS init) 3 +0.68 [-0.09, 1.07] no

Cite this page

ShortCastCheck, KORD aifs_single lead 0, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KORD/model/aifs_single/lead/0/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KORD (Chicago O'Hare), model aifs_single, lead day 0. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KORD/model/aifs_single/lead/0/

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